Placement Optimization for Humanoid Robot Manipulation Using a Task-Driven Planning Method

Planning a placement is crucial for humanoid robots to successfully execute specific manipulation tasks. While a feasible solution of placement ensures that the end-effector can reach the desired poses, it does not specify the arm configuration during the task. This paper introduces a task-driven planning method to optimize placement for manipulation tasks, enhancing overall configuration manipulability. Our approach employs heuristic designs to define manipulation tasks with key information besides the desired relative poses between the end-effector and targets. We establish a quadratic programming (QP) controller to track these desired poses, enabling the automatic generation of joint trajectories. Additionally, we use Particle Swarm Optimization (PSO) to optimize placement based on task information, aiming to minimize end-effector pose errors and maximize manipulability. The effectiveness of our method is demonstrated through experiments conducted with the BHR humanoid robot.