cs.RONov 19, 2026

PGX: Physically Grounded Execution for Long-Horizon Humanoid Loco-Manipulation

Authors: Kai Lu, Chenyang Ma, Ioannis Havoutis

Organizations: K. Lu and I. Havoutis are with the Oxford Robotics Institute, University of Oxford. · C. Ma is with the Department of Computer Science, University of Oxford.

Abstract

Robotic vision-language-action (VLA) models can execute diverse individual manipulation skills, yet they still struggle with long-horizon loco-manipulation tasks, where temporal structure, skills, and precision are tightly coupled within a monolithic model. We propose Physically Grounded Execution (PGX), a framework that offloads temporal and precision control to two classical training-free components, allowing the VLA to focus on stage-specific skill dynamics. PGX decomposes long-horizon loco-manipulation into three layers: (i) a predicate-based state machine governs task progression, using physical predicates to gate phase transitions, trigger recovery, and coordinate navigation and waiting. Shared predicate semantics connect offline demonstration segmentation, online execution, and stage-wise evaluation; (ii) VLA skills operate within active manipulation phases, with flat or stage-trained models concentrating on task-relevant actions; and (iii) world-coordinate locking (WCL) maintains spatial consistency through base station keeping, object-relative positioning, and world-anchored contact targets. We demonstrate the effectiveness of PGX with extensive experiments conducted on three simulated tasks and one real-world task using a Unitree G1 humanoid robot for long-horizon loco-manipulation, showing improvements in stage progression and task success rates. Project page is available at: https://kl-research.github.io/pgx

Figures & tables

Explore similar work

CardsList
  1. ViLoMan: Learning Visual-Proprioceptive Whole-Body Loco-Manipulation Skills for Humanoid Robots

    Sep 16, 2026Zejie Tian, Ruibing Hou, Bingpeng Ma +2Visuomotor Policy LearningWhole-Body Robotic Manipulation

  2. GTI: Grounding Task Intent Throughout Long-Horizon VLA Manipulation

    Nov 18, 2026Tianqi Gong, Haochen Niu, Yusheng Zhao +4Long-Horizon Robotic ManipulationRobotics

  3. TemporalFlow-VLA: Learning Physically Grounded Execution History for Long-Horizon Robot Manipulation

    Aug 27, 2026Jiarui Yang, Yehao Lu, Yuning Su +9Robot LearningLong-Horizon Robotic Manipulation