Wayve releases Learned Safety strategy after a decade of end-to-end AV research
alexgkendall · x · 2026-11-06
Wayve CEO Alex Kendall recalls being told since 2017 that end-to-end AI can't be safe and rule-based systems were required. The company now releases its Learned Safety strategy—the result of a decade of research on embedding learned safety into end-to-end driving AI and validating behavior at scale.
More from Embodied
- Aichi Institute of Tech's humanoid robot finishes last in ekiden relay but crosses the line — 4310sy · 2026-11-06
- OpenTac adds HDR tactile sensing: one sensor measures light touch and heavy loads at once — _krishna_murthy · 2026-11-06
- IEEE T-Haptics calls papers on touch in contact-rich dexterous manipulation, due March 2027 — HaozhiQ · 2026-11-06
- NVIDIA USDCode MCP Server brings expert Isaac Sim and USD scripting help to any MCP client — modelcontextprotocol · 2026-11-06
- Open-source humanoid Asimov 1 learns to dance on day 374 of its public build — freelerobot · 2026-11-06
- Browser-tab robot lab: upload a URDF and train a walking gait on GPU for free — R4nsack · 2026-11-06