Predictive Control for Autonomous Articulated Vehicles

Abstract

Autonomous driving is a highly topical research area, where signi cant positive impacts on safety and environment can be made, especially in the trucking industry. The vehicles in this industry often consist of a tractor unit combined with a trailer. This project focuses on navigating a model semi-trailer truck through an urbanlike environment. A number of challenges arise from these settings, such as path planning and control through sharp turns and crossings, combined with obstacle avoidance. This needs to be done with high precision, considering that the whole articulated vehicle needs to stay within the bounds of the road. Since the vehicle will need to take critical decisions quickly, the performance and reliability of the control system is also important. Working towards a real world solution, this project o ers a complete prototype implementation in a scaled testbed environment for articulated vehicles. To achieve this, we have mathematically modeled the vehicle, created a path planning algorithm that takes the trailer into account when calculating a suitable path, and developed a controller that makes the vehicle follow this path. These components have been integrated on a single-board computer (Raspberry Pi 3) embedded on the vehicle. The evaluation of the system shows satisfying results, where the prototype is able to do on-the- y path planning while staying within the allowed areas of the test track. The system is also extensible and modi able, and can be extended in future student projects.