AMZ Driverless: The full autonomous racing system

Abstract

This paper presents the algorithms and system architecture of an autonomous racecar. The introduced vehicle is powered by a software stack designed for robustness, reliability, and extensibility. To autonomously race around a previously unknown track, the proposed solution combines state of the art techniques from different fields of robotics. Specifically, perception, estimation, and control are incorporated into one high‐performance autonomous racecar. This complex robotic system, developed by AMZ Driverless and ETH Zürich, finished first overall at each competition we attended: Formula Student Germany 2017, Formula Student Italy 2018 and Formula Student Germany 2018. We discuss the findings and learnings from these competitions and present an experimental evaluation of each module of our solution.

Performance Assessment of an Electric Power Steering System for Driverless Formula Student Vehicles

“…The academic activities for developing a driverless single-seated race car provide a platform to develop and validate new technologies under challenging conditions. Self-driving racecars represent a unique opportunity to design and test software required in autonomous transport, such as redundant perception, failure detection and control in challenging conditions [22].…”

“…The required rack force for the considered application is F rack = 1000 N. It is due to the required torque needed to move the steering rack at standstill, as a worst-case scenario [22]. Then, the required ball screw torque T BS = 0.397 Nm and the motor speed n = 1350 rpm and power P mot = 57 W are computed.…”

Lateral-Acceleration-Based Vehicle-Models-Blending for Automated Driving Controllers

“…This way, some authors have integrated both vehicle models in parallel to estimate more accurately relevant vehicle dynamics behavior, such as the side-slip angle [25] or the vehicle's position [26,27]. As the previous technique requires computing both models in parallel and increasing the computational effort, in recent years, the so-called model-blending approach has been proposed by some authors [28,29]. In this latter method, a model-switching strategy allows for selecting the most appropriate model depending on the driving scenario, allowing for increasing the validity range of the MPC-based vehicle control approach.…”

“…This criterion has to be defined using a variable that allows for optimizing the operative range of each model so that the model-blending effectively improves trajectory tracking. In [28,29], the longitudinal speed is used as the switching condition, selecting the kinematic model to compute MPC predictions when the vehicle moves at low speed while using the dynamic model when moving at high-speed. However, as model validity is limited by the tire model saturation, it seems more appropriate to use another variable to perform the switching which is directly related to the tires' forces, such as lateral acceleration.…”

“…However, as model validity is limited by the tire model saturation, it seems more appropriate to use another variable to perform the switching which is directly related to the tires' forces, such as lateral acceleration. Regarding the switching mode, previous works have presented two different methods-firstly, a sudden switch strategy that instantly changes between kinematic and dynamic models [28]; secondly, a progressive switching strategy that performs this change more smoothly using a linear approach [29]. Nevertheless, there is not a recommended procedure to blend models, besides the trial-and-error method.…”