Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312406013> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4312406013 endingPage "352" @default.
- W4312406013 startingPage "335" @default.
- W4312406013 abstract "Simulators offer the possibility of safe, low-cost development of self-driving systems. However, current driving simulators exhibit naïve behavior models for background traffic. Hand-tuned scenarios are typically added during simulation to induce safety-critical situations. An alternative approach is to adversarially perturb the background traffic trajectories. In this paper, we study this approach to safety-critical driving scenario generation using the CARLA simulator. We use a kinematic bicycle model as a proxy to the simulator’s true dynamics and observe that gradients through this proxy model are sufficient for optimizing the background traffic trajectories. Based on this finding, we propose KING, which generates safety-critical driving scenarios with a 20% higher success rate than black-box optimization. By solving the scenarios generated by KING using a privileged rule-based expert algorithm, we obtain training data for an imitation learning policy. After fine-tuning on this new data, we show that the policy becomes better at avoiding collisions. Importantly, our generated data leads to reduced collisions on both held-out scenarios generated via KING as well as traditional hand-crafted scenarios, demonstrating improved robustness." @default.
- W4312406013 created "2023-01-04" @default.
- W4312406013 creator A5016606943 @default.
- W4312406013 creator A5041189908 @default.
- W4312406013 creator A5052134135 @default.
- W4312406013 creator A5066965497 @default.
- W4312406013 creator A5069868868 @default.
- W4312406013 date "2022-01-01" @default.
- W4312406013 modified "2023-10-15" @default.
- W4312406013 title "KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients" @default.
- W4312406013 cites W2112036188 @default.
- W4312406013 cites W2609532991 @default.
- W4312406013 cites W2616635592 @default.
- W4312406013 cites W2962894046 @default.
- W4312406013 cites W2964047820 @default.
- W4312406013 cites W2968008415 @default.
- W4312406013 cites W2968176166 @default.
- W4312406013 cites W2985936292 @default.
- W4312406013 cites W3009593063 @default.
- W4312406013 cites W3010003086 @default.
- W4312406013 cites W3025279871 @default.
- W4312406013 cites W3034445502 @default.
- W4312406013 cites W3034552332 @default.
- W4312406013 cites W3034652687 @default.
- W4312406013 cites W3034669477 @default.
- W4312406013 cites W3107235539 @default.
- W4312406013 cites W3109395584 @default.
- W4312406013 cites W3109791956 @default.
- W4312406013 cites W3118618654 @default.
- W4312406013 cites W3130718496 @default.
- W4312406013 cites W3131287736 @default.
- W4312406013 cites W3133465684 @default.
- W4312406013 cites W3172477795 @default.
- W4312406013 cites W3172863135 @default.
- W4312406013 cites W3179442871 @default.
- W4312406013 cites W3181350748 @default.
- W4312406013 cites W3193987867 @default.
- W4312406013 cites W3198460218 @default.
- W4312406013 cites W3207915602 @default.
- W4312406013 cites W3209892694 @default.
- W4312406013 cites W4210496774 @default.
- W4312406013 cites W4214530037 @default.
- W4312406013 cites W4214759451 @default.
- W4312406013 cites W4312363838 @default.
- W4312406013 doi "https://doi.org/10.1007/978-3-031-19839-7_20" @default.
- W4312406013 hasPublicationYear "2022" @default.
- W4312406013 type Work @default.
- W4312406013 citedByCount "6" @default.
- W4312406013 countsByYear W43124060132023 @default.
- W4312406013 crossrefType "book-chapter" @default.
- W4312406013 hasAuthorship W4312406013A5016606943 @default.
- W4312406013 hasAuthorship W4312406013A5041189908 @default.
- W4312406013 hasAuthorship W4312406013A5052134135 @default.
- W4312406013 hasAuthorship W4312406013A5066965497 @default.
- W4312406013 hasAuthorship W4312406013A5069868868 @default.
- W4312406013 hasBestOaLocation W43124060132 @default.
- W4312406013 hasConcept C104317684 @default.
- W4312406013 hasConcept C121332964 @default.
- W4312406013 hasConcept C185592680 @default.
- W4312406013 hasConcept C39920418 @default.
- W4312406013 hasConcept C41008148 @default.
- W4312406013 hasConcept C44154836 @default.
- W4312406013 hasConcept C55493867 @default.
- W4312406013 hasConcept C63479239 @default.
- W4312406013 hasConcept C74650414 @default.
- W4312406013 hasConceptScore W4312406013C104317684 @default.
- W4312406013 hasConceptScore W4312406013C121332964 @default.
- W4312406013 hasConceptScore W4312406013C185592680 @default.
- W4312406013 hasConceptScore W4312406013C39920418 @default.
- W4312406013 hasConceptScore W4312406013C41008148 @default.
- W4312406013 hasConceptScore W4312406013C44154836 @default.
- W4312406013 hasConceptScore W4312406013C55493867 @default.
- W4312406013 hasConceptScore W4312406013C63479239 @default.
- W4312406013 hasConceptScore W4312406013C74650414 @default.
- W4312406013 hasLocation W43124060131 @default.
- W4312406013 hasLocation W43124060132 @default.
- W4312406013 hasOpenAccess W4312406013 @default.
- W4312406013 hasPrimaryLocation W43124060131 @default.
- W4312406013 hasRelatedWork W1920082486 @default.
- W4312406013 hasRelatedWork W1976533469 @default.
- W4312406013 hasRelatedWork W2023565566 @default.
- W4312406013 hasRelatedWork W2145330576 @default.
- W4312406013 hasRelatedWork W2363475415 @default.
- W4312406013 hasRelatedWork W2950851759 @default.
- W4312406013 hasRelatedWork W3208708633 @default.
- W4312406013 hasRelatedWork W4239295757 @default.
- W4312406013 hasRelatedWork W4327728461 @default.
- W4312406013 hasRelatedWork W2532429920 @default.
- W4312406013 isParatext "false" @default.
- W4312406013 isRetracted "false" @default.
- W4312406013 workType "book-chapter" @default.