Composing Dextrous Grasping and In-hand Manipulation via Scoring with a Reinforcement Learning Critic
This work addresses a key bottleneck for deploying in-hand manipulation policies in real-world robotics by bridging the gap between grasping and manipulation, though it is incremental as it builds on existing reinforcement learning methods.
The paper tackles the problem of enabling autonomous in-hand manipulation by selecting initial grasps that promote manipulation success, using a reinforcement learning critic to score grasps without additional training. The method significantly increases manipulation success rates and is implemented on a real-world system for autonomous grasping and reorientation of unwieldy objects.
In-hand manipulation and grasping are fundamental yet often separately addressed tasks in robotics. For deriving in-hand manipulation policies, reinforcement learning has recently shown great success. However, the derived controllers are not yet useful in real-world scenarios because they often require a human operator to place the objects in suitable initial (grasping) states. Finding stable grasps that also promote the desired in-hand manipulation goal is an open problem. In this work, we propose a method for bridging this gap by leveraging the critic network of a reinforcement learning agent trained for in-hand manipulation to score and select initial grasps. Our experiments show that this method significantly increases the success rate of in-hand manipulation without requiring additional training. We also present an implementation of a full grasp manipulation pipeline on a real-world system, enabling autonomous grasping and reorientation even of unwieldy objects.