NavSafe-∞: photorealistic closed-loop benchmark exposes safety gap across 20 E2E driving policies
zhoubolei · x · 2026-10-08
Researchers from UCLA, UCSD and Toyota Research Institute released NavSafe-∞, an open photorealistic closed-loop driving safety benchmark with 280 event-based scenarios across 28 safety-critical event types (crashes, incidents, violations, vulnerable road users), built from photorealistic nuPlan reconstructions. Evaluating 20 end-to-end policies, they show comparable open-loop scores can lead to very different safety outcomes in closed-loop execution, exposing a consistent OL-to-CL safety gap. Paper, code and dataset are public.
More from Embodied
- Comma_ai user praises driving data setup, but car chewed through the cables — fforres · 2026-10-08
- ~200 production Cybercabs without steering wheels spotted staging in Houston — JOBhakdi · 2026-10-08
- LEDGER builds persistent 3D object memory from egocentric video, answers questions without rewatching — mangahomanga · 2026-10-08
- SEAR benchmark tests how LLM agents self-evolve on robots, from DeepSeek to Astra — xiye_nlp · 2026-10-08
- Polymarket bets open on whether Meta ships its Tamagotchi-style Muse Charm AI device by December — Polymarket · 2026-10-08
- Microsoft's $5,999 Surface RTX Spark Dev Box preorders open, ships November — tomwarren · 2026-10-08