The SURE_REACH Model for Motor Learning and Control of a Redundant Arm: From Modeling Human Behavior to Applications in Robotics

摘要: The recently introduced neural network SURE_REACH (sensorimotor unsupervised redundancy resolving control architecture) models motor cortical learning and of human reaching movements. model learns redundant, internal body that are highly suitable to flexibly invoke effective commands. encoded is used adapt behavior flexible situational constraints without the need for further learning. These adaptations specific tasks or situations realized by a neurally generated movement plan adheres various end-state trajectory-related constraints. can be implemented proprioceptive visual closed-loop control. This chapter briefly reviews literature on computational gives description its implementation. Furthermore, we relate performance discuss foundations. Finally, apply dynamic robot platform. In sum, grounds task-dependent framework It accounts processes underlie fundamental aspects well applicable robots.