Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Interaction-Aware Whole-Body Control for Compliant Object Transport

Hao Zhang, Yves Tseng, Ding Zhao, H. Eric Tseng

TL;DR

A bio-inspired, interaction-oriented whole-body control that functions as an artificial cerebellum - an adaptive motor agent that translates upstream commands into stable, physically consistent whole-body behavior under contact, enabling compliant object transport across a wide range of scenarios.

Abstract

Cooperative object transport in unstructured environments remains challenging for assistive humanoids because strong, time-varying interaction forces can make tracking-centric whole-body control unreliable, especially in close-contact support tasks. This paper proposes a bio-inspired, interaction-oriented whole-body control (IO-WBC) that functions as an artificial cerebellum - an adaptive motor agent that translates upstream (skill-level) commands into stable, physically consistent whole-body behavior under contact. This work structurally separates upper-body interaction execution from lower-body support control, enabling the robot to maintain balance while shaping force exchange in a tightly coupled robot-object system. A trajectory-optimized reference generator (RG) provides a kinematic prior, while a reinforcement learning (RL) policy governs body responses under heavy-load interactions and disturbances. The policy is trained in simulation with randomized payload mass/inertia and external perturbations, and deployed via asymmetric teacher-student distillation so that the student relies only on proprioceptive histories at runtime. Extensive experiments demonstrate that IO-WBC maintains stable whole-body behavior and physical interaction even when precise velocity tracking becomes infeasible, enabling compliant object transport across a wide range of scenarios.

Interaction-Aware Whole-Body Control for Compliant Object Transport

TL;DR

A bio-inspired, interaction-oriented whole-body control that functions as an artificial cerebellum - an adaptive motor agent that translates upstream commands into stable, physically consistent whole-body behavior under contact, enabling compliant object transport across a wide range of scenarios.

Abstract

Cooperative object transport in unstructured environments remains challenging for assistive humanoids because strong, time-varying interaction forces can make tracking-centric whole-body control unreliable, especially in close-contact support tasks. This paper proposes a bio-inspired, interaction-oriented whole-body control (IO-WBC) that functions as an artificial cerebellum - an adaptive motor agent that translates upstream (skill-level) commands into stable, physically consistent whole-body behavior under contact. This work structurally separates upper-body interaction execution from lower-body support control, enabling the robot to maintain balance while shaping force exchange in a tightly coupled robot-object system. A trajectory-optimized reference generator (RG) provides a kinematic prior, while a reinforcement learning (RL) policy governs body responses under heavy-load interactions and disturbances. The policy is trained in simulation with randomized payload mass/inertia and external perturbations, and deployed via asymmetric teacher-student distillation so that the student relies only on proprioceptive histories at runtime. Extensive experiments demonstrate that IO-WBC maintains stable whole-body behavior and physical interaction even when precise velocity tracking becomes infeasible, enabling compliant object transport across a wide range of scenarios.
Paper Structure (16 sections, 7 equations, 7 figures, 3 tables)

This paper contains 16 sections, 7 equations, 7 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Whole-Body Control and Reinforcement Learning
  4. Bionic-Inspired Hierarchical Body Control
  5. Motion Synthesis and Kinematic Priors
  6. Methodology
  7. System Modeling and Cascaded Control Architecture
  8. Kinematic Mapping and Reference Generator
  9. Learning Strategy and Asymmetric Distillation
  10. Interaction Robustness and Multi-Objective Reward
  11. Experimental Evaluation
  12. Experimental Setup and Baselines
  13. Performance Benchmark and Ablation Study
  14. Postural Resilience in Lifting Tasks
  15. Effectiveness and Compliance in Heavy-Duty Pushing
  16. ...and 1 more sections

Figures (7)

  • Figure 1: The proposed IO-WBC architecture that bridges skill-level HRC commands with low-level execution through a kinematic-prior-based RG, enabling stable coordination between upper-body interaction and lower-body support under strong robot--object coupling.
  • Figure 2: The comprehensive learning and execution pipeline of IO-WBC. The RG is trained via supervised learning to provide kinematic priors. The interaction-oriented WBC policy is developed through teacher-student distillation, where a privileged teacher guides a student policy to decode interaction dynamics from proprioceptive history.
  • Figure 3: Comprehensive performance comparison across algorithm variants. (a-b) Norm error for lifting and pushing scenarios. (c) Success rates across real-world task scenarios, highlighting the robustness of the full IO-WBC framework.
  • Figure 4: Visualization of the learning hierarchy in simulation. The framework encompasses single-agent skill learning for the IO-WBC layer and MARL for high-level HRC coordination.
  • Figure 5: Real-world deployment of IO-WBC on the HRC tasks between human and Unitree G1, including path-constrained collaborative pushing and carrying, as well as collaborative super-heavy object carrying. Specifically, the red dashed regions highlight the adaptive vertical synchronization and postural resilience during the transport of a 7 kg box and an 18 kg tire.
  • ...and 2 more figures