Approach to Define the Reliability of Safety-Related Machine Learning Based Functions in Highly Automated Driving

Current standards cannot cover the safety requirements of machine learning based functions used in highly automated driving. Because of the opacity of neural networks, some self-driving functions cannot be developed following the V-model. These functions require the expansion of the standards. This paper focuses on this gap and defines functional reliability for such functions to help the future standards control the quality of machine learning based functions. As an example, reliability functions for pedestrian detection are built. Since the quality criteria in computer vision do not consider safety, new approaches for expression and evaluation of this reliability are designed.

Critical Analysis of Prototype Autonomous Vehicle Crash Rates: Six Scientific Studies from 2015–2018

Will Automated Vehicles be Safer than Conventional Vehicles? One of the critically important questions that has emerged about advanced technologies in transportation is how to test the actual effects of these advanced systems on safety, particularly how to evaluate the safety of highly automated driving systems. Richard Young's Critical Analysis of Prototype Autonomous Vehicle Crash Rates does a deep dive into these questions by reviewing and then critically analyzing the first six scientific studies of AV crash rates.

Take-Over Time: A Cross-Cultural Study of Take-Over Responses in Highly Automated Driving

The article presents a cross-cultural study of take-over performance in highly automated driving. As take-over performance is an important measure of safe driving, potential cultural differences could have important implications for the future development of automated vehicles. The study was conducted in two culturally different locations, Seattle, WA (n = 20) and Ljubljana, Slovenia (n = 18), using a driving simulator. While driving, participants voluntarily engaged in secondary tasks. The take-over request (TOR) was triggered at a specific time during the drive, and take-over time and type of response (none, brake, steer) were measured for each participant. Results show significant differences in take-over performance between the two locations. In Seattle 30% of participants in Seattle did not respond to TOR; the remaining 70% responded by braking only, compared to Slovenian participants who all responded by either braking or steering. Participants from Seattle responded significantly more slowly to TOR (M = +1285 ms) than Slovenian participants. Secondary task engagement at TOR also had an effect, with distracted US participants’ response taking significantly longer (M = +1596 ms) than Slovenian participants. Reported differences in take-over performance may indicate cultural differences in driving behavior and trust in automated driving.

Research on Pressure Control Algorithm of Regenerative Braking System for Highly Automated Driving Vehicles

Conclusive evidence has demonstrated the critical importance of highly automated driving systems and regenerative braking systems in improving driving safety and economy. However, the traditional regenerative braking system cannot be applied to highly automated driving vehicles. Therefore, this paper proposes a fully decoupled regenerative braking system for highly automated driving vehicles, which has two working modes: conventional braking and redundant braking. Aimed at the above two working modes, this paper respectively proposes the pressure control algorithm, based on P-V characteristics, and the pressure control algorithm, based on the overflow characteristics of the solenoid valve. AMESim is utilized as the simulation platform, and then is co-simulated with MATLAB/Simulink, which is embedded with the control algorithm. The simulation results show the feasibility and effectiveness of the regenerative braking system and the pressure control algorithm.

How Do Non-driving-related Tasks Affect Engagement Under Highly Automated Driving Situations? A Literature Review

Driving automation has become a trending topic over the past decade, as recent technical and technological improvements have created hope for a possible short-term release of partially automated vehicles. Several research teams have been exploring driver performance during control transitions performed under highly automated driving (i.e., while resuming manual driving, when facing a critical situation for instance). In this paper, we present a state of the art of studies dealing with control transitions as well as the concept of non-driving-related task (NDRT) engagement. More specifically, we aim to provide a global view on how task engagement is investigated in the literature. Two main utilisations of task engagement emerged from our literature review: its manipulation as independent variable to vary the driver’s engagement state before a control transition, and its measurement as dependent variable to compare its variation to driving behaviour variables during a control transition. Furthermore, we propose a new perspective on control transition, which was so far studied through a techno-centric approach; research works were indeed designed in function of the system state. Our article suggests a more cognitive-centred view by taking in account the evolution of engagement mechanisms along control transition stages. Finally, we provide a categorisation of engagement mechanisms’ variables involved during these different stages, with a view to facilitate future investigations on the driver’s engagement state during this crucial phase of highly automated driving.