Event
KEC uses Fable and Astra to tune robot simulation parameters
2 reports · 1 sources
Ken Goldberg states that KEC combines Fable and Astra to adjust complex simulation parameters—including geometry, dynamics, deformation, materials, lighting, textures, and camera extrinsics—via RSS, so that the simulation matches a given input video. Previously, his claim was that large language models can use RSS to accomplish this kind of parameter tuning. According to Goldberg's description, given an online image or even an Amazon link as input, the two can reconstruct the scene in RoboSimStudio for a robot to use within 2 hours. This work targets the capability gap for embodied intelligent robots to scale to new environments, new objects, and new tasks. The above results come from Goldberg's own account; the report provides no experimental data or comparison results, so the actual parameter-tuning performance cannot yet be confirmed.
Report timeline
- KEC combines Fable and Astra for parameter tuning to achieve real2sim
KEC combines Fable with Astra to rapidly tune complex simulation parameters via RSS, including geometry, dynamics, deformation, materials, lighting, textures, and camera extrinsics, so that the simulation matches a given input video. This work targets the capability gap in agentic robotics for extending to new environments, new objects, and new tasks.
Ken Goldberg ·
- LLMs use RSS to tune robot simulation parameters
Large language models (LLMs) can use RSS to tune the parameters of complex robot manipulation simulations to match a given video, covering geometry, dynamics, deformation, materials, lighting, textures, and camera extrinsics, which I find impressive.
Ken Goldberg ·
Related topics
Interest trend
- Current
- 3
- Peak
- 7Nov 4 01:00
- Past 24 hours
- -50%
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.