Efficient Humanoid Contact Planning using Learned Centroidal Dynamics Prediction
This work addresses the need for efficient dynamic contact planning in robotics, offering a solution that overcomes computational limitations of prior methods for robots with arms and legs.
The paper tackles the problem of planning dynamic contact sequences for humanoid robots on rough terrain by learning a prediction of centroidal dynamics, enabling efficient generation of robust contact sequences for challenging scenarios like steep slopes and wide gaps.
Humanoid robots dynamically navigate an environment by interacting with it via contact wrenches exerted at intermittent contact poses. Therefore, it is important to consider dynamics when planning a contact sequence. Traditional contact planning approaches assume a quasi-static balance criterion to reduce the computational challenges of selecting a contact sequence over a rough terrain. This however limits the applicability of the approach when dynamic motions are required, such as when walking down a steep slope or crossing a wide gap. Recent methods overcome this limitation with the help of efficient mixed integer convex programming solvers capable of synthesizing dynamic contact sequences. Nevertheless, its exponential-time complexity limits its applicability to short time horizon contact sequences within small environments. In this paper, we go beyond current approaches by learning a prediction of the dynamic evolution of the robot centroidal momenta, which can then be used for quickly generating dynamically robust contact sequences for robots with arms and legs using a search-based contact planner. We demonstrate the efficiency and quality of the results of the proposed approach in a set of dynamically challenging scenarios.