Autonomous vehicles need human-interactive autonomy beyond just stopping

A new paper analyzes incidents involving autonomous vehicles (AVs) where their minimal risk condition (MRC) behaviors, such as stopping, have caused disruptions. The research categorizes these failures based on perception, planning, and control limitations within current AV systems. It highlights the need for AVs to interpret human authority, respond to multimodal instructions, and adapt to dynamic traffic conditions, suggesting a shift towards human-interactive autonomy for reliable urban deployment. AI

IMPACT Highlights the need for more sophisticated human-AI interaction in autonomous systems beyond basic safety protocols.

RANK_REASON The cluster contains an academic paper analyzing a specific technical challenge in autonomous vehicle safety. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Autonomous vehicles
• Human-Interactive Autonomous Driving
• Minimal Risk Condition
• Safe Transportation Systems

• paper
• safety
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →