Object Manipulation with an Anthropomorphic Robotic Hand via Deep Reinforcement Learning with a Synergy Space of Natural Hand Poses
Open Access
Abstract
Anthropomorphic robotic hands are designed to attain dexterous movements and flexibility much like human hands. Achieving human-like object manipulation remains a challenge especially due to the control complexity of the anthropomorphic robotic hand with a high degree of freedom. In this work, we propose a deep reinforcement learning (DRL) to train a policy using a synergy space for generating natural grasping and relocation of variously shaped objects using an anthropomorphic robotic hand. A synergy space is created using a continuous normalizing flow network with point clouds of haptic areas, representing natural hand poses obtained from human grasping demonstrations. The DRL policy accesses the synergistic representation and derives natural hand poses through a deep regressor for object grasping and relocation tasks. Our proposed synergy-based DRL achieves an average success rate of 88.38% for the object manipulation tasks, while the standard DRL without synergy space only achieves 50.66%. Qualitative results show the proposed synergy-based DRL policy produces human-like finger placements over the surface of each object including apple, banana, flashlight, camera, lightbulb, and hammer.Keywords
Funding Information
- National Research Foundation of Korea (NRF-2019R1A2C1003713)
This publication has 30 references indexed in Scilit:
- Synergy-Based Control of Underactuated Anthropomorphic HandsIEEE Transactions on Industrial Informatics, 2018
- Grasp and dexterous manipulation of multi-fingered robotic hands: a review from a control view pointAdvanced Robotics, 2017
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
- Hand synergies: Integration of robotics and neuroscience for understanding the control of biological and artificial handsPhysics of Life Reviews, 2016
- A novel type of compliant and underactuated robotic hand for dexterous graspingThe International Journal of Robotics Research, 2015
- Adaptive synergies for the design and control of the Pisa/IIT SoftHandThe International Journal of Robotics Research, 2014
- Modelling natural and artificial hands with synergiesPhilosophical Transactions of the Royal Society B: Biological Sciences, 2011
- A Probabilistic Framework for Learning Kinematic Models of Articulated ObjectsJournal of Artificial Intelligence Research, 2011
- Shadow delivers first handIndustrial Robot: the international journal of robotics research and application, 2005
- Postural Hand Synergies for Tool UseThe Journal of Neuroscience, 1998