Related Experiment Video
Updated: Oct 18, 2025
11:06
Design and Fabrication of an Elastomeric Unit for Soft Modular Robots in Minimally Invasive Surgery
Published on: November 14, 2015
9.1K
Modular Robotic Limbs for Astronaut Activities Assistance.
Sikai Zhao1, Jie Zhao1, Dongbao Sui1
1State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin 150001, China.
Sensors (Basel, Switzerland)
|September 28, 2021
Summary
Astronaut robotic limbs (AstroLimbs) offer enhanced support for space walks and on-orbit tasks. This modular system uses reinforcement learning for intelligent, autonomous assistance in unstructured environments.
Area of Science:
- Robotics
- Aerospace Engineering
- Artificial Intelligence
Background:
- Extravehicular activities (EVA) require significant astronaut support for tasks outside the International Space Station (ISS).
- Current EVA support systems may lack the flexibility and autonomy needed for complex, unstructured environments.
- Single-astronaut operations increase the demand for advanced assistive technologies.
Purpose of the Study:
- To propose and develop a novel astronaut robotic limbs system (AstroLimbs) for enhanced EVA assistance.
- To enable autonomous motion planning for robotic limbs in unstructured space environments.
- To enhance astronaut capabilities during extravehicular activities.
Main Methods:
- Design and development of a modular and reconfigurable robotic limb system (AstroLimbs).
- Integration of reinforcement learning for autonomous motion planning and intelligent assistance.
- Simulation of the ISS structure scene for EVA to validate system effectiveness.
Main Results:
- Successful design and development of the AstroLimbs system with modular robotic limbs.
- Demonstrated autonomous motion planning capabilities using reinforcement learning.
- Validated system effectiveness in a simulated ISS environment for EVA.
Conclusions:
- The AstroLimbs system provides a viable solution for astronaut assistance during extravehicular activities.
- Reinforcement learning enables intelligent and autonomous operation of robotic limbs in complex space settings.
- The modular design offers reconfigurability and adaptability for diverse EVA tasks.
