Multi-contact loco-manipulation trajectories for the ANYmal robot with a 6-DoF Arm

<p>Loco-manipulation planning skills are pivotal for expanding the utility of robots in everyday environments. These skills can be assessed based on a system's ability to coordinate complex holistic movements and multiple contact interactions when solving different tasks. However, existing approaches have been merely able to shape such behaviors with hand-crafted state machines, densely engineered rewards, or pre-recorded expert demonstrations. Here, we propose a minimally-guided framework that automatically discovers whole-body trajectories jointly with contact schedules for solving general loco-manipulation tasks in pre-modeled environments. The key insight is that multi-modal problems of this nature can be modeled within the context of integrated Task and Motion Planning (TAMP), resulting in a tractable bilevel optimization formulation. An effective bilevel search strategy is achieved owing to the fusion of domain-specific rules with the well-established strengths of different planning techniques: trajectory optimization and informed graph search, coupled with sampling-based planning. We showcase emergent behaviors for a quadrupedal mobile manipulator exploiting both prehensile and non-prehensile interactions to perform real-world tasks such as opening/closing heavy dishwashers and traversing spring-loaded doors. These behaviors are also deployed on the real system using a two-layer whole-body tracking controller.</p>