Humanoid controllers need the ability to yield to external forces while retaining the capacity to resume their original tasks. However, tracking objectives penalize the deviations needed for yielding, while relaxing tracking goals persistently can make task recovery harder. Existing approaches often rely on task-specif...
Hao-Yang Li, Ke-Qi Zhu, Zhan-Xiang Cao et al.· 0 citations
This work proposes PACE (Preference-refined Affordance-Conditioned Execution), a supervised local execution module that augments frozen zero-shot semantic planners for reliable cross-floor navigation and integrates into six open-source zero-shot VLN navigators and demonstrates consistent improvements on the cross-floor...
Xue-Kang Yang, Lu-Yao Chen, Shuang Luo et al.· arXiv.org· 0 citations
This work introduces P^3 (Probabilistic Policy Propagation), a distribution-aware optimization framework for VAE-based policies that couples moment-based probabilistic method for stable and efficient learning with sampling-based calibration for robust policy behavior under latent uncertainty.
Li-Yun Yan, Jian-Ming Ma, Yang Zhang et al.· arXiv.org· 0 citations
ActSafeGuard is introduced, a differentiable and training-aligned safeguard layer for flow-matching based policies that integrates hard action feasibility into policy learning, not merely treating safety as an inference-time external component.
Jian-Ming Ma, Rong-Jun Jin, Xia-Xi Si et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.