GitHub · Python
HexaFuture/EmbodiedLab
Manipulation benchmarks test acting to change; EmbodiedLab tests acting to know. Given only an objective and the apparatus, a robot runs its own experiment in a physics-based lab to find out a result it cannot know in advance. 30 science experiments, scored exactly.
- Stars
- 18
- Forks
- 2
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: ai-for-science, benchmark, embodied-ai, isaac-sim, llm-agents, physics-simulation, robot-manipulation, robotics, scientific-discovery
Latest data point: Nov 21, 2026 · 18 stars · 2 forks