English

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

Robotics 2026-07-20 v1

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/

Keywords

Cite

@article{arxiv.2607.17651,
  title  = {HCPG-Flow:Hierarchical Contact-Progress Guidance for Flow-Policy Robot Manipulation},
  author = {Guanghu Xie and Mingxu Li and Shuo Zhang and Yonglong Zhang and Yifan Yang and Yang Liu and Zongwu Xie and Baoshi Cao},
  journal= {arXiv preprint arXiv:2607.17651},
  year   = {2026}
}