ThorArena: Benchmarking Humanoid Physical Interaction with Human Motion-Force Demonstrations

2026-07-07

AI Summary

Existing evaluations of humanoid robots predominantly focus on motion trajectories while neglecting concurrent interaction forces, thereby failing to comprehensively assess tracking accuracy, stability, and control robustness in contact-intensive tasks. This work proposes ThorArena, a novel benchmark that introduces the first dataset capturing synchronized full-body human motion and bimanual interaction forces. It further presents new metrics such as Force-Aware Tracking Score (FATS). By integrating high-fidelity motion capture with force-sensing systems, a force-replay mechanism in simulation, and a unified control interface, the framework establishes a reproducible, force-aware evaluation protocol. Experimental results demonstrate that this approach effectively uncovers performance differences among control strategies that conventional force-agnostic assessments cannot detect, offering a more comprehensive evaluation methodology for physical human–robot interaction.

Abstract

Humanoid robots are increasingly expected to perform contact-rich tasks that require not only accurate whole-body motion but also robust physical interaction with surrounding objects and humans. Although recent advances in humanoid motion imitation and whole-body control have achieved remarkable tracking performance, existing datasets and benchmarks primarily focus on kinematic motion while largely overlooking synchronized interaction forces. As a result, current evaluations fail to capture how external interaction forces affect tracking accuracy, stability, and control robustness. In this paper, we present ThorArena, a benchmark for evaluating force-aware humanoid interaction based on human demonstrations with synchronized motion and force measurements. We collect a real-world interaction dataset that simultaneously captures whole-body human motion and forces exerted by both hands across six representative physical interaction tasks. Based on these demonstrations, we propose force-aware evaluation metrics that jointly assess whole-body tracking accuracy, robustness under different force levels, control effort, and episode survival through the Force-Aware Tracking Score (FATS) and complementary diagnostic metrics. We further establish a unified benchmark protocol that replays recorded interaction forces in simulation and provides a standardized evaluation interface for different humanoid control policies. Experiments on representative whole-body control policies demonstrate that force-aware evaluation reveals substantial performance differences that remain largely hidden under conventional no-force evaluation. ThorArena provides a practical and reproducible framework for studying force-aware humanoid interaction and offers a new benchmark for evaluating contact-rich humanoid behaviors.

Problem

• humanoid robots
• physical interaction
• interaction forces
• benchmarking
• force-aware evaluation

Innovation

• force-aware benchmark
• humanoid physical interaction
• synchronized motion-force demonstrations
• Force-Aware Tracking Score (FATS)
• whole-body control evaluation