US Patent 12070853 Soft-rigid robotic joints controlled by deep reinforcement-learning

A robotic arm having one or more hybrid (soft-rigid) joints includes a first link, a second link, and a joint interconnecting the first link and the second link, such that the first link is movable relative to the second link along an axis of motion. The joint includes: a socket component coupled to a distal end portion of the second link and a ball component coupled to a proximal end portion of first link, the ball component is configured to rotationally fit within the socket component. The joint also includes a flexible membrane encasing the socket component and the ball component. The robotic arm is controllable using a reinforcement learning algorithm training using a simulation of the robotic arm and optionally, further training in a physical world.