Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes

Abstract

In-hand object reorientation is necessary for performing many dexterous manipulation tasks, such as tool use in less structured environments that remain beyond the reach of current robots. Prior works built reorientation systems assuming one or many of the following: reorienting only specific objects with simple shapes, limited range of reorientation, slow or quasistatic manipulation, simulation-only results, the need for specialized and costly sensor suites, and other constraints which make the system infeasible for real-world deployment. We present a general object reorientation controller that does not make these assumptions. It uses readings from a single commodity depth camera to dynamically reorient complex and new object shapes by any rotation in real-time, with the median reorientation time being close to seven seconds. The controller is trained using reinforcement learning in simulation and evaluated in the real world on new object shapes not used for training, including the most challenging scenario of reorienting objects held in the air by a downward-facing hand that must counteract gravity during reorientation. Our hardware platform only uses open-source components that cost less than five thousand dollars. Although we demonstrate the ability to overcome assumptions in prior work, there is ample scope for improving absolute performance. For instance, the challenging duck-shaped object not used for training was dropped in 56 percent of the trials. When it was not dropped, our controller reoriented the object within 0.4 radians (23 degrees) 75 percent of the time. Videos are available at: https://taochenshh.github.io/projects/visual-dexterity.

Published in Science Robotics: https://www.science.org/doi/10.1126/scirobotics.adc9244

References in corpus (5)

• Learning Quadrupedal Locomotion over Challenging Terrain
• Surprisingly Robust In-Hand Manipulation: An Empirical Study
• An End-to-End Differentiable Framework for Contact-Aware Robot Design
• Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger
• Learning Purely Tactile In-Hand Manipulation with a Torque-Controlled Hand

Cited by in corpus (10)

• Embedding high-resolution touch across robotic hands enables adaptive human-like grasping
• From Screens to Scenes: A Survey of Embodied AI in Healthcare
• A roadmap for AI in robotics
• DexTouch: Learning to Seek and Manipulate Objects with Tactile Dexterity
• Composing Dextrous Grasping and In-hand Manipulation via Scoring with a Reinforcement Learning Critic
• Surface-Based Manipulation with Modular Foldable Robots
• DexRepNet++: Learning Dexterous Robotic Manipulation with Geometric and Spatial Hand-Object Representations
• Approximating Global Contact-Implicit MPC via Sampling and Local Complementarity
• TEXterity -- Tactile Extrinsic deXterity: Simultaneous Tactile Estimation and Control for Extrinsic Dexterity
• Human-Exoskeleton Kinematic Calibration to Improve Hand Tracking for Dexterous Teleoperation