Topometric Imitation Learning for Route Following Under Appearance Change

Shaojun Cai, Yingjia Wan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 1010-1011

Traditional navigation models in autonomous driving rely heavily on metric maps, which severely limits their application in large scale environments. In this paper, we introduce a two-level navigation architecture that contains a topological-metric memory structure and a deep image-based controller. The hybrid memory extracts visual features at each location point with a deep convolutional neural network, and stores information about local driving commands at each location point based on metric information estimated from ego-motion information. The topological-metric memory is seamlessly integrated with a conditional imitation learning controller through the navigational commands that drive the vehicle between different vertices without collision. We test the whole system in teach-and-repeat experiments in an urban driving simulator. Results show that after being trained in a separate environment, the system could quickly adapt to novel environments with a single teach trial and follow route successively under various illumination and weather conditions.