← 研踪 PaperTrailarXiv:2611.02691 · v1
Closing the Dynamics Gap through Self-Directed Robotic Interaction
首次提交 2026-11-02 15:40
版本更新 2026-11-02 15:40
雷达观测 2026-11-04 23:42
摘要
Agentic Real2Sim2Real systems can reconstruct a scene in simulation from camera observations, but contact-rich dynamics such as friction and restitution cannot be observed without interaction. We call this the dynamics gap and present CUE, an agentic system that closes it by interacting with the environment itself. Given only a high-level instruction and no resets, the agent builds its own perception, identifies physical parameters, and targets interactions where its simulation is least accurate. On billiards, CUE reduces held-out ball-position error by 72% relative to the strongest baseline across 25 hidden-physics conditions in simulation, and we further deploy it on a real pool table. More details can be found on the project website: https://cue-dynamics.github.io/
作者备注：Accepted to CoRL 2026 Late Breaking Results. Project website: https://cue-dynamics.github.io/
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-02 15:40 · 最新观测版本
Closing the Dynamics Gap through Self-Directed Robotic Interaction
Agentic Real2Sim2Real systems can reconstruct a scene in simulation from camera observations, but contact-rich dynamics such as friction and restitution cannot be observed without interaction. We call this the dynamics gap and present CUE, an agentic system that closes it by interacting with the environment itself. Given only a high-level instruction and no resets, the agent builds its own perception, identifies physical parameters, and targets interactions where its simulation is least accurate. On billiards, CUE reduces held-out ball-position error by 72% relative to the strongest baseline across 25 hidden-physics conditions in simulation, and we further deploy it on a real pool table. More details can be found on the project website: https://cue-dynamics.github.io/
查看此版本解读 →查看此版本原文 ↗