Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add future imagining to L-RA (ablation) | Risk Assessment (RA) · Epic Fail (EF) | accident anticipation mAP: 74.2 -> 75.1 | Helped |
| add future imagining to L-RA (ablation) | Risk Assessment (RA) · Street Accident (SA) | accident anticipation mAP: 49.1 -> 51.4 | Helped |
| add future imagining to L-RA (ablation) | Risk Assessment (RA) · Epic Fail (EF) | ATTA: 1.84 -> 2.23 | Helped |
| add future imagining to L-RA (ablation) | Risk Assessment (RA) · Street Accident (SA) | ATTA: 3.04 -> 3.01 | Hurt |
| add memory to RA (ablation) | Risk Assessment (RA) · Epic Fail (EF) | accident anticipation mAP: 72.2 -> 74.2 | Helped |
| add memory to RA (ablation) | Risk Assessment (RA) · Street Accident (SA) | accident anticipation mAP: 47.8 -> 49.1 | Helped |
| add memory to RA (ablation) | Risk Assessment (RA) · Epic Fail (EF) | ATTA: 2.10 -> 1.84 | Hurt |
| add memory to RA (ablation) | Risk Assessment (RA) · Street Accident (SA) | ATTA: 2.55 -> 3.04 | Helped |
| add memory to the single-frame RA model (ablation) | Risk Assessment (RA) · Epic Fail (EF) | risky-region mAP: 12.3 -> 14.0 | Helped |
| add memory to the single-frame RA model (ablation) | Risk Assessment (RA) · Street Accident (SA) | risky-region mAP: 40.1 -> 43.8 | Helped |
| add future imagining (ablation) | Risk Assessment (RA) · Epic Fail (EF) | risky-region mAP: 14.0 -> 15.1 | Helped |
| add future imagining (ablation) | Risk Assessment (RA) · Street Accident (SA) | risky-region mAP: 43.8 -> 45.4 | Helped |
Closest papers by meaning
- Accident Anticipation via Temporal Occurrence Prediction (NeurIPS 2025 · similarity 0.83)
- Building a Foundational Guardrail for General Agentic Systems via Synthetic Data (ICLR 2026 · similarity 0.82)
- Progressive Risk Estimation for Accident Anticipation (NeurIPS 2026 · similarity 0.82)
- Safety through feedback in Constrained RL (NeurIPS 2024 · similarity 0.82)
- RedVLA: Physical Red Teaming for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.81)
- AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions (CVPR 2026 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.