Redundancy-aware Action Spaces for Robot Learning
This work addresses the problem of inefficient training and limited control in robot manipulation for researchers and practitioners in robotics, offering an incremental improvement over existing action space formulations.
The paper tackles the trade-off between joint space and task space control for robot arms by introducing the ER action space, which addresses manipulator redundancies to combine precise control with efficient learning, demonstrating superior performance especially in settings requiring precise configuration control.
Joint space and task space control are the two dominant action modes for controlling robot arms within the robot learning literature. Actions in joint space provide precise control over the robot's pose, but tend to suffer from inefficient training; actions in task space boast data-efficient training but sacrifice the ability to perform tasks in confined spaces due to limited control over the full joint configuration. This work analyses the criteria for designing action spaces for robot manipulation and introduces ER (End-effector Redundancy), a novel action space formulation that, by addressing the redundancies present in the manipulator, aims to combine the advantages of both joint and task spaces, offering fine-grained comprehensive control with overactuated robot arms whilst achieving highly efficient robot learning. We present two implementations of ER, ERAngle (ERA) and ERJoint (ERJ), and we show that ERJ in particular demonstrates superior performance across multiple settings, especially when precise control over the robot configuration is required. We validate our results both in simulated and real robotic environments.