Learning to Act Through Contact: A Unified View of Multi-Task Robot Learning
For robot learning researchers, this work provides a scalable foundation for multi-task loco-manipulation by unifying task definitions through contact goals, though the novelty is incremental as it combines existing ideas of goal-conditioned RL and contact planning.
This paper proposes a unified framework for multi-task locomotion and manipulation that uses contact-explicit representations to train a single policy across diverse tasks and embodiments. The approach achieves versatile behaviors on quadrupeds and humanoids for gaits and manipulation, with improved generalization to unseen scenarios.
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