Learning to Navigate Cloth using Haptics
This work addresses the challenge of robotic manipulation of deformable objects like clothing, which is important for applications in domestic robotics and automation, but it is incremental as it builds on existing haptic and reinforcement learning methods in simulation.
The paper tackled the problem of enabling a robotic arm to navigate deformable cloth garments in simulation without causing damage, by developing a controller that uses haptic feedback from multiple sensing spheres to guide movement and resolve conflicts through inverse kinematics, and demonstrated successful navigation across various garments while outperforming baseline controllers.
We present a controller that allows an arm-like manipulator to navigate deformable cloth garments in simulation through the use of haptic information. The main challenge of such a controller is to avoid getting tangled in, tearing or punching through the deforming cloth. Our controller aggregates force information from a number of haptic-sensing spheres all along the manipulator for guidance. Based on haptic forces, each individual sphere updates its target location, and the conflicts that arise between this set of desired positions is resolved by solving an inverse kinematic problem with constraints. Reinforcement learning is used to train the controller for a single haptic-sensing sphere, where a training run is terminated (and thus penalized) when large forces are detected due to contact between the sphere and a simplified model of the cloth. In simulation, we demonstrate successful navigation of a robotic arm through a variety of garments, including an isolated sleeve, a jacket, a shirt, and shorts. Our controller out-performs two baseline controllers: one without haptics and another that was trained based on large forces between the sphere and cloth, but without early termination.