Joint Space Control via Deep Reinforcement Learning
This simplifies robot control for robotics researchers and engineers by automatically handling redundancy, joint limits, and acceleration profiles, though it is incremental as it builds on existing deep reinforcement learning methods.
The paper tackled robot manipulator control by replacing hand-crafted differential equations with a deep neural network trained via model-free reinforcement learning to map from task space to joint space, achieving sub-centimeter accuracy in simulation and real-world experiments.
The dominant way to control a robot manipulator uses hand-crafted differential equations leveraging some form of inverse kinematics / dynamics. We propose a simple, versatile joint-level controller that dispenses with differential equations entirely. A deep neural network, trained via model-free reinforcement learning, is used to map from task space to joint space. Experiments show the method capable of achieving similar error to traditional methods, while greatly simplifying the process by automatically handling redundancy, joint limits, and acceleration / deceleration profiles. The basic technique is extended to avoid obstacles by augmenting the input to the network with information about the nearest obstacles. Results are shown both in simulation and on a real robot via sim-to-real transfer of the learned policy. We show that it is possible to achieve sub-centimeter accuracy, both in simulation and the real world, with a moderate amount of training.