Axis-space framework for cable-driven soft continuum robot control via reinforcement learning
Problem
Deep reinforcement learning control of cable-driven soft continuum robots (used in minimally invasive surgery) suffers from high sample complexity and a simulation-to-real-world gap.
Why it matters
These robots reduce lesions, pain and infection risk in minimally invasive surgery, per the abstract.
What the AI did
A deep reinforcement learning Axis-Space framework redesigns state and action spaces to cut sample complexity and training steps, controlling a robot with four tendons per section.
Results
Over 11-fold convergence speed increase vs DDQN controller; positioning error reduced (value truncated in abstract)
Impact
Demonstrated faster, more accurate DRL control of a cable-driven soft continuum robot.
Record
| Venue | Communications Engineering |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Dehao Wei, Jiaqi Zhou, Yinheng Zhu, Jiabin Ma, Shaohua Ma |
| Citations | 21 (OpenAlex, at import time) |
| References | 37 |
| Model or method | Deep reinforcement learning, Axis-Space framework (vs DDQN baseline) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s44172-023-00110-2 |
| Open access | gold |
| Keywords | reinforcement learning, cable-driven robot, continuum robot, minimally invasive surgery, control |
Importance rating
real but narrower advance
Abstract states these robots reduce lesions, pain and infection risk in minimally invasive surgery, but no patient scale is given; advance is a faster control method for one robot class.
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
|