However, most autonomous navigation systems end up designed to avoid obstacles, even when an insect could naturally climb over them. This can result in longer routes and reduced exploration efficiency.
To that end, a new navigation system for cyborg insects that combine the cockroach’s natural climbing ability with AI-based real-time terrain recognition is now in development, according to an international research team from the University of Osaka and Universitas Diponegoro. This could enable the insects to traverse obstacles faster and more efficiently than with conventional navigation methods.
The team, therefore, developed a reactive-climbing strategy combining goal-seeking, obstacle avoidance, wall-following, and innate climbing behavior. However, because the controller could not identify terrain, it issued steering commands during climbing, causing hesitation and inefficient movement.
Onboard Sensor Data
To address this problem, the researchers incorporated a multilayer-perceptron-based AI module that used onboard sensor data to recognize flat surfaces, ascents, descents, and holes in real time.
The classifier achieved 92 percent accuracy in offline evaluation, enabling the controller to adjust stimulation according to the terrain, reduced unnecessary steering, and support sustained forward movement across challenging surfaces.
“The main challenge was to develop a system capable of recognizing terrain in real time without compromising the insect’s natural locomotor abilities,” said Professor Keisuke Morishima of the University of Osaka. “In this study, we propose ‘biohybrid physical AI’ to enable efficient autonomous navigation. We hope these findings will inspire the development of robotic systems capable of operating in complex environments, including search-and-rescue sites.”
Cyborg insect learn to get around obstacles using the proposed navigation system.Source: Mochammad Ariyanto et al.
This adaptive-terrain navigation system enabled by a wireless module attached to a cockroach was able to guide cyborg insects over obstacles toward a target destination. By coordinating adaptive-terrain recognition and navigation guidance that consider the insect’s reactive-climbing behavior, this strategy can enable more capable and efficient cyborg insect navigation in challenging terrain.
Click here to view the paper.