2018/12/21 by Nima Mohajerin, Mohajerin, Nima, Mohsen Rohani +1 · 1 citation
Computer Science · Engineering · #Autonomous Vehicle Technology and Safety #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Robotic Path Planning Algorithms #Robotics (cs.RO) #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.1812.09395
openalex publication_date 2018/12/21 · openalex created_date 2022/08/01 · openalex updated_date 2026/07/28
We investigate the multi-step prediction of the drivable space, represented\nby Occupancy Grid Maps (OGMs), for autonomous vehicles. Our motivation is that\naccurate multi-step prediction of the drivable space can efficiently improve\npath planning and navigation resulting in safe, comfortable and optimum paths\nin autonomous driving. We train a variety of Recurrent Neural Network (RNN)\nbased architectures on the OGM sequences from the KITTI dataset. The results\ndemonstrate significant improvement of the prediction accuracy using our\nproposed difference learning method, incorporating motion related features,\nover the state of the art. We remove the egomotion from the OGM sequences by\ntransforming them into a common frame. Although in the transformed sequences\nthe KITTI dataset is heavily biased toward static objects, by learning the\ndifference between subsequent OGMs, our proposed method provides accurate\nprediction over both the static and moving objects.\n