Learning to Act Through Contact: A Unified View of Multi-Task Robot Learning

arXiv cs.RO / 5/5/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes a unified framework for multi-task robot locomotion and manipulation using an explicit contact-based representation rather than separate policies per task.
Tasks are defined via contact goals (desired contact positions, timing, and active end-effectors), and a single goal-conditioned reinforcement learning policy learns to realize any provided contact plan.
The approach is validated across different robot embodiments, including quadrupeds and humanoids, where one policy controls multiple gaits and biped/quadrupedal locomotion.
For manipulation, the same contact-grounded policy is shown to handle multiple bimanual object manipulation tasks on a humanoid.
The authors report that explicit contact reasoning improves generalization to unseen scenarios, suggesting a scalable foundation for loco-manipulation learning.

Abstract

We present a unified framework for multi-task locomotion and manipulation policy learning grounded in a contact-explicit representation. Instead of designing different policies for different tasks, our approach unifies the definition of a task through a sequence of contact goals--desired contact positions, timings, and active end-effectors. This enables leveraging the shared structure across diverse contact-rich tasks, leading to a single policy that can perform a wide range of tasks. In particular, we train a goal-conditioned reinforcement learning (RL) policy to realise given contact plans. We validate our framework on multiple robotic embodiments and tasks: a quadruped performing multiple gaits, a humanoid performing multiple biped and quadrupedal gaits, and a humanoid executing different bimanual object manipulation tasks. Each of these scenarios is controlled by a single policy trained to execute different tasks grounded in contacts, demonstrating versatile and robust behaviours across morphologically distinct systems. Our results show that explicit contact reasoning significantly improves generalisation to unseen scenarios, positioning contact-explicit policy learning as a promising foundation for scalable loco-manipulation. Video available at: https://youtu.be/idHx67oHHU0?si=qZJ7C0ujemXNWgA5