Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380136306> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4380136306 abstract "Autonomous driving requires accurate reasoning of the location of objects from raw sensor data. Recent end-to-end learning methods go from raw sensor data to a trajectory output via Bird's Eye View(BEV) segmentation as an interpretable intermediate representation. 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 optimization process is simplistic and involves just evaluating a fixed set of trajectories over the cost map. The trajectory samples are not adapted based on their associated cost values. Second, the existing cost maps do not account for the uncertainty in the cost maps that can arise due to noise in RGB images, and BEV annotations. As a result, these approaches 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 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 modeling 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. To further validate our method, we also show results on the real-world dataset NuScenes, where we report improvements in collision avoidance and smoothness." @default.
- W4380136306 created "2023-06-10" @default.
- W4380136306 creator A5017355813 @default.
- W4380136306 creator A5025870053 @default.
- W4380136306 creator A5030702255 @default.
- W4380136306 creator A5068014632 @default.
- W4380136306 creator A5076179405 @default.
- W4380136306 creator A5079727474 @default.
- W4380136306 creator A5092130689 @default.
- W4380136306 date "2023-06-08" @default.
- W4380136306 modified "2023-09-25" @default.
- W4380136306 title "UAP-BEV: Uncertainty Aware Planning using Bird's Eye View generated from Surround Monocular Images" @default.
- W4380136306 doi "https://doi.org/10.48550/arxiv.2306.04939" @default.
- W4380136306 hasPublicationYear "2023" @default.
- W4380136306 type Work @default.
- W4380136306 citedByCount "0" @default.
- W4380136306 crossrefType "posted-content" @default.
- W4380136306 hasAuthorship W4380136306A5017355813 @default.
- W4380136306 hasAuthorship W4380136306A5025870053 @default.
- W4380136306 hasAuthorship W4380136306A5030702255 @default.
- W4380136306 hasAuthorship W4380136306A5068014632 @default.
- W4380136306 hasAuthorship W4380136306A5076179405 @default.
- W4380136306 hasAuthorship W4380136306A5079727474 @default.
- W4380136306 hasAuthorship W4380136306A5092130689 @default.
- W4380136306 hasBestOaLocation W43801363061 @default.
- W4380136306 hasConcept C115961682 @default.
- W4380136306 hasConcept C121332964 @default.
- W4380136306 hasConcept C1276947 @default.
- W4380136306 hasConcept C13662910 @default.
- W4380136306 hasConcept C154945302 @default.
- W4380136306 hasConcept C19966478 @default.
- W4380136306 hasConcept C31972630 @default.
- W4380136306 hasConcept C41008148 @default.
- W4380136306 hasConcept C49937458 @default.
- W4380136306 hasConcept C57077369 @default.
- W4380136306 hasConcept C65909025 @default.
- W4380136306 hasConcept C89600930 @default.
- W4380136306 hasConcept C90509273 @default.
- W4380136306 hasConcept C99498987 @default.
- W4380136306 hasConceptScore W4380136306C115961682 @default.
- W4380136306 hasConceptScore W4380136306C121332964 @default.
- W4380136306 hasConceptScore W4380136306C1276947 @default.
- W4380136306 hasConceptScore W4380136306C13662910 @default.
- W4380136306 hasConceptScore W4380136306C154945302 @default.
- W4380136306 hasConceptScore W4380136306C19966478 @default.
- W4380136306 hasConceptScore W4380136306C31972630 @default.
- W4380136306 hasConceptScore W4380136306C41008148 @default.
- W4380136306 hasConceptScore W4380136306C49937458 @default.
- W4380136306 hasConceptScore W4380136306C57077369 @default.
- W4380136306 hasConceptScore W4380136306C65909025 @default.
- W4380136306 hasConceptScore W4380136306C89600930 @default.
- W4380136306 hasConceptScore W4380136306C90509273 @default.
- W4380136306 hasConceptScore W4380136306C99498987 @default.
- W4380136306 hasLocation W43801363061 @default.
- W4380136306 hasOpenAccess W4380136306 @default.
- W4380136306 hasPrimaryLocation W43801363061 @default.
- W4380136306 hasRelatedWork W1534568064 @default.
- W4380136306 hasRelatedWork W1990911012 @default.
- W4380136306 hasRelatedWork W2000407620 @default.
- W4380136306 hasRelatedWork W2005437358 @default.
- W4380136306 hasRelatedWork W2077703563 @default.
- W4380136306 hasRelatedWork W2086929871 @default.
- W4380136306 hasRelatedWork W2517104666 @default.
- W4380136306 hasRelatedWork W2999749393 @default.
- W4380136306 hasRelatedWork W4246474087 @default.
- W4380136306 hasRelatedWork W4281695986 @default.
- W4380136306 isParatext "false" @default.
- W4380136306 isRetracted "false" @default.
- W4380136306 workType "article" @default.