Abstract
We present a novel human-aware navigation approach, where the robot learns to mimic humans to navigate safely in crowds. The presented model referred to as DeepMoTIon, is trained with pedestrian surveillance data to predict human velocity. The robot processes LiDAR scans via the trained network to navigate to the target location. We conduct extensive experiments to assess the different components of our network and prove the necessity of each to imitate humans. Our experiments show that DeepMoTIon outperforms state-of-the-art in terms of human imitation and reaches the target on 100% of the test cases without breaching humans’ safe distance.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1803.03719