技术领域technical field
本发明涉及星球车遥操作、移动路径规划领域，具体而言，涉及一种基于轮地匹配的星球车路径规划方法及装置。The present invention relates to the field of planetary vehicle teleoperation and movement path planning, in particular to a method and device for planning a planetary vehicle path based on wheel-ground matching.
背景技术Background technique
星球车移动路径规划方法是在地外环境下通过立体视觉或者其他深度传感器感知周边地形情况，生成三维地形产品，基于深度信息提取坡度、坡向、粗糙度等多维的非结构地形属性，结合星球车的移动性能和约束来构建可通行代价图层，在代价图上进行全局路径搜索，获得星球车无碰撞、低代价或者安全、路径最短的移动路径，同时考虑星球车的运动学进行轨迹平滑性优化。The mobile path planning method of the planetary vehicle is to perceive the surrounding terrain through stereo vision or other depth sensors in the extraterrestrial environment, generate 3D terrain products, and extract multi-dimensional non-structural terrain attributes such as slope, aspect, and roughness based on depth information, and combine the The mobile performance and constraints of the car are used to construct a passable cost layer, and a global path search is performed on the cost map to obtain a collision-free, low-cost or safe, shortest path for the planetary vehicle, while considering the kinematics of the planetary vehicle for trajectory smoothing performance optimization.
移动路径规划是地外天体移动星球车探测重要的一个环节，在复杂危险的环境中星球车移动存在较大的安全隐患。目前主要的星球车路径规划算法是把星球车简化为质点进行建模，在识别车体移动障碍后，根据车体尺寸膨胀障碍物，再进行质点模型下的路径点搜索，最后采用圆弧拟合路径点形成连续平滑的移动路径。随着月球探测和星际探测的逐步推进，人类不断探测科学价值更高的地外区域，探索的地形环境也越来越复杂，面对障碍物密集的区域基于质点膨胀的车体路径规划较可能无法搜索出有效路径，或者无法搜索出星球车最优的路径。Movement path planning is an important link in the detection of extraterrestrial celestial bodies by mobile planetary rovers, and the movement of planetary rovers in complex and dangerous environments has great potential safety hazards. At present, the main path planning algorithm for planetary vehicles is to simplify the planetary vehicles into mass points for modeling. After identifying the movement obstacles of the vehicle body, the obstacles are expanded according to the size of the vehicle body, and then the path point search is carried out under the mass point model. Combine the path points to form a continuous and smooth moving path. With the gradual advancement of lunar exploration and interstellar exploration, human beings continue to explore extraterrestrial areas with higher scientific value, and the terrain environment to be explored is becoming more and more complex. Facing areas with dense obstacles, vehicle body path planning based on particle expansion is more likely An effective path cannot be searched out, or the optimal path of the planetary rover cannot be searched out.
发明内容Contents of the invention
本发明为了解决上述背景技术中的至少一个技术问题，提出了一种基于轮地匹配的星球车路径规划方法及装置。In order to solve at least one technical problem in the above-mentioned background technology, the present invention proposes a method and device for path planning of planetary vehicles based on wheel-ground matching.
为了实现上述目的，根据本发明的一个方面，提供了一种基于轮地匹配的星球车路径规划方法，该方法包括：In order to achieve the above object, according to one aspect of the present invention, a method for path planning of planetary vehicles based on wheel-ground matching is provided, the method includes:
基于数字高程地形图构建星球车单轮移动综合代价图；Constructing a comprehensive cost map for single-wheel movement of planetary vehicles based on digital elevation terrain maps;
在所述星球车单轮移动综合代价图上进行星球车多轮移动构型的全局路径规划，得到路径点集；Carry out the global path planning of the multi-wheel mobile configuration of the planetary vehicle on the comprehensive cost map of the single-wheel movement of the planetary vehicle, and obtain the set of path points;
从所述路径点集中提取出关键点，基于所述关键点进行曲线拟合得到移动路径，针对所述移动路径计算整车移动代价，基于所述整车移动代价调整关键点以不断优化所述移动路径，最终得到最优路径。Extract key points from the set of path points, perform curve fitting based on the key points to obtain a moving path, calculate the moving cost of the vehicle for the moving path, adjust the key points based on the moving cost of the whole vehicle to continuously optimize the Move the path, and finally get the optimal path.
可选的，所述基于数字高程地形图构建星球车单轮移动综合代价图，具体包括：Optionally, the construction of a comprehensive cost map for single-wheel movement of planetary vehicles based on digital elevation topographic maps specifically includes:
根据星球车单轮的尺寸构建星球车单轮的评价窗口；Construct the evaluation window of the single wheel of the planetary vehicle according to the size of the single wheel of the planetary vehicle;
根据所述评价窗口计算所述数字高程地形图中各位置的综合代价值；Calculate the comprehensive cost value of each position in the digital elevation topographic map according to the evaluation window;
根据所述综合代价值构建星球车单轮移动综合代价图。According to the comprehensive cost value, the comprehensive cost map of the single-wheel movement of the planetary vehicle is constructed.
可选的，所述根据所述评价窗口计算所述数字高程地形图中各位置的综合代价值，具体包括：Optionally, the calculating the comprehensive cost value of each position in the digital elevation topographic map according to the evaluation window specifically includes:
根据所述评价窗口确定所述数字高程地形图中各位置的坡度、粗糙度以及平坦度；Determine the slope, roughness and flatness of each position in the digital elevation topographic map according to the evaluation window;
根据所述数字高程地形图中各位置的坡度、粗糙度以及平坦度确定所述数字高程地形图中各位置的综合代价值。The comprehensive cost value of each position in the digital elevation topographic map is determined according to the slope, roughness and flatness of each position in the digital elevation topographic map.
可选的，所述在所述星球车单轮移动综合代价图上进行星球车多轮移动构型的全局路径规划，得到路径点集，具体包括：Optionally, the global path planning of the multi-wheel mobile configuration of the planetary vehicle is performed on the comprehensive cost map of the single-wheel movement of the planetary vehicle to obtain a set of path points, which specifically includes:
在确定目标路径点对应的下一个路径点时，根据所述目标路径点以及所述目标路径点的相邻位置点计算星球车的航向；When determining the next waypoint corresponding to the target waypoint, calculate the heading of the star vehicle according to the target waypoint and the adjacent position points of the target waypoint;
根据所述目标路径点以及所述航向确定星球车的每个车轮各自的位置；determining the respective positions of each wheel of the planetary vehicle according to the target waypoint and the heading;
根据每个车轮各自的位置计算车轮位置的综合代价值总和；Calculate the sum of the comprehensive cost values of the wheel positions according to the respective positions of each wheel;
将所述目标路径点对应的车轮位置的综合代价值总和最小的相邻位置点确定为所述目标路径点对应的下一个路径点。Determine the adjacent position point with the minimum sum of comprehensive cost values of the wheel positions corresponding to the target way point as the next way point corresponding to the target way point.
可选的，所述从所述路径点集中提取出关键点，具体包括：Optionally, the extracting key points from the set of waypoints specifically includes:
根据所述路径点集中连续三个路径点之间的转弯角度进行关键点提取。The key point is extracted according to the turning angle between three consecutive waypoints in the set of waypoints.
可选的，所述基于所述整车移动代价调整关键点以不断优化所述移动路径，最终得到最优路径，具体包括：Optionally, the adjusting key points based on the vehicle movement cost to continuously optimize the movement path, and finally obtain the optimal path, specifically includes:
分别针对每个所述关键点，将所述关键点分别调整到各个相邻栅格点后进行曲线拟合得到新的移动路径，计算该新的移动路径的整车移动代价，进而根据该新的移动路径的整车移动代价确定出各所述关键点各自对应的最优相邻栅格点；For each of the key points, adjust the key points to each adjacent grid point and perform curve fitting to obtain a new moving path, calculate the vehicle movement cost of the new moving path, and then according to the new The vehicle movement cost of the moving path determines the respective optimal adjacent grid points corresponding to each of the key points;
将各所述关键点分别调整到各自对应的所述最优相邻栅格点后进行曲线拟合，得到最优移动路径。Curve fitting is performed after adjusting each of the key points to the respective optimal adjacent grid points to obtain an optimal moving path.
可选的，所述针对所述移动路径计算整车移动代价，具体包括：Optionally, the calculating the vehicle movement cost for the movement path specifically includes:
对所述移动路径进行离散化，得到离散路径点以及每个所述离散路径点各自对应的偏航角；Discretizing the moving path to obtain discrete path points and a yaw angle corresponding to each of the discrete path points;
根据所述偏航角确定星球车在每个所述离散路径点处的各车轮的位置；determining the positions of the wheels of the planetary vehicle at each of the discrete waypoints according to the yaw angle;
根据星球车在每个所述离散路径点处的各车轮的位置以及所述数字高程地形图中各位置的综合代价值，确定每个所述离散路径点各自对应的综合代价值；According to the position of each wheel of the planetary vehicle at each of the discrete waypoints and the comprehensive cost value of each position in the digital elevation map, determine the respective comprehensive cost value corresponding to each of the discrete waypoints;
计算星球车在每个所述离散路径点处的车体倾斜角度和车底板离地间隙；Calculating the inclination angle of the vehicle body and the ground clearance of the vehicle floor at each of the discrete path points of the planetary vehicle;
根据每个所述离散路径点各自对应综合代价值、车体倾斜角度和车底板离地间隙，确定出所述整车移动代价。The moving cost of the whole vehicle is determined according to the comprehensive cost value, the tilt angle of the vehicle body and the ground clearance of the vehicle floor corresponding to each of the discrete path points.
为了实现上述目的，根据本发明的另一方面，提供了一种基于轮地匹配的星球车路径规划装置，该装置包括：In order to achieve the above object, according to another aspect of the present invention, a planetary vehicle path planning device based on wheel-ground matching is provided, the device includes:
单轮移动综合代价图构建单元，用于基于数字高程地形图构建星球车单轮移动综合代价图；A single-wheel mobile comprehensive cost map construction unit is used to construct a single-wheel mobile comprehensive cost map for planetary vehicles based on digital elevation terrain maps;
多轮移动构型全局路径规划单元，用于在所述星球车单轮移动综合代价图上进行星球车多轮移动构型的全局路径规划，得到路径点集；The multi-wheel mobile configuration global path planning unit is used to perform the global path planning of the multi-wheel mobile configuration of the planetary vehicle on the comprehensive cost map of the single-wheel movement of the planetary vehicle to obtain a set of path points;
轨迹拟合及优化单元，用于从所述路径点集中提取出关键点，基于所述关键点进行曲线拟合得到移动路径，针对所述移动路径计算整车移动代价，基于所述整车移动代价调整关键点以不断优化所述移动路径，最终得到最优路径。The trajectory fitting and optimization unit is used to extract key points from the set of path points, perform curve fitting based on the key points to obtain a movement path, calculate the movement cost of the vehicle for the movement path, and calculate the vehicle movement cost based on the movement of the vehicle. The cost adjusts the key points to continuously optimize the moving path, and finally obtains the optimal path.
为了实现上述目的，根据本发明的另一方面，还提供了一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述基于轮地匹配的星球车路径规划方法的步骤。In order to achieve the above object, according to another aspect of the present invention, a computer device is also provided, including a memory, a processor, and a computer program stored in the memory and operable on the processor, the processor executes the computer The program is the steps to realize the above-mentioned path planning method for planetary vehicles based on wheel-ground matching.
为了实现上述目的，根据本发明的另一方面，还提供了一种计算机可读存储介质，其上存储有计算机程序/指令，该计算机程序/指令被处理器执行时实现上述基于轮地匹配的星球车路径规划方法的步骤。In order to achieve the above object, according to another aspect of the present invention, there is also provided a computer-readable storage medium, on which computer programs/instructions are stored, and when the computer program/instructions are executed by a processor, the above-mentioned wheel-based matching The steps of the planetary rover path planning method.
本发明的有益效果为：The beneficial effects of the present invention are:
本发明先基于数字高程地形图构建星球车单轮移动综合代价图，然后在所述星球车单轮移动综合代价图上进行星球车多轮移动构型的全局路径规划，得到路径点集，进而从所述路径点集中提取出关键点，基于所述关键点进行曲线拟合得到移动路径，针对所述移动路径计算整车移动代价，基于所述整车移动代价调整关键点以不断优化所述移动路径，最终得到最优路径，本发明从单轮-多轮-整车三个层次的模型对星球车可通行代价进行精细分析，最终确定出最优的移动路径，由此提高了星球车路径规划的准确性。The present invention first constructs a comprehensive cost map for single-wheel movement of planetary vehicles based on digital elevation terrain maps, and then performs global path planning for multi-wheel movement configurations of planetary vehicles on the comprehensive cost map for single-wheel movement of planetary vehicles to obtain a set of path points, and then Extract key points from the set of path points, perform curve fitting based on the key points to obtain a moving path, calculate the moving cost of the vehicle for the moving path, adjust the key points based on the moving cost of the whole vehicle to continuously optimize the The moving path finally obtains the optimal path. The present invention conducts a detailed analysis of the traversable cost of the planetary vehicle from the three-level model of single-wheel-multi-wheel-whole vehicle, and finally determines the optimal moving path, thus improving the efficiency of the planetary vehicle. Accuracy of path planning.
附图说明Description of drawings
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。在附图中：In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are For some embodiments of the present invention, those skilled in the art can also obtain other drawings based on these drawings without creative work. In the attached picture:
图1是本发明实施例基于轮地匹配的星球车路径规划方法的第一流程图；Fig. 1 is the first flowchart of the path planning method for planetary vehicles based on wheel-ground matching in an embodiment of the present invention;
图2是本发明实施例基于轮地匹配的星球车路径规划方法的第二流程图；Fig. 2 is the second flowchart of the path planning method for planetary vehicles based on wheel-ground matching in an embodiment of the present invention;
图3是本发明实施例基于轮地匹配的星球车路径规划方法的第三流程图；Fig. 3 is the third flowchart of the path planning method for planetary vehicles based on wheel-ground matching according to the embodiment of the present invention;
图4是本发明实施例基于轮地匹配的星球车路径规划方法的第四流程图；Fig. 4 is the fourth flow chart of the path planning method for planetary vehicles based on wheel-ground matching according to the embodiment of the present invention;
图5是本发明实施例基于轮地匹配的星球车路径规划方法的第五流程图；Fig. 5 is a fifth flow chart of a method for planning a planetary vehicle path based on wheel-ground matching according to an embodiment of the present invention;
图6是本发明实施例基于轮地匹配的星球车路径规划方法的第六流程图；Fig. 6 is the sixth flow chart of the method for planning the path of planetary vehicles based on wheel-ground matching according to the embodiment of the present invention;
图7是本发明实施例星球车路径规划方法的整体流程图；FIG. 7 is an overall flow chart of a method for planning a planetary vehicle path according to an embodiment of the present invention;
图8是本发明实施例基于单轮的星球车移动综合代价图计算流程；Fig. 8 is the calculation process of the comprehensive cost map based on the single-wheel movement of the planetary vehicle according to the embodiment of the present invention;
图9是本发明实施例多轮移动构型的综合代价计算示意图；Fig. 9 is a schematic diagram of comprehensive cost calculation of a multi-wheel mobile configuration according to an embodiment of the present invention;
图10是本发明实施例提取关键点的方法示意图；Fig. 10 is a schematic diagram of a method for extracting key points according to an embodiment of the present invention;
图11是本发明实施例圆弧拟合示意图；Fig. 11 is a schematic diagram of arc fitting according to an embodiment of the present invention;
图12是本发明实施例终点允许原地转弯的拟合路径图；Fig. 12 is a fitting path diagram of an in-situ turn allowed at the end point of the embodiment of the present invention;
图13是本发明实施例起点原地转弯规划示意图；Fig. 13 is a schematic diagram of turning plan in situ at the starting point according to the embodiment of the present invention;
图14是本发明实施例整车轨迹综合代价图计算和轨迹优化流程示意图；Fig. 14 is a schematic diagram of the calculation and trajectory optimization process of the vehicle trajectory comprehensive cost map according to the embodiment of the present invention;
图15是本发明实施例基于轮地匹配的星球车路径规划装置的结构框图；Fig. 15 is a structural block diagram of a planetary vehicle path planning device based on wheel-ground matching according to an embodiment of the present invention;
图16是本发明实施例计算机设备示意图。Fig. 16 is a schematic diagram of computer equipment according to an embodiment of the present invention.
具体实施方式Detailed ways
为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分的实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本发明保护的范围。In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only It is an embodiment of a part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
需要说明的是，本发明的说明书和权利要求书及上述附图中的术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。It should be noted that the terms "comprising" and "having" in the description and claims of the present invention and the above drawings, as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, including a series of steps or units A process, method, system, product or device is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to the process, method, product or device.
需要说明的是，在不冲突的情况下，本发明中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本发明。It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and examples.
本发明要解决的技术问题是：实现了一种基于轮地匹配的星球车移动路径规划方法及装置，解决以往质点模型下移动路径规划中障碍膨胀区域过大，与实际车轮轨迹不匹配的问题，例如无法搜索出车体跨过障碍的路径。建立星球车多轮模型综合代价的精细路径规划。解决以往单一栅格的坡度、粗糙度、平坦度难以准确评估车体与实际地形相互作用的问题，计算了轮地实际接触区域用以评估车体倾斜度、车体离地间隙。解决以往局部质点移动路径未进行车轮实际移动轨迹代价优化的问题，建立曲率行走、原地转弯等车轮轨迹综合代价优化，实现车轮真实移动轨迹的精准路径规划。The technical problem to be solved by the present invention is to realize a method and device for planning the moving path of the planetary vehicle based on wheel-ground matching, and solve the problem that the obstacle expansion area is too large in the moving path planning under the particle model in the past and does not match the actual wheel trajectory. , for example, it is not possible to search for a path for the car body to cross obstacles. Establish the fine path planning of the comprehensive cost of the multi-wheel model of the planetary vehicle. To solve the problem that the slope, roughness, and flatness of a single grid are difficult to accurately evaluate the interaction between the car body and the actual terrain, the actual contact area of the wheel and the ground is calculated to evaluate the inclination of the car body and the ground clearance of the car body. To solve the problem that the cost optimization of the actual wheel trajectory has not been carried out in the local particle movement path in the past, the comprehensive cost optimization of the wheel trajectory such as curvature walking and turning in place is established, and the precise path planning of the real wheel trajectory is realized.
图7是本发明实施例星球车路径规划方法的整体流程图，如图7所示，本发明的技术方案大致包括：路径规划考虑星球车的移动构型和轮地的相互匹配，构建单轮-多轮移动机构-整车的移动可通行代价计算模型，三个层次的模型对星球车可通行代价进行精细分析，而不再当成质点模型。具体说建立基于轮地接触的单轮栅格计算粗糙度、平坦度、坡度，分析单轮移动代价；全局路径搜索时，基于车体不同偏航计算多轮土壤接触区域的路径代价，并搜索最优移动路径点；最后局部轨迹曲线拟合和最小代价寻优时，基于车体当前移动形态计算车体倾斜度、车轮安全性、车底板与地面的最大间隙，加权形成整车车轮移动轨迹代价，进行关键点位置调整、曲线拟合、代价计算、移动轨迹寻优，迭代输出移动轨迹。Fig. 7 is the overall flowchart of the path planning method of the planetary vehicle in the embodiment of the present invention. As shown in Fig. 7, the technical solution of the present invention generally includes: path planning considers the mobile configuration of the planetary vehicle and the mutual matching of the wheel and the ground, and constructs a single wheel -Multi-wheel mobile mechanism-the calculation model of the mobile traversable cost of the whole vehicle, the three-level model conducts a detailed analysis of the traversable cost of the planetary vehicle, and is no longer regarded as a particle model. Specifically, a single-wheel grid based on wheel-ground contact is established to calculate the roughness, flatness, and slope, and to analyze the movement cost of a single wheel; when searching for a global path, calculate the path cost of the multi-wheel soil contact area based on the different yaws of the vehicle body, and search Optimal moving path point; in the final local trajectory curve fitting and minimum cost optimization, the vehicle body inclination, wheel safety, and the maximum gap between the vehicle floor and the ground are calculated based on the current movement form of the vehicle body, and weighted to form the vehicle wheel movement trajectory Cost, key point position adjustment, curve fitting, cost calculation, movement trajectory optimization, iterative output movement trajectory.
基于轮地匹配的星球车路径规划方法，具体指：1)在环境建模阶段基于单轮栅格来计算粗糙度、平坦度、坡度环境代价；2)在单轮可通行代价图上进行多轮移动形态的代价计算，全局搜索出最优的路径点集。3)在局部优化阶段，在路径点集中基于运动约束规则提取关键点，基于关键点约束的区域范围内进行路径点的路径曲线拟合，计算曲率运动、直线运动及原地转弯等基本运动方式的综合代价，同时加入车体倾斜度、底板与地面最大间隙的代价函数进行最后轨迹的迭代优化。The path planning method of planetary vehicles based on wheel-ground matching refers specifically to: 1) calculating roughness, flatness, and slope environmental costs based on single-wheel grids in the environmental modeling stage; The cost calculation of the wheel movement form, and the optimal path point set is searched globally. 3) In the local optimization stage, key points are extracted based on motion constraint rules in the path point set, and path curve fitting of path points is performed within the area constrained by key points, and basic motion modes such as curvature motion, straight line motion, and in-situ turning are calculated. At the same time, the cost function of the inclination of the car body and the maximum gap between the floor and the ground is added to iteratively optimize the final trajectory.
图1是本发明实施例基于轮地匹配的星球车路径规划方法的第一流程图，如图1所示，在本发明一个实施例中，本发明的基于轮地匹配的星球车路径规划方法包括步骤S101至步骤S103。Fig. 1 is the first flowchart of the path planning method for planetary vehicles based on wheel-ground matching according to the embodiment of the present invention. It includes step S101 to step S103.
步骤S101，基于数字高程地形图构建星球车单轮移动综合代价图。Step S101, constructing a comprehensive cost map for single-wheel movement of the planetary vehicle based on the digital elevation terrain map.
步骤S102，在所述星球车单轮移动综合代价图上进行星球车多轮移动构型的全局路径规划，得到路径点集。In step S102, the global path planning of the multi-wheel movement configuration of the planetary vehicle is performed on the comprehensive cost map of the single-wheel movement of the planetary vehicle, and a set of path points is obtained.
步骤S103，从所述路径点集中提取出关键点，基于所述关键点进行曲线拟合得到移动路径，针对所述移动路径计算整车移动代价，基于所述整车移动代价调整关键点以不断优化所述移动路径，最终得到最优路径。Step S103, extracting key points from the set of path points, performing curve fitting based on the key points to obtain a moving path, calculating the moving cost of the entire vehicle based on the moving path, and adjusting the key points based on the moving cost of the entire vehicle to continuously The moving path is optimized to finally obtain the optimal path.
如图2所示，在本发明一个实施例中，上述步骤S101的基于数字高程地形图构建星球车单轮移动综合代价图，具体包括步骤S201至步骤S203。As shown in FIG. 2 , in one embodiment of the present invention, the step S101 of constructing a comprehensive cost map for single-wheel movement of the planetary vehicle based on the digital elevation terrain map above specifically includes steps S201 to S203.
步骤S201，根据星球车单轮的尺寸构建星球车单轮的评价窗口。Step S201, constructing an evaluation window for the single wheel of the planetary vehicle according to the size of the single wheel of the planetary vehicle.
在本发明一个实施例中，本发明基于车轮的最大包络边长d构建评价窗口，最大包络边长d指单个车轮俯视图的对角线长度，用以简化车轮的旋转，当单轮中心与地接触的位置为(xi，yj)时，以(xi，yj)为中心、d为边长的正方形区域作为评价窗口。In one embodiment of the present invention, the present invention builds the evaluation window based on the maximum envelope side length d of the wheel, and the maximum envelope side length d refers to the diagonal length of a single wheel top view to simplify the rotation of the wheel. When the center of a single wheel When the position in contact with the ground is (xi, yj), the square area with (xi, yj) as the center and d as the side length is used as the evaluation window.
步骤S202，根据所述评价窗口计算所述数字高程地形图中各位置的综合代价值。Step S202, calculating the comprehensive cost value of each position in the digital elevation topographic map according to the evaluation window.
在本发明一个实施例中，本发明在所述数字高程地形图中各位置处设置评价窗口，进而根据评价窗口计算所述数字高程地形图中各位置的综合代价值。In one embodiment of the present invention, the present invention sets an evaluation window at each position in the digital elevation topographic map, and then calculates the comprehensive cost value of each position in the digital elevation topographic map according to the evaluation window.
在本发明一个实施例中，所述数字高程地形图具体为栅格图，栅格的大小可以根据精细程度来自由设置，本步骤中的位置指的是所述数字高程地形图中的各栅格点。In one embodiment of the present invention, the digital elevation topographic map is specifically a grid map, and the size of the grid can be freely set according to the degree of fineness. The position in this step refers to each grid in the digital elevation topographic map Grid.
步骤S203，根据所述综合代价值构建星球车单轮移动综合代价图。Step S203, constructing a comprehensive cost map for single-wheel movement of the planetary vehicle according to the comprehensive cost value.
如图3所示，在本发明一个实施例中，上述步骤S202的根据所述评价窗口计算所述数字高程地形图中各位置的综合代价值，具体包括步骤S301和步骤S302。As shown in FIG. 3 , in one embodiment of the present invention, the above-mentioned step S202 of calculating the comprehensive cost value of each position in the digital elevation topographic map according to the evaluation window specifically includes steps S301 and S302.
步骤S301，根据所述评价窗口确定所述数字高程地形图中各位置的坡度、粗糙度以及平坦度。Step S301, determining the slope, roughness and flatness of each position in the digital elevation topographic map according to the evaluation window.
步骤S302，根据所述数字高程地形图中各位置的坡度、粗糙度以及平坦度确定所述数字高程地形图中各位置的综合代价值。Step S302, determining the comprehensive cost value of each position in the digital elevation topographic map according to the slope, roughness and flatness of each position in the digital elevation topographic map.
为了实现车轮匹配的路径规划，本发明重点建立了基于车轮移动轨迹的星球车全局路径搜索和局部轨迹优化方法，通过优化星球车移动路径的轮地接触区域运动代价来实现精细化的路径规划。地形可以通过双目相机视觉系统计算获取数字高程地形图(digitalevaluation map，DEM)，轮地接触区域以星球车的移动构型为基础计算，以多轮星球车为例，星球车的构型可以表示为(x，y，theta)，其中x，y为车体的位置，theta为车体的航向，在(x，y，theta)构型下计算第i个车轮的位置(xi，yj)，把以(xi，yj)为中心、车轮尺度d为边长的正方形作为单个车轮的评价窗口，用以计算移动代价，在星球构型的约束下计算不同位置的车轮移动代价。In order to realize the path planning of wheel matching, the present invention focuses on establishing a global path search and local trajectory optimization method for the planetary vehicle based on the wheel movement trajectory, and realizes refined path planning by optimizing the motion cost of the wheel-ground contact area of the movement path of the planetary vehicle. The terrain can be calculated by the binocular camera vision system to obtain a digital elevation map (digitalevaluation map, DEM). The wheel-ground contact area is calculated based on the mobile configuration of the planetary vehicle. Taking the multi-wheeled planetary vehicle as an example, the configuration of the planetary vehicle can be Expressed as (x, y, theta), where x, y is the position of the car body, theta is the heading of the car body, and the position (xi, yj) of the i-th wheel is calculated under the (x, y, theta) configuration , the square with (xi, yj) as the center and the wheel scale d as the side length is used as the evaluation window of a single wheel to calculate the movement cost, and the wheel movement cost at different positions is calculated under the constraints of the planetary configuration.
本发明通过星球车上相机获取数字高程地形图DEM，构建以单轮为质点模型的移动综合代价图，一般情况下，数字高程地形图的地形分辨率a远小于单个最大包络边长d，最大包络边长d指单个车轮俯视图的对角线长度，用以简化车轮的旋转，当单轮中心与地接触的位置为(xi，yj)时，以(xi，yj)为中心、d为边长的正方形区域作为评价窗口，进而在评价窗口内计算车轮(xi，yj)位置上的坡度slop、粗糙度roughness、平坦度flatness等量化指标，同时根据移动性能的约束设置最大坡度和粗糙度，得到单个车轮区域的综合代价计算方法。车轮的坡度根据评价窗口高程值拟合成一个平面，平面的坡度即为slop代价，评价窗口内各点到平面距离的均值定义为平坦度，评价窗口内在拟合平面两侧的点中离平面最远两个点的距离之和为粗糙度。根据最大坡度、最大粗糙度、平坦度约束进行归一化，超过约束的代价值设为1，定义为障碍。The present invention obtains the digital elevation topographic map DEM through the camera on the planetary vehicle, and constructs a moving comprehensive cost map with a single wheel as a particle model. Generally, the topographic resolution a of the digital elevation topographic map is much smaller than the single maximum envelope side length d, The maximum envelope side length d refers to the diagonal length of the top view of a single wheel, which is used to simplify the rotation of the wheel. When the center of the single wheel is in contact with the ground (xi, yj), take (xi, yj) as the center, d The square area with side length is used as the evaluation window, and then the quantitative indicators such as slope slop, roughness, flatness and other quantitative indicators at the position of the wheel (xi, yj) are calculated in the evaluation window, and the maximum slope and roughness are set according to the constraints of the mobility performance. Degree, the comprehensive cost calculation method of a single wheel area is obtained. The slope of the wheel is fitted into a plane according to the elevation value of the evaluation window. The slope of the plane is the slop cost. The mean value of the distance from each point in the evaluation window to the plane is defined as flatness. The points on both sides of the fitting plane in the evaluation window are far from the plane The sum of the distances between the furthest two points is the roughness. Normalization is performed according to the maximum slope, maximum roughness, and flatness constraints, and the cost value exceeding the constraints is set to 1, which is defined as an obstacle.
图8以四个车轮为例展示了以单轮为质点模型的代价图计算方法，以车轮最大包络的正方形为评价窗口计算车轮中心点的代价图，代价图主要包括坡度、平坦度、粗糙度，通过不同的权重综合坡度、平坦度、粗糙度评价指标得到移动综合代价图。Figure 8 takes four wheels as an example to show the calculation method of the cost map with a single wheel as the particle model. The cost map of the center point of the wheel is calculated with the square of the largest envelope of the wheel as the evaluation window. The cost map mainly includes slope, flatness, roughness degree, the mobile comprehensive cost map is obtained by integrating the evaluation indexes of slope, flatness and roughness with different weights.
如图4所示，在本发明一个实施例中，上述步骤S102的在所述星球车单轮移动综合代价图上进行星球车多轮移动构型的全局路径规划，得到路径点集，具体包括步骤S401至步骤S404。As shown in Figure 4, in one embodiment of the present invention, the global path planning of the multi-wheel movement configuration of the planetary vehicle is performed on the comprehensive cost map of the single-wheel movement of the planetary vehicle in the above step S102, and the set of path points is obtained, which specifically includes Step S401 to step S404.
步骤S401，在确定目标路径点对应的下一个路径点时，根据所述目标路径点以及所述目标路径点的相邻位置点计算星球车的航向。Step S401, when determining the next waypoint corresponding to the target waypoint, calculate the heading of the planetary vehicle according to the target waypoint and the adjacent position points of the target waypoint.
步骤S402，根据所述目标路径点以及所述航向确定星球车的每个车轮各自的位置。Step S402, determining the respective positions of each wheel of the planetary vehicle according to the target waypoint and the heading.
步骤S403，根据每个车轮各自的位置计算车轮位置的综合代价值总和。Step S403, calculating the sum of comprehensive cost values of the wheel positions according to the respective positions of each wheel.
步骤S404，将所述目标路径点对应的车轮位置的综合代价值总和最小的相邻位置点确定为所述目标路径点对应的下一个路径点。Step S404, determining the adjacent position point corresponding to the target waypoint with the minimum sum of comprehensive cost values of the wheel positions as the next waypoint corresponding to the target waypoint.
如图7所示，本发明在构建出单轮的移动综合代价图之后，进行基于多轮构型的移动综合代价的全局搜索，得到最优路径集合。具体步骤大致包括：读取起点或终点；相邻位置的计算；根据相邻两位置计算航向；在指定位置和航向下各个车轮的位置；所有车轮位置的单轮代价求和；选择代价最小的下一个路径点；迭代搜索起点到终点的最优路径点集合。As shown in FIG. 7 , after constructing a single-round integrated mobile cost map, the present invention performs a global search based on multi-round integrated mobile cost to obtain an optimal path set. The specific steps roughly include: reading the starting point or end point; calculating adjacent positions; calculating the heading according to two adjacent positions; the position of each wheel under the specified position and heading; summing the single-wheel costs of all wheel positions; selecting the least costly The next path point; iteratively search for the optimal path point set from the start point to the end point.
具体的，全局路径搜索阶段把星球车建模成多轮的移动模型，在单轮构建的移动综合代价图上计算车体构型的多轮综合代价，通过全局的路径搜索方法搜索出无碰撞的移动路径，代价函数为：Specifically, in the global path search stage, the planetary vehicle is modeled as a multi-wheel mobile model, and the multi-wheel comprehensive cost of the car body configuration is calculated on the mobile comprehensive cost map constructed by a single wheel, and the collision-free The moving path of , the cost function is:
其中(i，j)为星球车的位置，θ车体的偏航角，n为车轮的数量，g(i,j)为步骤一中栅格点(i，j)的环境代价函数。车体在(i，j，θ)构型下计算单个车轮的位置方法可以通过矩阵旋转计算得到，当n＝4时，4个车轮的位置可以计算为：Where (i, j) is the position of the planetary vehicle, θ is the yaw angle of the vehicle body, n is the number of wheels, and g(i, j) is the environmental cost function of the grid point (i, j) in step 1. The method of calculating the position of a single wheel in the (i, j, θ) configuration of the car body can be calculated by matrix rotation. When n=4, the positions of the four wheels can be calculated as:
本发明可以采用基于Field D*或者A*其他的路径搜索算法进行最优路径点的搜索，本发明基于星球车构型下的路径规划算法中，搜索的代价函数定义为：The present invention can use other path search algorithms based on Field D* or A* to search for the optimal path point. In the path planning algorithm based on the star vehicle configuration in the present invention, the cost function of the search is defined as:
f(s)＝g(s)+h(s)f(s)=g(s)+h(s)
其中，f(s)表示为起点到终点途经s的代价预计值，g(s)为s点到终点的实际移动代价值，h(s)为启发函数，表示从起点到s点的代价预估值，定义为起点到s点的欧式距离。c(s,si)由当前构型下的整车移动代价和距离代价l(s,si)的和，车构型的偏航角定义为s到si的方向Among them, f(s) represents the estimated cost of passing through s from the starting point to the end point, g(s) is the actual moving cost value from point s to the end point, h(s) is a heuristic function, representing the estimated cost from the starting point to point s Estimate, defined as the Euclidean distance from the starting point to point s. c(s,si ) is the sum of the vehicle movement cost and the distance cost l(s,si ) in the current configuration, and the yaw angle of the vehicle configuration is defined as the direction from s to si
本发明通过全局的路径点搜索可以获得f(s)最小的路径点集，如图9中的路径点集，方块为车轮位置。The present invention can obtain the path point set with the minimum f(s) through the global path point search, such as the path point set in Figure 9, where the squares are the wheel positions.
如图7所示，本发明在通过全局的路径点搜索得到路径点集合之后，还进行基于整车综合移动代价最小的局部轨迹优化，具体包括轨迹拟合和局部优化两个步骤。As shown in FIG. 7 , after obtaining the waypoint set through the global waypoint search, the present invention also performs local trajectory optimization based on the minimum comprehensive movement cost of the vehicle, specifically including two steps of trajectory fitting and local optimization.
轨迹拟合步骤具体包括：根据路径点中三点之间的转弯角度进行关键点的提取；基于关键点进行圆弧的曲线拟合；曲线按固定距离进行路径的离散获取路径点集，计算多轮构型的移动代价和安全性；计算整车轮地匹配下的车体倾斜角度、车底板离地间隙和安全性，并归一化为匹配代价；加权后计算移动轨迹的代价，输出代价最优路径。The trajectory fitting step specifically includes: extracting key points according to the turning angle between the three points in the way point; performing arc fitting based on the key point; discretizing the path according to a fixed distance to obtain a set of way points, and calculating multiple The movement cost and safety of the wheel configuration; calculate the tilt angle of the vehicle body, the ground clearance of the vehicle floor and safety under the ground matching of the whole wheel, and normalize it to the matching cost; calculate the cost of the moving trajectory after weighting, and output the cost optimal path.
局部优化步骤具体包括：读取关键点；关键点i进行向相邻栅格移动，曲线拟合，代价计算，获取最优移动方向；判断所有关键点的最优移动方向以及代价的优化值；比较所有关键点中影响移动代价最大的关键点进行优化，更新关键点，输出最优路径；迭代上述优化过程，直至路径最优。The local optimization step specifically includes: reading the key point; moving the key point i to the adjacent grid, curve fitting, cost calculation, and obtaining the optimal moving direction; judging the optimal moving direction of all key points and the optimization value of the cost; Compare all the key points that affect the movement cost the most to optimize, update the key points, and output the optimal path; iterate the above optimization process until the path is optimal.
在本发明一个实施例中，基于整车综合移动代价最小的局部轨迹优化主要分成三步，第一步提取关键点，在路径点集中提取关键点；第二步基于关键点的曲线拟合及拟合曲线的整车综合移动代价计算，主要包括多轮构型下代价、整车倾斜程度、离地间隙的加权代价；第三步轨迹优化，在关键点区域设置优化区域，调整关键点的位置后进行曲线拟合、代价计算，迭代调整位置、曲线拟合、代价计算过程，输出最优的运动轨迹。In one embodiment of the present invention, the local trajectory optimization based on the minimum comprehensive movement cost of the vehicle is mainly divided into three steps. The first step is to extract key points, and the key points are extracted from the path points; the second step is based on the curve fitting of key points and The calculation of the comprehensive movement cost of the vehicle by fitting the curve mainly includes the weighted cost of the cost under the multi-wheel configuration, the degree of inclination of the vehicle, and the ground clearance; the third step is trajectory optimization, setting the optimization area in the key point area, and adjusting the key point After the position, perform curve fitting and cost calculation, iteratively adjust the position, curve fitting, and cost calculation process, and output the optimal trajectory.
在本发明一个实施例中，上述步骤S103中的从所述路径点集中提取出关键点，具体包括：In one embodiment of the present invention, the extraction of key points from the set of waypoints in step S103 above specifically includes:
根据所述路径点集中连续三个路径点之间的转弯角度进行关键点提取。The key point is extracted according to the turning angle between three consecutive waypoints in the set of waypoints.
本发明全局路径规划中得到了路径点集合，在局部优化需要提取关键点进行曲线拟合，最后生成星球车移动控制参数。提取关键点主要考虑星球车的最小转弯半径的运动学约束，保证移动过程运动的曲率可达或者规避短距离曲率运动的特殊情况下两点之间直线可达。The present invention obtains a set of path points in the global path planning, needs to extract key points for curve fitting in local optimization, and finally generates the movement control parameters of the planetary vehicle. The key point extraction mainly considers the kinematic constraints of the minimum turning radius of the planetary vehicle, so as to ensure that the curvature of the motion during the movement can be reached or avoid the straight line between two points in the special case of short-distance curvature motion.
图10是本发明实施例提取关键点的方法示意图，如图10所示，在本发明一个实施例中，提取关键点的方法具体包括：将起点加入关键点集合，将起点设为路径计算端点；读取路径端点；读取下一个路径点；判断端点和当前点是否直线可达，若是，则读取下一个路径点，若否，则加入关键点队列；判读路径点是否为终点，若是，则结束，若否，则将当前点做为路径端点，进而读取下一个路径点。Fig. 10 is a schematic diagram of a method for extracting key points in an embodiment of the present invention. As shown in Fig. 10, in one embodiment of the present invention, the method for extracting key points specifically includes: adding the starting point to the key point set, and setting the starting point as the path calculation endpoint ;Read the path endpoint; read the next path point; judge whether the endpoint and the current point are reachable in a straight line, if so, read the next path point, if not, add the key point queue; judge whether the path point is the end point, if so , then end, if not, use the current point as the path endpoint, and then read the next path point.
如图10所示，在本发明另一个实施例中，提取关键点的方法具体包括：读取所有的路径点，设置初值angle0＝180°；读取前两个路径点；读取下一个点；计算三个点形成的夹角angle；记录更小的夹角及形成最小夹角的中间路径点；判断路径点是否为终点，若是，则删除当前最小夹角的中间点，若否，则读取下一个点；判断路径点个数是否满足设定，若是，则结束，若否，则进入步骤读取所有的路径点，设置初值angle0＝180°。As shown in Figure 10, in another embodiment of the present invention, the method for extracting key points specifically includes: reading all path points, setting the initial value angle0=180°; reading the first two path points; reading the next point; calculate the included angle angle formed by three points; record the smaller included angle and the intermediate path point forming the smallest included angle; judge whether the path point is the end point, if so, delete the intermediate point of the current smallest included angle, if not, Then read the next point; judge whether the number of waypoints satisfies the setting, if yes, then end, if not, then enter the step of reading all the waypoints, and set the initial value angle0=180°.
在本发明中，本发明基于关键点进行曲线拟合得到移动路径。在提取关键点之后进行路径拟合，输出移动控制参数，采用圆弧进行关键点之间的曲线拟合，基于车体设定的起点、终点及航向计算关键点间的圆弧，计算方法根据起点、终点是否支持原地转弯分别进行曲线拟合，择优选择不同的路径轨迹。In the present invention, the present invention performs curve fitting based on the key points to obtain the moving path. After the key points are extracted, the path fitting is performed, the movement control parameters are output, and the arc is used for curve fitting between the key points. The arc between the key points is calculated based on the starting point, end point and heading of the car body. The calculation method is based on Whether the start point and the end point support turning in place are used for curve fitting respectively, and different path trajectories are selected according to the best.
(1)起点不允许原地转弯，从起点开始，依据前一点位置及其航向、下一点位置计算圆弧曲率，即已知圆上两点坐标和其中某一点的切线求解圆的半径，如图11所示，令AD切线的航向角为ψ,根据下面计算公式可以方便得到曲率1/R，若曲率小于一定阈值则采用直线拟合，然后依据多轮综合代价计算移动的安全性，保证路径的可通行，依次拟合各个关键点得到各个路径的移动曲率和里程，最后根据终点航向，确定终点原点转弯的角度，从而得到整个起点到终点的移动控制参数。(1) Turning in place is not allowed at the starting point. From the starting point, calculate the curvature of the arc based on the position of the previous point and its heading, and the position of the next point. That is, the coordinates of two points on the circle and the tangent of one point are known to find the radius of the circle. For example, As shown in Figure 11, let the heading angle of the AD tangent line be ψ, and the curvature 1/R can be easily obtained according to the following calculation formula. If the curvature is less than a certain threshold, a straight line is used to fit it, and then the safety of the movement is calculated based on the comprehensive cost of multiple rounds to ensure For the passability of the path, each key point is fitted in turn to obtain the moving curvature and mileage of each path. Finally, according to the heading of the end point, the angle of turning at the origin point of the end point is determined, so as to obtain the movement control parameters from the entire starting point to the end point.
(2)终点不允许原地转弯则采用从终点开始计算，以终点航向为约束，依次利用圆弧拟合至起点，在起点实现原地转弯。(2) If turning in place is not allowed at the end point, it is calculated from the end point, constrained by the heading of the end point, and the arc is fitted to the starting point in turn, and the turn in place is realized at the starting point.
(3)起点和终点无原地转弯约束则采用按照指定间隔遍历360°，按照(1)的方法进行圆弧拟合，得到一系列的不同航向下的控制参数，同时给出综合代价最优的移动轨迹。图12为终点允许原地转弯的拟合路径图，图13为起点原地转弯规划示意图。(3) The starting point and the ending point have no in-situ turning constraints. The 360° is traversed according to the specified interval, and the arc fitting is carried out according to the method (1), so as to obtain a series of control parameters under different headings, and at the same time give the optimal comprehensive cost. movement track. Fig. 12 is a fitting path diagram of an in-situ turn allowed at the end point, and Fig. 13 is a schematic diagram of an in-situ turn planning at the starting point.
如图5所示，在本发明一个实施例中，上述步骤S103中的基于所述整车移动代价调整关键点以不断优化所述移动路径，最终得到最优路径，具体包括步骤S501和步骤S502。As shown in Figure 5, in one embodiment of the present invention, in the above step S103, the key points are adjusted based on the vehicle movement cost to continuously optimize the movement path, and finally obtain the optimal path, which specifically includes steps S501 and S502 .
步骤S501，分别针对每个所述关键点，将所述关键点分别调整到各个相邻栅格点后进行曲线拟合得到新的移动路径，计算该新的移动路径的整车移动代价，进而根据该新的移动路径的整车移动代价确定出各所述关键点各自对应的最优相邻栅格点。Step S501, for each of the key points, adjust the key points to each adjacent grid point and perform curve fitting to obtain a new moving path, calculate the vehicle movement cost of the new moving path, and then The optimal adjacent grid points corresponding to each of the key points are determined according to the vehicle movement cost of the new movement path.
步骤S502，将各所述关键点分别调整到各自对应的所述最优相邻栅格点后进行曲线拟合，得到最优移动路径。In step S502, each key point is adjusted to its corresponding optimal adjacent grid point, and then curve fitting is performed to obtain an optimal moving path.
在提取关键点和路径拟合之后，需要对拟合的轨迹进行代价计算和轨迹的优化。After extracting key points and path fitting, it is necessary to perform cost calculation and trajectory optimization on the fitted trajectory.
在本发明一个实施例中，轨迹的优化见图14的右流程，对路径关键点进行优化，采用小范围固定移动步长调整关键点位置后重新进行曲线拟合，遍历所有关键点找到影响代价最大的关键点以及其偏移方向，调整此关键点，每轮优化只移动一个关键点的一个步长，迭代调整的过程直至最优路径。In one embodiment of the present invention, the optimization of the trajectory is shown in the right process of Figure 14. The key points of the path are optimized, and the position of the key points is adjusted using a small-scale fixed movement step, and then the curve fitting is performed again, and all key points are traversed to find the impact cost. The largest key point and its offset direction, adjust this key point, each round of optimization only moves a step of one key point, and iteratively adjusts the process until the optimal path.
如图7所示，本发明的局部优化步骤具体包括：读取关键点；关键点i进行向相邻栅格移动，曲线拟合，代价计算，获取最优移动方向；判断所有关键点的最优移动方向以及代价的优化值；比较所有关键点中影响移动代价最大的关键点进行优化，更新关键点，输出最优路径；迭代上述优化过程，直至路径最优。As shown in Figure 7, the local optimization steps of the present invention specifically include: reading key points; moving key point i to adjacent grids, curve fitting, cost calculation, and obtaining the optimal moving direction; judging the optimal moving direction of all key points Optimize the movement direction and the optimization value of the cost; compare the key points that affect the movement cost the most among all key points for optimization, update the key points, and output the optimal path; iterate the above optimization process until the path is optimal.
如图6所示，在本发明一个实施例中，上述步骤S103中的针对所述移动路径计算整车移动代价，具体包括步骤S601至步骤S605。As shown in FIG. 6 , in one embodiment of the present invention, the calculation of the vehicle movement cost for the movement path in the above step S103 specifically includes steps S601 to S605 .
步骤S601，对所述移动路径进行离散化，得到离散路径点以及每个所述离散路径点各自对应的偏航角。Step S601, discretize the moving path to obtain discrete path points and a yaw angle corresponding to each of the discrete path points.
步骤S602，根据所述偏航角确定星球车在每个所述离散路径点处的各车轮的位置。Step S602, determining the position of each wheel of the planetary vehicle at each of the discrete waypoints according to the yaw angle.
步骤S603，根据星球车在每个所述离散路径点处的各车轮的位置以及所述数字高程地形图中各位置的综合代价值，确定每个所述离散路径点各自对应的综合代价值。Step S603, according to the position of each wheel of the planetary vehicle at each of the discrete waypoints and the comprehensive cost value of each position in the digital elevation map, determine the respective comprehensive cost values corresponding to each of the discrete waypoints.
步骤S604，计算星球车在每个所述离散路径点处的车体倾斜角度和车底板离地间隙。Step S604, calculating the inclination angle of the vehicle body and the ground clearance of the vehicle floor at each discrete path point of the planetary vehicle.
步骤S605，根据每个所述离散路径点各自对应综合代价值、车体倾斜角度和车底板离地间隙，确定出所述整车移动代价。Step S605, determining the vehicle movement cost according to the integrated cost value, vehicle body inclination angle and vehicle floor clearance corresponding to each of the discrete path points.
在本发明一个实施例中，整车移动代价计算如图14的左流程，读取轨迹参数进行原地转弯、曲率移动、直线等移动类型的轨迹线离散，采用固定距离进行轨迹的离散，根据离散后的轨迹点及对应航向计算多轮星球车的综合移动代价。车体的倾斜角可以根据实际车体的移动分系统结构进行解算或者直接根据多个车轮区域的平均高程值进行曲面拟合。车体的离地间隙则根据车体的倾斜角得到车底板的平面，计算车体下方区域中离车底板平面的最小距离。In one embodiment of the present invention, the calculation of the vehicle movement cost is shown in the left process of Figure 14, and the track parameters are read to perform track line discretization of movement types such as in-situ turning, curvature movement, and straight line, and a fixed distance is used to discretize the track, according to The discretized trajectory points and corresponding headings are used to calculate the comprehensive movement cost of the multi-wheel planetary vehicle. The inclination angle of the vehicle body can be calculated according to the structure of the actual vehicle body's mobile subsystem, or the surface can be fitted directly according to the average elevation values of multiple wheel areas. The ground clearance of the car body is obtained from the plane of the car floor according to the inclination angle of the car body, and the minimum distance from the plane of the car floor in the area under the car body is calculated.
如图7所示，本发明的整车移动代价计算步骤具体包括：移动路径按固定距离进行路径的离散获取路径点集，计算多轮构型的移动代价和安全性；计算整车轮地匹配下的车体倾斜角度、车底板离地间隙和安全性，并归一化为匹配代价；加权后计算移动轨迹的代价，输出代价最优路径。As shown in Figure 7, the calculation steps of the whole vehicle movement cost in the present invention specifically include: the movement path is carried out according to a fixed distance to discretely obtain the path point set of the path, and the movement cost and safety of the multi-wheel configuration are calculated; The inclination angle of the vehicle body, the ground clearance of the vehicle floor and the safety are normalized into the matching cost; the cost of the moving trajectory is calculated after weighting, and the optimal path of the cost is output.
由以上实施例可以看出，本发明解决了复杂环境下基于轮地匹配的轮式移动机器人精细路径规划的问题，实现了单轮-多轮-整车多层次移动代价下的精细环境建模，建立基于轮地匹配代价计算的全局路径搜索和基于关键点邻近区域的局部轨迹优化。通过轮地匹配的全局优化选择移动路径点，确定最优的移动路径；提取关键路径点，在关键路径点设定局部优化区域，实现局部路径的迭代寻优，确定更优的移动轨迹，从而实现了基于车轮匹配的精细路径规划。采用了车轮移动实际轨迹进行代价计算，有效提高了复杂地形下移动路径搜索的解空间，建立多层次代价计算提供了精细的移动寻优，提高了移动路径的有效性和精细程度，具有较高的工程应用价值。It can be seen from the above embodiments that the present invention solves the problem of fine path planning for wheeled mobile robots based on wheel-ground matching in complex environments, and realizes fine environment modeling under the cost of single-wheel-multi-wheel-vehicle multi-level movement , establish a global path search based on wheel-ground matching cost calculation and local trajectory optimization based on the keypoint neighborhood. Through the global optimization of wheel-ground matching, the moving path points are selected to determine the optimal moving path; the key path points are extracted, and the local optimization area is set at the key path points, so as to realize the iterative optimization of the local path and determine a better moving trajectory, thereby The fine path planning based on wheel matching is realized. The actual trajectory of the wheel is used for cost calculation, which effectively improves the solution space of the mobile path search under complex terrain. The establishment of multi-level cost calculation provides fine mobile optimization, improves the effectiveness and fineness of the mobile path, and has a high engineering application value.
需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。It should be noted that the steps shown in the flowcharts of the accompanying drawings may be performed in a computer system, such as a set of computer-executable instructions, and that although a logical order is shown in the flowcharts, in some cases, The steps shown or described may be performed in an order different than here.
基于同一发明构思，本发明实施例还提供了一种基于轮地匹配的星球车路径规划装置，可以用于实现上述实施例所描述的基于轮地匹配的星球车路径规划方法，如下面的实施例所述。由于基于轮地匹配的星球车路径规划装置解决问题的原理与基于轮地匹配的星球车路径规划方法相似，因此基于轮地匹配的星球车路径规划装置的实施例可以参见基于轮地匹配的星球车路径规划方法的实施例，重复之处不再赘述。以下所使用的，术语“单元”或者“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。Based on the same inventive concept, the embodiment of the present invention also provides a wheel-ground matching-based planetary vehicle path planning device, which can be used to implement the wheel-ground matching-based planetary vehicle path planning method described in the above embodiment, such as the following implementation example described. Since the problem-solving principle of the planetary rover path planning device based on wheel-earth matching is similar to the method of wheel-earth matching-based planetary rover path planning, the embodiment of the wheel-earth matching-based planetary rover path planning device can be found in the wheel-earth matching-based Embodiments of the vehicle route planning method, the repetitive parts will not be repeated. As used below, the term "unit" or "module" may be a combination of software and/or hardware that realizes a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
图15是本发明实施例基于轮地匹配的星球车路径规划装置的结构框图，如图15所示，在本发明一个实施例中，本发明的基于轮地匹配的星球车路径规划装置包括：Fig. 15 is a structural block diagram of a planetary vehicle path planning device based on wheel-ground matching in an embodiment of the present invention. As shown in Fig. 15, in one embodiment of the present invention, the wheel-ground matching-based planetary vehicle path planning device of the present invention includes:
单轮移动综合代价图构建单元1，用于基于数字高程地形图构建星球车单轮移动综合代价图；A single-wheel mobile integrated cost map construction unit 1 is used to construct a single-wheel mobile integrated cost map for planetary vehicles based on digital elevation terrain maps;
多轮移动构型全局路径规划单元2，用于在所述星球车单轮移动综合代价图上进行星球车多轮移动构型的全局路径规划，得到路径点集；The multi-wheel mobile configuration global path planning unit 2 is used to perform the global path planning of the multi-wheel mobile configuration of the planetary vehicle on the comprehensive cost map of the single-wheel movement of the planetary vehicle to obtain a set of path points;
轨迹拟合及优化单元3，用于从所述路径点集中提取出关键点，基于所述关键点进行曲线拟合得到移动路径，针对所述移动路径计算整车移动代价，基于所述整车移动代价调整关键点以不断优化所述移动路径，最终得到最优路径。The trajectory fitting and optimization unit 3 is used to extract key points from the set of path points, perform curve fitting based on the key points to obtain a moving path, calculate the moving cost of the whole vehicle for the moving path, and calculate the moving cost of the whole vehicle based on the moving path. The movement cost adjusts the key points to continuously optimize the movement path, and finally obtains the optimal path.
在本发明一个实施例中，所述单轮移动综合代价图构建单元1，具体包括：In one embodiment of the present invention, the construction unit 1 of the comprehensive cost map for single-round movement specifically includes:
评价窗口构建模块，用于根据星球车单轮的尺寸构建星球车单轮的评价窗口；The evaluation window building module is used to construct the evaluation window of the single wheel of the planetary vehicle according to the size of the single wheel of the planetary vehicle;
综合代价值计算模块，用于根据所述评价窗口计算所述数字高程地形图中各位置的综合代价值；A comprehensive cost value calculation module, used to calculate the comprehensive cost value of each position in the digital elevation topographic map according to the evaluation window;
移动综合代价图生成模块，用于根据所述综合代价值构建星球车单轮移动综合代价图。The mobile comprehensive cost map generating module is used to construct a single-wheel mobile comprehensive cost map of the planetary vehicle according to the comprehensive cost value.
在本发明一个实施例中，所述综合代价值计算模块，具体包括：In one embodiment of the present invention, the comprehensive cost value calculation module specifically includes:
指标计算子模块，用于根据所述评价窗口确定所述数字高程地形图中各位置的坡度、粗糙度以及平坦度；An index calculation submodule, configured to determine the slope, roughness and flatness of each position in the digital elevation topographic map according to the evaluation window;
指标综合计算子模块，用于根据所述数字高程地形图中各位置的坡度、粗糙度以及平坦度确定所述数字高程地形图中各位置的综合代价值。The indicator comprehensive calculation sub-module is used to determine the comprehensive cost value of each position in the digital elevation topographic map according to the slope, roughness and flatness of each position in the digital elevation topographic map.
在本发明一个实施例中，所述多轮移动构型全局路径规划单元2，具体包括：In one embodiment of the present invention, the multi-round mobile configuration global path planning unit 2 specifically includes:
航向计算模块，用于在确定目标路径点对应的下一个路径点时，根据所述目标路径点以及所述目标路径点的相邻位置点计算星球车的航向；The course calculation module is used to calculate the course of the planetary vehicle according to the target waypoint and the adjacent position points of the target waypoint when determining the next waypoint corresponding to the target waypoint;
车轮位置确定模块，用于根据所述目标路径点以及所述航向确定星球车的每个车轮各自的位置；A wheel position determination module, configured to determine the respective positions of each wheel of the planetary vehicle according to the target waypoint and the heading;
综合代价值总和计算模块，用于根据每个车轮各自的位置计算车轮位置的综合代价值总和；A comprehensive cost value sum calculation module, which is used to calculate the comprehensive cost value sum of the wheel positions according to the respective positions of each wheel;
路径点确定模块，用于将所述目标路径点对应的车轮位置的综合代价值总和最小的相邻位置点确定为所述目标路径点对应的下一个路径点。A waypoint determining module, configured to determine an adjacent position point corresponding to the target waypoint with the smallest sum of comprehensive cost values of wheel positions as the next waypoint corresponding to the target waypoint.
在本发明一个实施例中，所述轨迹拟合及优化单元3，具体包括：In one embodiment of the present invention, the trajectory fitting and optimization unit 3 specifically includes:
关键点提取模块，用于根据所述路径点集中连续三个路径点之间的转弯角度进行关键点提取。The key point extraction module is used for extracting key points according to the turning angle between three consecutive way points in the set of way points.
在本发明一个实施例中，所述轨迹拟合及优化单元3，具体包括：In one embodiment of the present invention, the trajectory fitting and optimization unit 3 specifically includes:
关键点调整模块，用于分别针对每个所述关键点，将所述关键点分别调整到各个相邻栅格点后进行曲线拟合得到新的移动路径，计算该新的移动路径的整车移动代价，进而根据该新的移动路径的整车移动代价确定出各所述关键点各自对应的最优相邻栅格点；The key point adjustment module is used to respectively adjust the key points to each adjacent grid point for each key point and then perform curve fitting to obtain a new moving path, and calculate the whole vehicle of the new moving path The movement cost, and then determine the optimal adjacent grid points corresponding to each of the key points according to the vehicle movement cost of the new movement path;
最优移动路径确定模块，用于将各所述关键点分别调整到各自对应的所述最优相邻栅格点后进行曲线拟合，得到最优移动路径。The optimal moving path determination module is used to adjust each key point to the corresponding optimal adjacent grid point and perform curve fitting to obtain the optimal moving path.
在本发明一个实施例中，所述轨迹拟合及优化单元3，具体包括：In one embodiment of the present invention, the trajectory fitting and optimization unit 3 specifically includes:
移动路径离散化模块，用于对所述移动路径进行离散化，得到离散路径点以及每个所述离散路径点各自对应的偏航角；A movement path discretization module, configured to discretize the movement path to obtain discrete path points and the respective yaw angles corresponding to each of the discrete path points;
离散路径点车轮位置确定模块，用于根据所述偏航角确定星球车在每个所述离散路径点处的各车轮的位置；A discrete waypoint wheel position determination module, configured to determine the position of each wheel of the planetary vehicle at each of the discrete waypoints according to the yaw angle;
离散路径点综合代价值计算模块，用于根据星球车在每个所述离散路径点处的各车轮的位置以及所述数字高程地形图中各位置的综合代价值，确定每个所述离散路径点各自对应的综合代价值；Discrete path point integrated cost value calculation module, used to determine each of the discrete paths according to the position of each wheel of the planetary vehicle at each of the discrete path points and the integrated cost value of each position in the digital elevation topographic map The comprehensive value corresponding to each point;
离散路径点评价参数计算模块，用于计算星球车在每个所述离散路径点处的车体倾斜角度和车底板离地间隙；Discrete waypoint evaluation parameter calculation module, used to calculate the vehicle body inclination angle and ground clearance of the vehicle floor at each discrete waypoint of the planetary vehicle;
整车移动代价确定模块，用于根据每个所述离散路径点各自对应综合代价值、车体倾斜角度和车底板离地间隙，确定出所述整车移动代价。The vehicle movement cost determination module is configured to determine the vehicle movement cost according to the integrated cost value, vehicle body inclination angle and vehicle floor ground clearance corresponding to each of the discrete path points.
为了实现上述目的，根据本申请的另一方面，还提供了一种计算机设备。如图16所示，该计算机设备包括存储器、处理器、通信接口以及通信总线，在存储器上存储有可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述实施例方法中的步骤。In order to achieve the above purpose, according to another aspect of the present application, a computer device is also provided. As shown in Figure 16, the computer device includes a memory, a processor, a communication interface and a communication bus, and a computer program that can run on the processor is stored in the memory, and the above-mentioned embodiments are realized when the processor executes the computer program steps in the method.
处理器可以为中央处理器(Central Processing Unit，CPU)。处理器还可以为其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等芯片，或者上述各类芯片的组合。The processor may be a central processing unit (Central Processing Unit, CPU). The processor can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate array (Field-Programmable Gate Array, FPGA) or other Chips such as programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above-mentioned types of chips.
存储器作为一种非暂态计算机可读存储介质，可用于存储非暂态软件程序、非暂态计算机可执行程序以及单元，如本发明上述方法实施例中对应的程序单元。处理器通过运行存储在存储器中的非暂态软件程序、指令以及模块，从而执行处理器的各种功能应用以及作品数据处理，即实现上述方法实施例中的方法。As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer-executable programs and units, such as the corresponding program units in the above method embodiments of the present invention. The processor runs the non-transitory software programs, instructions and modules stored in the memory to execute various functional applications of the processor and process data of works, that is, to realize the methods in the above method embodiments.
存储器可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储处理器所创建的数据等。此外，存储器可以包括高速随机存取存储器，还可以包括非暂态存储器，例如至少一个磁盘存储器件、闪存器件、或其他非暂态固态存储器件。在一些实施例中，存储器可选包括相对于处理器远程设置的存储器，这些远程存储器可以通过网络连接至处理器。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created by the processor, and the like. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include memory located remotely from the processor, and such remote memory may be connected to the processor via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
所述一个或者多个单元存储在所述存储器中，当被所述处理器执行时，执行上述实施例中的方法。The one or more units are stored in the memory, and when executed by the processor, execute the methods in the above embodiments.
上述计算机设备具体细节可以对应参阅上述实施例中对应的相关描述和效果进行理解，此处不再赘述。The specific details of the above computer device can be understood by correspondingly referring to the corresponding relevant descriptions and effects in the above embodiments, and details are not repeated here.
为了实现上述目的，根据本申请的另一方面，还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序在计算机处理器中执行时实现上述基于轮地匹配的星球车路径规划方法中的步骤。本领域技术人员可以理解，实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)、随机存储记忆体(RandomAccessMemory，RAM)、快闪存储器(Flash Memory)、硬盘(Hard Disk Drive，缩写：HDD)或固态硬盘(Solid-State Drive，SSD)等；所述存储介质还可以包括上述种类的存储器的组合。In order to achieve the above object, according to another aspect of the present application, a computer-readable storage medium is also provided, the computer-readable storage medium stores a computer program, and when the computer program is executed in a computer processor, the above-mentioned The steps in the path planning method of the planetary rover based on wheel-ground matching. Those skilled in the art can understand that all or part of the processes in the methods of the above-mentioned embodiments can be completed by instructing related hardware through computer programs, and the programs can be stored in a computer-readable storage medium. During execution, it may include the processes of the embodiments of the above-mentioned methods. Wherein, the storage medium can be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive) , abbreviation: HDD) or a solid-state hard drive (Solid-State Drive, SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memory.
为了实现上述目的，根据本申请的另一方面，还提供了一种计算机程序产品，包括计算机程序/指令，该计算机程序/指令被处理器执行时实现上述基于轮地匹配的星球车路径规划方法的步骤。In order to achieve the above purpose, according to another aspect of the present application, a computer program product is also provided, including computer programs/instructions, when the computer program/instructions are executed by a processor, the above-mentioned planetary vehicle path planning method based on wheel-ground matching is implemented. A step of.
显然，本领域的技术人员应该明白，上述的本发明的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本发明不限制于任何特定的硬件和软件结合。Obviously, those skilled in the art should understand that each module or each step of the present invention described above can be realized by a general-purpose computing device, and they can be concentrated on a single computing device, or distributed in a network formed by multiple computing devices Optionally, they can be implemented with program codes executable by a computing device, thus, they can be stored in a storage device and executed by a computing device, or they can be made into individual integrated circuit modules, or they can be integrated into Multiple modules or steps are fabricated into a single integrated circuit module to realize. As such, the present invention is not limited to any specific combination of hardware and software.
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310146333 | 2023-02-08 | ||
| CN2023101463334 | 2023-02-08 |
| Publication Number | Publication Date |
|---|---|
| CN116449838Atrue CN116449838A (en) | 2023-07-18 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310383111.4APendingCN116449838A (en) | 2023-02-08 | 2023-04-11 | Method and device for path planning of planetary rover based on wheel-ground matching |
| Country | Link |
|---|---|
| CN (1) | CN116449838A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117993585A (en)* | 2023-12-29 | 2024-05-07 | 江苏省港口集团信息科技有限公司 | Global path planning method and system under mixed scene compatible with multiple vehicle types |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117993585A (en)* | 2023-12-29 | 2024-05-07 | 江苏省港口集团信息科技有限公司 | Global path planning method and system under mixed scene compatible with multiple vehicle types |
| Publication | Publication Date | Title |
|---|---|---|
| CN112292581B (en) | Relative atlas of autonomous vehicles and its generation | |
| CN111492202B (en) | Location determination of vehicle operation | |
| Nagatani et al. | Multirobot exploration for search and rescue missions: A report on map building in RoboCupRescue 2009 | |
| Weng et al. | Pole-based real-time localization for autonomous driving in congested urban scenarios | |
| CN114812581A (en) | Cross-country environment navigation method based on multi-sensor fusion | |
| Inotsume et al. | Robust path planning for slope traversing under uncertainty in slip prediction | |
| CN112184736A (en) | Multi-plane extraction method based on European clustering | |
| Xu et al. | Heuristic and random search algorithm in optimization of route planning for Robot’s geomagnetic navigation | |
| Ishigami et al. | Range‐dependent Terrain Mapping and Multipath Planning using Cylindrical Coordinates for a Planetary Exploration Rover | |
| CN115016458B (en) | Path planning method for underground cave exploration robot based on RRT algorithm | |
| CN117968714A (en) | A navigation path planning system and method for unmanned vehicles on complex and rugged terrain cluster maps | |
| CN115371662B (en) | Static map construction method for removing dynamic objects based on probability grids | |
| CN116753970A (en) | Path planning method, path planning device, electronic equipment and storage medium | |
| CN115170772A (en) | Three-dimensional path planning method based on point cloud map interactive passability analysis | |
| CN108446785A (en) | A kind of optimal visual overlay path planing method based on landform visible range | |
| CN116136417B (en) | Unmanned vehicle local path planning method facing off-road environment | |
| CN116449838A (en) | Method and device for path planning of planetary rover based on wheel-ground matching | |
| Fan et al. | An improved JPS algorithm for global path planning of the seabed mining vehicle | |
| CN116147653B (en) | Three-dimensional reference path planning method for unmanned vehicle | |
| Kim et al. | A geodetic normal distribution map for long-term lidar localization on earth | |
| Liu et al. | An improved A* algorithm for generating four-track trajectory planning to adapt to longitudinal rugged terrain | |
| Yu | The Impact of Path Planning Model Based on Improved Ant Colony Optimization Algorithm on Green Traffic Management. | |
| Zhong et al. | Integrating Global Path Information with Advanced Risk Assessment: An Enhanced Potential Field Method for Intelligent Connected Vehicles Local Path Planning | |
| Cao et al. | MPP: Multiscale Path Planning for UGV Navigation in Semi-structured Environments | |
| Liu et al. | LiDAR mini-matching positioning method based on constraint of lightweight point cloud feature map |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |