果冻传媒

For his PhD research Chris van der Ploeg developed effective methods for detecting, isolating, and estimating faults in automated vehicle steering systems, crucial for vehicle safety. These methods, validated through simulations and experiments, enable vehicles to respond to faults effectively. Additionally, Van der Ploeg introduced a methodology for vehicles to plan routes by assessing risks in their immediate environment, considering both static and dynamic elements like other vehicles, pedestrians, and hidden road users. This approach helps vehicles minimize risks by anticipating future scenarios and adjusting their routes accordingly. By integrating self-awareness of system errors with enhanced situational awareness in route planning, this research takes an important step toward higher levels of automation. This integration is crucial for developing automated vehicles that can safely navigate complex environments and reduce traffic accidents.

In the pursuit of zero traffic casualties and higher levels of vehicle automation, new challenges emerge as more tasks are automated. While taking over human responsibilities, the safety and performance of automated vehicles are examined closely. Recent media coverage suggests that automated vehicles are still susceptible to conditions traditionally managed by human drivers. These conditions can affect different parts of the vehicle, such as hardware components, software running on the vehicle, or signals transmitted to or received from the vehicle. They can also arise from the vehicle's behavior or its interpretation of the environment. This necessitates the creation of approaches for making the vehicle self-aware to understand its own condition and operation within a given setting. This includes understanding its performance, operational boundaries, and the consequences of its actions. Furthermore, the vehicle should be situationally aware, possessing the capability to sense, comprehend, and predict elements and occurrences in its immediate environment and to act on those insights.

Improve self-awareness

First, Van der Ploeg presents methods to enhance the self-awareness of an automated vehicle by focusing on the diagnosis of faults in the steering system. The steering system plays a vital role in safety; a fault in this system can have catastrophic consequences if not detected and addressed appropriately. The methods proposed here show effectiveness in detecting, isolating, and estimating relevant faults under varying (and potentially uncertain) circumstances of the vehicle. These methods have been proven both in simulation and in an experimental setting, allowing the vehicle to act appropriately given this knowledge.

Situationally aware

Secondly, his research provides a methodology for the vehicle to plan its future path while being situationally aware. In particular, it enables the vehicle to view its environment from a risk-based perspective, allowing it to plan a path towards a certain goal while minimizing its own risk. This is achieved by incorporating information about the road, the observed actors (vehicles, pedestrians, cyclists, etc.), and the presence of possible hidden road users that may appear shortly. The results show that the vehicle is capable of driving in complex circumstances while anticipating the presence of potential hidden road users.

Combining these results, a next step is taken towards higher levels of automation of vehicles, thereby increasing the potential for these vehicles to improve road safety and reduce traffic casualties.

The research line on the chapter on situational awareness has been widely covered in the news this year. The research preceding this chapter (also listed in the publications of Chris van der Ploeg) was included in TNO's annual report (see . As a result, it has been shared by 44 different media outlets and was even broadcast on television by EditieNL (https://www.rtl.nl/nieuws/editienl/artikel/5440714/zelfrijdende-auto-voorspelt-toekomst-tno) and OP1 (https://op1npo.nl/2024/03/18/peter-werkhoven-en-wouter-karssen-over-een-zelfrijdende-auto-die-de-toekomst-kan-voorspellen/).

Title of PhD thesis: Supervisors: Prof. Nathan van de Wouw (果冻传媒), Dr. P. Mohajerin Esfahani (TU Delft), and Emilia Silvas (果冻传媒).