Rapid Humanoid Motion Learning through Coordinated, Parallel Evolution

Abstract. Planning movements for humanoid robots is still a major challenge due to the very high degrees-of-freedom involved. Most hu-manoid control frameworks incorporate dynamical constraints related to a task that require detailed knowledge of the robot’s dynamics, making them impractical as efficient planning. In previous work, we introduced a novel planning method that uses an inverse kinematics solver called Nat-ural Gradient Inverse Kinematics (NGIK) to build task-relevant roadmaps (graphs in task space representing robot configurations that satisfy task constraints) by searching the configuration space via the Natural Evolu-tion Strategies (NES) algorithm. The approach places minimal require-ments on the constraints, allowing for complex planning in the task space. However, building a roadmap via NGIK is too slow for dynamic envi-ronments. In this paper, the approach is scaled-up to a fully-parallelized implementation where additional constraints coordinate the interaction between independent NES searches running on separate threads. Par-allelization yields a 12 × speedup that moves this promising planning method a major step closer to working in dynamic environments