Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger

Abstract

We present a system for learning a challenging dexterous manipulation task involving moving a cube to an arbitrary 6-DoF pose with only 3-fingers trained with NVIDIA's IsaacGym simulator. We show empirical benefits, both in simulation and sim-to-real transfer, of using keypoints as opposed to position+quaternion representations for the object pose in 6-DoF for policy observations and in reward calculation to train a model-free reinforcement learning agent. By utilizing domain randomization strategies along with the keypoint representation of the pose of the manipulated object, we achieve a high success rate of 83% on a remote TriFinger system maintained by the organizers of the Real Robot Challenge. With the aim of assisting further research in learning in-hand manipulation, we make the codebase of our system, along with trained checkpoints that come with billions of steps of experience available, at https://s2r2-ig.github.io

International Conference on Intelligent Robots and Systems (IROS 2022)

References in corpus (8)

• Learning agile and dynamic motor skills for legged robots
• Solving Rubik's Cube with a Robot Hand
• Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
• CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
• Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning
• Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation
• Circus ANYmal: A Quadruped Learning Dexterous Manipulation with Its Limbs
• Grasp and Motion Planning for Dexterous Manipulation for the Real Robot Challenge

Cited by in corpus (7)

• Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes
• Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
• Getting the Ball Rolling: Learning a Dexterous Policy for a Biomimetic Tendon-Driven Hand with Rolling Contact Joints
• Dexterous Robotic Manipulation using Deep Reinforcement Learning and Knowledge Transfer for Complex Sparse Reward-based Tasks
• Dynamic object goal pushing with mobile manipulators through model-free constrained reinforcement learning
• Sampling-Based Model Predictive Control for Dexterous Manipulation on a Biomimetic Tendon-Driven Hand
• Benchmarking Population-Based Reinforcement Learning across Robotic Tasks with GPU-Accelerated Simulation