Related Experiment Video
Updated: Jun 27, 2026
07:23
Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches
Published on: August 4, 2014
23.0K
Bio-Inspired Neural Network for Real-Time Evasion of Multi-Robot Systems in Dynamic Environments.
1School of Engineering, University of Guelph, 50 Stone Road East, Guelph, ON N1G2W1, Canada.
Biomimetics (Basel, Switzerland)
|March 27, 2024
Summary
This study introduces a bio-inspired neural network (BINN) for pursuit-evasion games. The BINN effectively generates real-time evasive trajectories in complex, dynamic environments with changing obstacles.
Area of Science:
- Robotics and Artificial Intelligence
- Computational Neuroscience
Background:
- Traditional pursuit-evasion models struggle with sudden environmental changes.
- Neurodynamics offers an alternative perspective for complex dynamic systems.
Purpose of the Study:
- To propose a bio-inspired neural network (BINN) for approximating pursuit-evasion games.
- To enable real-time evasive trajectory generation in dynamic environments.
Main Methods:
- A topologically organized bio-inspired neural network (BINN) with local connections.
- Utilizing the neurodynamic shunting model to simulate neural activity.
- Approximating the game from a neurodynamic perspective, not as a differential game.
Main Results:
- The BINN effectively handles moving and sudden-change obstacles.
- Demonstrated effectiveness and efficiency in complex and dynamic environments through simulations and experiments.
Conclusions:
- The proposed BINN provides a robust solution for pursuit-evasion in challenging environments.
- This neurodynamic approach offers a novel method for real-time trajectory generation.
