A Human-like Upper-limb Motion Planner: Generating naturalistic movements for humanoid robots

As robots are starting to become part of our daily lives, they must be able cooperate in a natural and efficient manner with humans socially accepted. Human-like morphology motion often considered key features for intuitive human–robot interactions because allow human peers easily predict the final intention robotic movement. Here, we present novel planning algorithm, Upper-limb Motion Planner, upper limb anthropomorphic robots, that generates collision-free trajectories human-like characteristics. Mainly inspired from established theories motor control, process takes into account task-dependent hierarchy spatial postural constraints modelled as cost functions. For experimental validation, generate arm-hand series tasks including simple point-to-point reaching movements sequential object-manipulation paradigms. Being major contribution current literature, specific focus is on kinematics naturalistic arm during avoidance obstacles. To evaluate human-likeness, observe kinematic regularities adopt smoothness measures applied control studies distinguish between well-coordinated impaired movements. The results this study show proposed algorithm capable at computational allows fluent interactions.