AI Daybook
AI Daybook
Today's issue
RepoPhysical AI

LEASH introduces RoboRisk benchmark for agentic robotics safety

Original titlezhuqinfeng1999/LEASH

Outlet
GitHub
Published
Importance
3/5
Trending
7

Summary

LEASH is a project that evaluates safety in robot agents. It provides the RoboRisk benchmark comprising 92 simulated tasks and 13 real-robot tasks, along with a camera-grounded safety harness. The work is designed for researchers and developers validating the safety of foundation-model-based robot planners.

Original excerpt

LEASH: Stay Safe in Agentic Robotics. RoboRisk benchmark (92 simulated + 13 real-robot tasks) and a camera-grounded safety harness for foundation-model robot planners. · topics: agentic-ai, ai-safety, benchmark, embodied-ai, foundation-models, libero, llm-agents, robot-manipulation, robot-safety, robotics, vision-language-models

#benchmark#robotics#safety#embodied-ai
Read the original
See all →