PhD thesis on "Cooperative driving between a human driver and an autonomous vehicle" (M/F)

Job Description

Thesis Subject

This thesis aims to study a cooperative driving system between a human driver and an autonomous system (Autonomous Driving - AD), following the Human-Autonomy Teaming (HAT) paradigm [1], for the longitudinal and lateral control of a vehicle. Assuming the driver remains active and in control of the situation, the thesis objectives are organized into two main parts.
The first part involves developing a cooperative system at the operational level between the autonomous driving system and the human driver, who interact mutually via a non-mechanical haptic feedback interface, such as the Joysteer(1), for guidance tasks. The study focuses on intermediate driving delegation (SAE(2) Level 2) with an AD system controller operating around a nominal mode defined by a reference path and speed profile. A primary objective of this cooperation is to enable the AD system to understand the driver's intentions in order to adjust the vehicle's setpoints or commands. The AD system can also control the stiffness of the interface (adaptive haptic feedback) based on the situation and various system variables. Scenarios such as lane-keeping and stop-and-go will be considered.
The second part of the work aims to extend the study to more complex driving situations in dynamic environments with other road users (pedestrians, cyclists, vehicles, etc.). In this case, the study will incorporate the AD system's trajectory planning module, which uses a perception system coupled with map-based localization [3]. Given the uncertainties associated with such an AD system, the human driver will have an additional role in aiding decision-making. Since cooperation in this case is more complex—extending to the decisional level—the objective will be to further exploit the haptic interaction interface as a means of communication, while retaining the operational control characteristics. Scenarios such as obstacle avoidance, intersection crossing, or roundabout navigation will be considered.
In this work, we also aim to explore the use of machine learning approaches [1][2] to personalize the driving system according to individual driver preferences. Finally, another expected outcome of this thesis is the formalization of global AD system architectures that explicitly integrate human interaction.
It is worth noting that the thesis will rely on an experimental approach, with implementations and validations planned on the Virtuoz platform. This platform is currently under development at Heudiasyc as part of the EquipEx+ TIRREX project and will be equipped with a "Steer-by-Wire" interface for human interaction.


References:
[1] J. Lee et al., « Teaming with Your Car: Redefining the Driver–Automation Relationship in Highly Automated Vehicles”, Journal of Cognitive Engineering and Decision Making, Volume 17, Issue 1, 2022.
[2] A. Muzahid et al. “Survey on Human-Vehicle Interactions and AI Collaboration for Optimal Decision-Making in Automated Driving”, arXiv 2024.
[3] A. Hamdan, R. Talj and V. Cherfaoui, "A Fuzzy Logic Shared Steering Control Approach For Semi-Autonomous Vehicle," 2021 20th International Conference on Advanced Robotics (ICAR), Ljubljana, Slovenia, 2021, pp. 83-90, doi: 10.1109/ICAR53236.2021.9659434

(1) https://www.youtube.com/shorts/SfUwC3nq4Os
(2) https://www.sae.org/news/blog/sae-levels-driving-automation-clarity-refinements

Your Work Environment

This thesis is part of the CAP Twinning project, which is itself a component of the PostGenAI@Paris project (AI cluster) led by Sorbonne Université. It will benefit from the momentum of this project and the ongoing collaborations with academic partners ISIR and IRCAM, as well as the industrial partner Renault/Ampère. The thesis is also closely aligned with the objectives of the EquipEx+ TIRREX project, which focuses on the development of the Virtuoz platform designed for cooperative driving between a human driver and an AD (Autonomous Driving) system.

Compensation and benefits

Compensation

2300 € gross monthly

Annual leave and RTT

44 jours

Remote Working practice and compensation

Pratique et indemnisation du TT

Transport

Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€

About the offer

About the CNRS

The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.

CNRS

The research professions