Locust inspired neural network improves visual collision detection
A Bio-Plausible Visual Neural Network for Locust-Inspired Collision Perception
Neural and Evolutionary Computing
Summary
Seeing objects coming closer is important for avoiding crashes, and locusts do this very well with their eyes and brains. The authors created a computer model inspired by locust eyes and neurons to better detect approaching objects. Their model works more reliably in tricky visual situations and is more like the real biology of locusts. This could help machines better understand and react to looming threats.
What this means in practice
- •For autonomous vehicle engineers: Enhance collision avoidance systems in self-driving cars by using a biologically inspired neural model for more reliable object approach detection under complex conditions.
- •For robotics developers: Implement robust, efficient visual collision perception in mobile robots navigating dynamic environments, leveraging the locust-inspired neural network model.
Authors
Qinbing Fu, Jiani Li, Jiajun Huang, Jigen Peng
Abstract
Locust visual systems have long served as an important biological paradigm for studying looming perception and collision avoidance. Numerous computational models have successfully reproduced the selective responses of Lobula Giant Movement Detector (LGMD) neurons to approaching objects, thereby emulating the fundamental functionality of the biological system. However, existing models remain limited in biological plausibility and robustness when operating in complex and dynamic visual environments. To address these limitations, we propose a biologically plausible neural network for locust-inspired looming detection. The proposed framework incorporates a spatially isotropic sampling strategy that mimics the ommatidial organization of the locust compound eye, a population-voting mechanism inspired by population coding in biological neural systems, and leaky integrate-and-fire neuronal dynamics to replace conventional sigmoid-based membrane activation. Systematic experiments on synthetic stimuli, laboratory sequences, and real-world driving scenarios demonstrate that the proposed model improves robustness under challenging visual conditions while preserving computational efficiency and enhancing biological fidelity. These results highlight the potential of biologically grounded neural computation for robust and efficient collision perception.