Training Robots without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfer
This addresses the challenge of expensive and complex demonstration methods in robotics for tasks requiring force feedback, offering a more accessible approach, but it appears incremental as it builds on existing imitation learning techniques.
The study tackled the problem of training robots for force feedback-based manipulation tasks without needing robots for demonstrations, by proposing a master-to-robot policy transfer system using a controller with force/torque sensors; it achieved successful evaluation on a bottle-cap-opening task, though no concrete numbers were provided.
Deep imitation learning is promising for robot manipulation because it only requires demonstration samples. In this study, deep imitation learning is applied to tasks that require force feedback. However, existing demonstration methods have deficiencies; bilateral teleoperation requires a complex control scheme and is expensive, and kinesthetic teaching suffers from visual distractions from human intervention. This research proposes a new master-to-robot (M2R) policy transfer system that does not require robots for teaching force feedback-based manipulation tasks. The human directly demonstrates a task using a controller. This controller resembles the kinematic parameters of the robot arm and uses the same end-effector with force/torque (F/T) sensors to measure the force feedback. Using this controller, the operator can feel force feedback without a bilateral system. The proposed method can overcome domain gaps between the master and robot using gaze-based imitation learning and a simple calibration method. Furthermore, a Transformer is applied to infer policy from F/T sensory input. The proposed system was evaluated on a bottle-cap-opening task that requires force feedback.