Determination of optimal arm and hand configurations for grasping objects by humanoid robots and avatars

This paper presents an algorithm that computes arm motion and hand grasp configuration to reach and grasp an object by a humanoid robot. Although grasping an object is a relatively easy task for humans, this task needs to take into account many constraints including arm joint limits, stability of grasp, and the possibility of collisions between the robot and objects in the environment, The presented algorithm finds the optimal arm and hand configuration to grasp an object without enumerating all possible configurations by employing heuristics to guide the search. Efficiency is gained by evaluating different constraints in increasing order of complexity so as to eliminate infeasible grasp configurations with minimal computation. Computed grasp configurations are such that arm joints are far from their limits, and they are close to grasps used by humans. Our algorithm will be an important module for humanoid robots and avatars in virtual reality systems