Robot designed for socially acceptable navigation

Abstract

Autonomous (self-driving) vehicles are increasingly being tested on highways and city streets. But there is also a need for robots that can navigate through environments like sidewalks, buildings, and hallways. In these situations, the robots must interact and cooperate with pedestrians in a socially acceptable manner. The "rules of the road" no longer apply -- there are no lanes or street signs, and pedestrians don't use turn signals when cutting through crowds. This thesis describes the hardware and software architecture of a robot that was developed for this application. This thesis also proposes a 2nd generation robot with tighter budget and size constraints. Finally, this thesis presents a novel collision avoidance method that extends the Reciprocal Velocity Obstacle (RVO) framework to consider the impact of planning decisions on future world states.