Related Experiment Video
Updated: Dec 4, 2025
11:18
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
10.6K
A hybrid and scalable brain-inspired robotic platform.
Zhe Zou1, Rong Zhao1, Yujie Wu1
1Center for Brain-Inspired Computing Research (CBICR), Beijing Innovation Center for Future Chip, Optical Memory National Engineering Research Center, and Department of Precision Instrument, Tsinghua University, Beijing, 100084, China.
Scientific Reports
|October 24, 2020
Summary
This study introduces a brain-inspired robotic platform on an unmanned bicycle, enhancing robot intelligence. The scalable system efficiently handles diverse, real-time tasks in dynamic environments, mimicking human adaptability.
Area of Science:
- Robotics
- Artificial Intelligence
- Neuroscience
Background:
- Intelligent robots struggle with multi-tasking in dynamic environments.
- Scalability and adaptability are crucial for advanced robotic capabilities.
- Current robots lack human-like efficiency in complex, variable scenarios.
Purpose of the Study:
- To develop a brain-inspired robotic platform for enhanced intelligence.
- To achieve scalability and adaptability in robotic systems.
- To enable efficient multi-tasking in dynamic environments.
Main Methods:
- Implemented a brain-inspired platform using an unmanned bicycle.
- Utilized a trainable and scalable neural state machine for hybrid network cooperation.
- Developed an embedded system with a cross-paradigm neuromorphic chip for diverse neural networks.
Main Results:
- The platform demonstrated scalability in network scale, quantity, and diversity.
- Achieved concurrent real-time task execution in various real-world scenarios.
- Enabled flexible cooperation of hybrid networks using rich coding schemes.
Conclusions:
- The brain-inspired robotic platform offers a new pathway to enhance robot intelligence.
- The system's scalability and adaptability are key to handling complex, dynamic environments.
- Neuromorphic chip integration facilitates diverse neural network implementations for improved robotic performance.
