MEGA Hub
New

HCPG-Flow:Hierarchical Contact-Progress Guidance for Flow-Policy Robot Manipulation

Published on Jul 20cs.RO

Authors

Do you know Guanghu Xie?You can claim authorship or link another user.Do you know Mingxu Li?You can claim authorship or link another user.Do you know Shuo Zhang?You can claim authorship or link another user.Do you know Yonglong Zhang?You can claim authorship or link another user.Do you know Yifan Yang?You can claim authorship or link another user.Do you know Yang Liu?You can claim authorship or link another user.Do you know Zongwu Xie?You can claim authorship or link another user.Do you know Baoshi Cao?You can claim authorship or link another user.

Abstract

Flow policies can represent multimodal action distributions for robot manipulation, yet a robot must execute one action at each control step. When several proposals are sampled, critic-based ranking makes data collection depend on value estimates over candidate actions that may be weakly represented in replay. We introduce HCPG-Flow, an analytic rollout-time selector that augments SAC-Flow with hierarchical, object-centric contact-progress guidance while preserving its actor and critic objectives. HCPG switches from end-effector approach to task progress after contact, scores each proposal by the first-order reduction of a task-relevant distance, standardizes scores within the candidate set, and executes a temperature-controlled action embedding. Across ten simulated tasks, HCPG improves mean success over SAC-Flow on both benchmarks, including a 9.5 percentage-point gain on Maniskill. Four physical tasks further show high success with a 17.4% reduction in successful completion steps.Project page: https://hitxraz.github.io/HCPG-Flow/

Community

00