Composing Dextrous Grasping and In-hand Manipulation via Scoring with a Reinforcement Learning Critic

Abstract

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.

References in corpus (8)

• Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes
• Learning Purely Tactile In-Hand Manipulation with a Torque-Controlled Hand
• Dextrous Tactile In-Hand Manipulation Using a Modular Reinforcement Learning Architecture
• Speeding Up Optimization-based Motion Planning through Deep Learning
• Estimator-Coupled Reinforcement Learning for Robust Purely Tactile In-Hand Manipulation
• Self-Contained Calibration of an Elastic Humanoid Upper Body Using Only a Head-Mounted RGB Camera
• Combining Shape Completion and Grasp Prediction for Fast and Versatile Grasping with a Multi-Fingered Hand
• Self-Contained and Automatic Calibration of a Multi-Fingered Hand Using Only Pairwise Contact Measurements