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

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.