2018/07/03 by Patrick Wenzel, Wenzel, Patrick, Qadeer Khan +5 · 5 citations
Computer Science · Engineering · Mathematics · Physics and Astronomy · #Artificial Intelligence (cs.AI) #Artificial intelligence #Autonomous Vehicle Technology and Safety #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Control (management) #Deep learning #FOS: Computer and information sciences #Generalization #Generative Adversarial Networks and Image Synthesis #Generative adversarial network #Ground truth #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Model Reduction and Neural Networks #Modular design #Robotics (cs.RO) #Semantic data model #Task (project management) #Train #cs.AI #cs.CV #cs.LG #cs.RO #stat.ML
paper · pdf · doi:10.48550/arxiv.1807.01001
published in arXiv (Cornell University), 253-269 (Cornell University) · 2nd Conference on Robot Learning (CoRL 2018), Zürich, Switzerland
openalex publication_date 2018/07/03 · arxiv created 2018/10/01 · arxiv updated 2018/10/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Even though end-to-end supervised learning has shown promising results for sensorimotor control of self-driving cars, its performance is greatly affected by the weather conditions under which it was trained, showing poor generalization to unseen conditions. In this paper, we show how knowledge can be transferred using semantic maps to new weather conditions without the need to obtain new ground truth data. To this end, we propose to divide the task of vehicle control into two independent modules: a control module which is only trained on one weather condition for which labeled steering data is available, and a perception module which is used as an interface between new weather conditions and the fixed control module. To generate the semantic data needed to train the perception module, we propose to use a generative adversarial network (GAN)-based model to retrieve the semantic information for the new conditions in an unsupervised manner. We introduce a master-servant architecture, where the master model (semantic labels available) trains the servant model (semantic labels not available). We show that our proposed method trained with ground truth data for a single weather condition is capable of achieving similar results on the task of steering angle prediction as an end-to-end model trained with ground truth data of 15 different weather conditions.