by Dhimiter Pikuli, Jordan Cosio, Xavier Alameda-Pineda, Pierre-Brice Wieber, Thierry Fraichard
Robotics: Science and Systems (RSS) Workshop on Unsolved Problems in Social Robot Navigation
[ paper ]
Navigation is one of the essential tasks in order for robots to be deployed in environments shared with humans. The problem becomes increasingly complex when taking in consideration that the robot’s behaviour should be suitable to humans. This is referred to as social navigation and it is a cognitive task that us humans pay little attention to as it comes naturally. Since crafting a model of the environment dynamics that faithfully characterises how humans navigate seems an impossible task, we look on the side of learning-based approaches and especially reinforcement learning. In this paper we are interested in drawing conclusions on the vast number of design choices when training a navigation agent using reinforcement learning. To make this educated decisions, we offer a short survey on recent papers addressing the social navigation problem using learning-based algorithms. Additionally, we take note of what worked best in our testing.
