Skip to content
arXiv Robotics — research abstracts· Haodong Yang, Runhan Huang, Bowen Zhang, Iofai Lei, Zunzhe Zhang, Xiangcheng Zhang, Shaoting Zhu, Linzhan Mou, Yicheng Liu, Hang Zhao·· 5 days agoEditorial score62

EqC: Equilibrium Energy Control for Introspective Lifelong Robot Learning

EqC: Equilibrium Energy Control for Introspective Lifelong Robot Learning

Summary

EqC is a framework for introspective lifelong robot learning that enables policies to recognize when their behavior is no longer supported and use assistance to improve. It casts generative action refinement as equilibrium-seeking optimization and integrates with Diffusion Transformer and VLA policies, showing improved control performance and robustness in simulation and real-world bimanual manipulation tasks.

Source: arXiv Robotics — research abstracts · Read original article ↗

Loading article text…

Source:arXiv Robotics — research abstracts · arxiv.org

Timezone · UTC

Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).