Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation

arXiv:2308.14947v2 Announce Type: replace-cross
Abstract: In order for autonomous mobile robots to navigate in human spaces, they must abide by our social norms. Reinforcement learning (RL) has emerged as an effective method to train sequential decision-making policies that are able to respect these norms. However, a large portion of existing work in the field conducts both RL training and testing in simplistic environments. This limits the generalization potential of these models to unseen environments, and the meaningfulness of their reported …

abstract arxiv autonomous autonomous mobile robots cs.lg cs.ma cs.ro decision human making mobile navigation reinforcement reinforcement learning robot robot navigation robots social spaces train training type