SNOW - Self-driving Navigation Optimized for Winter

点击翻译按钮获取中文摘要

Self-driving cars, or autonomous vehicles in general, are taking a larger place in the public sphere and are expected on our roads in the near future. Although great technological advances have occurred during the last decade, autonomous driving during winter still raises reliability concerns. Laval University has the expertise to automatically build 3D maps of the environment while moving through it with robots and aims at using this knowledge to investigate solutions for challenging conditions related to Canadian weather. The main goal of this proposal is to extend the current technology used for autonomous driving toward unstructured and dynamic environments (e.g., a snow-covered forest). Maps built by a UGV will be able to adapt to environmental changes caused by snow and winds, while allowing a robust localization of the vehicle in real-time. This map will serve as the foundation for novel path planning algorithms handling deformable obstacles and environments (e.g., deep snow under a vehicle). The project will be carried out in partnership with General Dynamics Land Systems - Canada (GDLS-C), a leading Canadian defence company. The outcomes of this project will allow Laval University to strengthen its current 3D mapping algorithms and make scientific advances in autonomous navigation in general. The project will also open new application opportunities for GDLS-C, which will be able to absorb new knowledge and lessons learned from the experimental work to prepare for future customer requests