Reinforcement Learning Based User-Specific Shared Control Navigation in Crowds

摘要

Shared control is a mode where the user input is combined with a planned motion to achieve a common goal. In navigation, a shared control approach could provide a potential mobility solution for people who have a mobility impairment and find traditional powered wheelchairs unsuitable. While state-of-the-art work in shared control has demonstrated its capability in improving safety, human-machine interaction and reduce confusion, it is still challenging to use shared control in dynamic, crowded scenarios, in a way that is acceptable to users. Learning from recent advances in robot navigation, we present a reinforcement learning based framework, which allows navigation to be achieved in a user-specific shared controlled way. Our approach was trained and tested in a Unity3D based simulator. It achieved 33% fewer collisions, similar high user agreement (≤ 85%) and 27% less completion time when compared with our previous model-based method.