Funded by a $2.2 million grant from the European Union’s Horizon 2020 program, the ULTRACEPT project (Ultra-layered perception with brain-inspired information processing for vehicle collision avoidance) is developing a miniature, trustworthy collision detection sensor system that could drastically improve the safety of autonomous vehicles.
According to the team behind the project, current approaches to vehicle collision detection have a number of limitations: radar is too sensitive to metallic materials; GPS-based methods face difficulties in cities with high buildings; vehicle-to-vehicle communication cannot detect pedestrians or any unconnected objects, and normal vision sensors cannot cope with fog, rain or dim light conditions at night.
The ULTRACEPT team claims that by drawing on lessons from the insect world they will be able to develop a system with enhanced collision detection capabilities that could enable autonomous vehicles to better adapt to unexpected hazards and different conditions such as sudden weather changes or driving in and out of tunnels.
Project leader, University of Lincoln Computer Scientist Professor, Shigang Yue, said: “Autonomous vehicles….have demonstrated huge potential for shaping our future lifestyles …but to be functional on a daily basis there is one critical issue to solve; trustworthy collision detection. Collision detection and avoidance is so important for vehicles now and in the future, yet there is no acceptable product currently available on the market to specifically meet this need – that is exactly what we hope to develop.”
Yue, who has previously been involved in the developments of autonomous navigation systems for mobile robots based on the locust’s visual system, said that naturally evolved biological systems could provide the solution to this problem.
“Biology provides a rich source of inspiration for artificial visual systems for collision detection and avoidance. For example, locusts, with a compact visual brain, can fly for hundreds of miles in dense swarms free of collision; praying mantis can monitor tiny moving prey with the help of specialized visual neurons; and nocturnal insects successfully forage in the forest at night without collision.”
Locusts have a distinctive way of processing information through electrical and chemical signals, giving them an extremely fast and accurate warning system for impending collisions. The insect has incredibly powerful data processing systems built into its biology, which can in theory be recreated in robotics.
Yue added that these natural vision systems provide ideal models to develop an artificial system for collision detection and avoidance. The project, which includes researchers from Germany, China, Japan, Malaysia and South America, brings together experts in hardware and software systems and robotics, invertebrate vision, chip design and robotics.
"While some collision-avoidance features are pricey options on luxury cars, their performance is not always as good as it could be and they come at a high cost. This research offers us important insights into how we can develop a system for the car which could improve performance to such a level that we could take out the element of human error."
The team claims that as well as being used within autonomous vehicles, the ULTRACEPT vision system will be applicable to a number of other industries, including robotics, video game developments and healthcare.
Their findings are published in the International Journal of Advanced Mechatronic Systems.
Author unknown. 2018. “Swarming insects inspire collision avoidance technology for driverless cars”. Retrieved from https://www.theengineer.co.uk/insects-collision-avoidance-technology/.