Get Started
Home
Topics
Search
Library
Research questionHow can autonomous-driving scenario generators reliably induce collisions at a requested region of the target vehicle?Existing autonomous-driving scenario generators can produce crashes but offer limited control over where the target vehicle is struck. This makes it difficult to construct tests for region-specific collision behavior.
AI
Computer Vision
Diffusion Models
Evaluation & Benchmarks
Multimodal Models
Reasoning
Research Paper
Robotics
Technology
Latest papersRecent research connected to this question, newest first.CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario GenerationThe paper studies a VLM-guided diffusion framework for executable trajectories in WOMD-derived closed-loop scenarios. It reports target-collision success, contact-region control success, and trajectory naturalness, with evidence limited to that experimental setup.research paper · Sep 2, 2026
Related questions
How can synthetic driving videos preserve physically plausible vehicle trajectories after collisions when real crash footage is scarce?How can hybrid autonomous-driving planners align trajectory generation and refinement when their objectives differ?How can autonomous-driving planners be stress-tested in realistic closed-loop scenarios that expose failures missed by nominal benchmarks?How can low-cost platforms enable reproducible testing of end-to-end autonomous-driving policies across simulation and physical vehicles?