Enabling Safe Autonomous Driving in Uncertain Environments
Doctoral thesis, 2022

Autonomous driving technologies have been developed in the past decades with the objective of increasing safety and efficiency. However, in order to enable such systems to be deployed on a global scale, the problems and concerns regarding safety must be addressed. The difficulty in providing safety guarantees for autonomous driving applications comes from the fact that the self-driving vehicle needs to be able to handle a diverse set of environments and traffic situations. More specifically, it must be able to interact with other road users, whose intentions cannot be perfectly known.

This thesis proposes a Model Predictive Control (MPC) approach to ensure safe autonomous driving in uncertain environments. While MPC has been widely used in motion planning and control for autonomous driving applications, the standard literature cannot be directly applied to ensure safety (recursive feasibility) in the presence of other road users, i.e., pedestrians, cyclists, and other vehicles. To that end, this thesis shows how recursive feasibility can still be obtained through a slight modification of the MPC controller design.

The results of this thesis build upon the assumption that the behavior of the surrounding environment can be predicted to some extent, i.e., a future motion trajectory with some uncertainty bound can be propagated. Then, by postulating the existence of a safe set for the autonomous driving problem, and requiring that the motion prediction models have a consistent structure, safety guarantees can be derived for an MPC controller.

Finally, this thesis shows that the proposed MPC framework does not only hold in theory and simulations, but that it can also be deployed on a real vehicle test platform and operate in real-time, while still ensuring that the conditions needed for the derived safety guarantees hold.

robust constraint satisfaction

autonomous driving

uncertain environments

model predictive control

HB1
Opponent: Prof. Nathan van de Wouw, Dynamics and Control group, Eindhoven University of Technology, Netherlands

Author

Ivo Batkovic

Chalmers, Electrical Engineering, Systems and control

Real-Time Constrained Trajectory Planning and Vehicle Control for Proactive Autonomous Driving with Road Users

2019 18th European Control Conference, ECC 2019,; (2019)p. 256-262

Paper in proceeding

A Robust Scenario MPC Approach for Uncertain Multi-Modal Obstacles

IEEE Control Systems Letters,; Vol. 5(2021)p. 947-952

Journal article

Safe Trajectory Tracking in Uncertain Environments

IEEE Transactions on Automatic Control,; Vol. 68(2023)p. 4204-4217

Journal article

Model Predictive Control for Safe Autonomous Driving Applications

Lecture Notes in Intelligent Transportation and Infrastructure,; (2023)p. 255-282

Book chapter

Experimental Validation of Safe MPC for Autonomous Driving in Uncertain Environments

IEEE Transactions on Control Systems Technology,; Vol. In Press(2023)

Journal article

Self-driving vehicles are believed to hold the potential to significantly increase traffic safety by replacing human drivers with automated driving technologies. In particular, since traffic-related accidents account for over one million people being killed every year, it is envisioned that self-driving vehicles can and will play an important role in the saving of countless lives. In addition, while having the potential to save lives, the self-driving technology is also believed to be an enabler when it comes to making the transportation sector more efficient. However, for self-driving vehicles to be deployed on a global scale, the problems and concerns regarding safety must be addressed. A self-driving vehicle must, above all, be safe and have the capacity to interact with other traffic participants. This thesis considers an approach called Model Predictive Control (MPC) which enables a self-driving vehicle to plan its driving, while avoiding collisions with other road users.

The results of this thesis show that an MPC-based decision logic can be a suitable choice for controlling the actions of self-driving vehicles. The results also show, that by considering the behavior of the surrounding environment, the MPC-based framework can adapt to the different traffic situations, and plan future decisions in time which will always remain safe. Finally, the thesis shows through real vehicle experiments that the derived theory is not only applicable to simulations, but also in practice.

COPPLAR CampusShuttle cooperative perception & planning platform

VINNOVA (2015-04849), 2016-01-01 -- 2018-12-31.

Areas of Advance

Transport

Infrastructure

ReVeRe (Research Vehicle Resource)

Subject Categories

Electrical Engineering, Electronic Engineering, Information Engineering

Control Engineering

ISBN

978-91-7905-623-0

Doktorsavhandlingar vid Chalmers tekniska högskola. Ny serie: 5089

Publisher

Chalmers

HB1

Opponent: Prof. Nathan van de Wouw, Dynamics and Control group, Eindhoven University of Technology, Netherlands

More information

Latest update

11/9/2023