Motion Planning for a Humanoid Mobile Manipulator System

A high redundant non-holonomic humanoid mobile dual-arm manipulator system (MDAMS) is presented in this paper, where the motion planning to realize "human-like" autonomous navigation and manipulation tasks is studied. First, an improved MaxiMin NSGA-II algorithm, which optimizes five objective functions to solve the problems of singularity, redundancy and coupling between mobile base and manipulator simultaneously, is proposed to design the optimal pose to manipulate the target object. Then, in order to link the initial pose and that optimal pose, an off-line motion planning algorithm is designed. In detail, an efficient direct-connect bidirectional RRT and gradient descent algorithm is proposed to reduce the sampled nodes largely, and a geometric optimization method is proposed for path pruning. Besides, head forward behaviors are realized by calculating the reasonable orientations and assigning them to the mobile base to improve the quality of human-robot interaction. Third, the extension to online planning is done by introducing real-time sensing, collision-test and control cycles to update robotic motion in dynamic environments. Fourth, an EEs' via-point-based multi-objective genetic algorithm (MOGA) is proposed to design the "human-like" via-poses by optimizing four objective functions. Finally, numerous simulations are presented to validate the effectiveness of proposed algorithms.