English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Autonomous driving requires accurate reasoning of the location of objectsfrom raw sensor data. Recent end-to-end learning methods go from raw sensordata to a trajectory output via Bird's Eye View(BEV) segmentation as aninterpretable intermediate representation. Motion planning over cost mapsgenerated via Birds Eye View (BEV) segmentation has emerged as a prominentapproach in autonomous driving. However, the current approaches have twocritical gaps. First, the optimization process is simplistic and involves justevaluating a fixed set of trajectories over the cost map. The trajectorysamples are not adapted based on their associated cost values. Second, theexisting cost maps do not account for the uncertainty in the cost maps that canarise due to noise in RGB images, and BEV annotations. As a result, theseapproaches can struggle in challenging scenarios where there is abrupt cut-in,stopping, overtaking, merging, etc from the neighboring vehicles.  In this paper, we propose UAP-BEV: A novel approach that models the noise inSpatio-Temporal BEV predictions to create an uncertainty-aware occupancy gridmap. Using queries of the distance to the closest occupied cell, we obtain asample estimate of the collision probability of the ego-vehicle. Subsequently,our approach uses gradient-free sampling-based optimization to compute low-costtrajectories over the cost map. Importantly, the sampling distribution isadapted based on the optimal cost values of the sampled trajectories. Byexplicitly modeling probabilistic collision avoidance in the BEV space, ourapproach is able to outperform the cost-map-based baselines in collisionavoidance, route completion, time to completion, and smoothness. To furthervalidate our method, we also show results on the real-world dataset NuScenes,where we report improvements in collision avoidance and smoothness.

UAP-BEV: Uncertainty Aware Planning using Bird's Eye View generated from Surround Monocular Images