Autonomous Bus Driving: A Novel Motion-Planning Approach

In this article, we present a motion-planning framework that leverages expert bus driver behavior, increasing the safety and maneuverability of autonomous buses. Autonomous vehicles will increase the safety, quality, and efficiency of transportation systems. However, to deploy this technology in urban public transport, many challenges related to self-driving buses still need to be addressed. Unlike passenger cars, buses have long and wide dimensions and a distinct chassis configuration, which significantly challenges their maneuverability. To deal with their special dimensions, we introduce a novel optimization objective that centers their whole body as they travel along a road. Furthermore, we present new environment classification schemes that enable self-driving buses to take advantage of their distinct chassis configuration, namely, the elevated overhangs, to increase maneuverability. Finally, we offer a novel collision checking method that explicitly considers a bus's front wheels and how they can protrude from beneath the chassis when maneuvering near stops. We demonstrate the benefits of our framework through experiments using an autonomous bus in real road scenarios.