Nematode worm inspired robotic model for pothole detection
John Lones, Anthony Cohn and Netta Cohen
Animals navigate complex and varied environments, but often use only limited sensory information. Here we present a simulated robot system using a sensory model and navigation strategy inspired by the nematode worm C. elegans. In particular we focused on the application of finding road damage such as potholes. Over two sets of experiments we demonstrated how our approach leads to a highly robust and efficient search algorithm that is achieved with limited sensory capabilities and no prior knowledge of the environments.
This paper was presented as part of the Proceedings of NIPS 2017 Workshop on Worm’s Neural Information Processing (9 December 2017, Long Beach, California).