Repository files navigation

Vikrant Dewangan¹Basant Sharma²Sarthak Sharma¹Tushar Choudhary¹Aakash Aanegola¹,Arun Kumar Singh²,K. Madhava Krishna¹

(1- Robotics Research Center, IIIT Hyderabad, 2- University of Tartu, Estonia)

• Code Release
• Add simulation scenarios
• Improve README

Literature review is present in theliterature-review branch.

Motion planning over cost maps generated via Birds Eye View (BEV) segmentation has emerged as a prominent approach in autonomous driving. However, the current approaches have two critical gaps. First, the optimizationprocess is simplistic and involves just evaluating a fixed setof trajectories over the cost map. The trajectory samples arenot adapted based on their associated cost values. Second, theexisting cost maps do not account for the uncertainty in thecost maps that can arise due to noise in RGB images, BEVannotations etc. As a result, these approaches can struggle inchallenging scenarios where there is abrupt cut-in, stopping,overtaking, merging, etc from the neighbouring vehicles.

In this paper, we propose UAP-BEV, a novel approach that models the noise in Spatio-Temporal BEV predictions to create an uncertainty-aware occupancy grid map. Using queries of the distance to the closest occupied cell, we obtain a sample estimate of the collision probability of the ego-vehicle. Subsequently, our approach uses gradient-free sampling-based optimization to compute low-cost trajectories over the cost map. Importantly, the sampling distribution is adapted based on the optimal cost values of the sampled trajectories. By explicitly modelling probabilistic collision avoidance in the BEV space, our approach is able to outperform the cost-map based baselines in collision avoidance, route completion, time to completion, and smoothness.

• Noise in RGB Images

• Noise in Intrinsics, error in GPS.

• Noisy BEV annotations

• Assumes shape of underlying distribution
• Can lead to conservative behaviour
• Does not handle Noisy Annotations

a.The histogram of constraint violation functions for each set in the elite set. At the start, multiple samples are spread out on non-zero values, complete convergence is achieved and at Iteration 10, all samples have values 0.

b.Convergence of normalized costs with trace of covariance, signifying the samples are pushed towards good regions.