Object Manipulation with an Anthropomorphic Robotic Hand via Deep Reinforcement Learning with a Synergy Space of Natural Hand Poses
Problem
Anthropomorphic robotic hands with many degrees of freedom are hard to control for human-like grasping and relocation of variously shaped objects.
Why it matters
Dexterous robotic manipulation is a key barrier to useful robotic hands in industry and assistance.
What the AI did
A deep reinforcement learning policy trained in a synergy space built from human grasping demonstrations (continuous normalizing flow over point clouds) to generate natural hand poses for grasping and relocation tasks.
Results
Average success rate of 88.38% for object manipulation tasks; standard DRL baseline comparison truncated.
Impact
Peer-reviewed simulation-based study showing the synergy approach beats standard DRL, but no real-world deployment evidence.
Record
| Venue | Sensors |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Patricio Rivera, Edwin Valarezo Añazco, Tae-Seong Kim |
| Citations | 14 (OpenAlex, at import time) |
| References | 45 |
| Model or method | DRL policy with continuous normalizing flow synergy space and deep regressor |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/s21165301 |
| Open access | gold |
| Keywords | robotic hand, deep reinforcement learning, grasping, synergy space, anthropomorphic, manipulation |
Importance rating
real but narrower advance
Dexterous manipulation is a key barrier to useful robotic hands in industry and assistance; a significant robotics capability advance but simulation-only with no stated deployment scale.
More in Robotics & Autonomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Autonomous robotic laparoscopic surgery for intestinal anastomosis | 2022 | 384 |
7
|
| 2 | Solving Rubik's Cube with a Robot Hand | 2019 | 569 |
6
|
| 3 | PaLM-E: An Embodied Multimodal Language Model | 2023 | 346 |
6
|
| 4 | Assistive Navigation Using Deep Reinforcement Learning Guiding Robot With UWB/Voice Beacons and Semantic Feedbacks for Blind and Visually Impaired People | 2021 | 48 |
6
|
| 5 | Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges | 2022 | 154 |
6
|