Advanced Driver-Assistance Systems (ADAS) have been thriving and widely deployed in recent years. In general, these systems receive sensor data, compute driving decisions, and output control signals to the vehicles. To smooth out the uncertainties brought by sensor outputs, they usually leverage multi-sensor fusion (MSF) to fuse the sensor outputs and produce a more reliable understanding of the surroundings. However, MSF cannot completely eliminate the uncertainties since it lacks the knowledge about which sensor provides the most accurate data and how to optimally integrate the data provided by the sensors. As a result, critical consequences might happen unexpectedly. In this work, we observed that the popular MSF methods in an industry-grade ADAS can mislead the car control and result in serious safety hazards. We define the failures (e.g., car crashes) caused by the faulty MSF as fusion errors and develop a novel evolutionary-based domain-specific search framework, FusED, for the efficient detection of fusion errors. We further apply causality analysis to show that the found fusion errors are indeed caused by the MSF method. We evaluate our framework on two widely used MSF methods in two driving environments. Experimental results show that FusED identifies more than 150 fusion errors. Finally, we provide several suggestions to improve the MSF methods we study.
Advanced driver assistance systems have successfully reduced drivers' workloads and increased safety. On the other hand, the excessive use of such systems can impede the development of driving skills. However, there exist collaborative driver assistance systems, including shared and cooperative controls, which can promote effective collaboration between an assistance system and a human operator under appropriate system settings. Given an effective collaboration setup, we address the goal of simultaneously developing or maintaining driving skills while reducing workload. As there has been a pau…
University of Technology of Compiègne（贡比涅技术大学）；CNRS Heudiasyc UMR 7253（法国国家科学研究中心Heudiasyc UMR 7253实验室）
Taking into account the drivers' state is a major challenge for designing new advanced driver assistance systems. In this paper we present a driver assistance system strongly coupled to the user. DAARIA 1 stands for Driver Assistance by Augmented Reality for Intelligent Automobile. It is an augmented reality interface powered by several sensors. The detection has two goals: one is the position of obstacles and the quantification of the danger represented by them. The other is the driver's behavior. A suitable visualization metaphor allows the driver to perceive at any time the location of the …
Reinforcement learning (RL)-based driver assistance systems seek to improve fuel consumption via continual improvement of powertrain control actions considering experiential data from the field. However, the need to explore diverse experiences in order to learn optimal policies often limits the application of RL techniques in safety-critical systems like vehicle control. In this paper, an exponential control barrier function (ECBF) is derived and utilized to filter unsafe actions proposed by an RL-based driver assistance system. The RL agent freely explores and optimizes the performance object…
Vision-based driver assistance systems is one of the rapidly growing research areas of ITS, due to various factors such as the increased level of safety requirements in automotive, computational power in embedded systems, and desire to get closer to autonomous driving. It is a cross disciplinary area encompassing specialised fields like computer vision, machine learning, robotic navigation, embedded systems, automotive electronics and safety critical software. In this paper, we survey the list of vision based advanced driver assistance systems with a consistent terminology and propose a taxono…
Worcester Polytechnic Institute（伍斯特理工学院）；Toyota Motor North America（丰田汽车北美公司）
This study presents a novel approach for modeling and simulating human-vehicle interactions in order to examine the effects of automated driving systems (ADS) on driving performance and driver control workload. Existing driver-ADS interaction studies have relied on simulated or real-world human driver experiments that are limited in providing objective evaluation of the dynamic interactions and control workloads on the driver. Our approach leverages an integrated human model-based active driving system (HuMADS) to simulate the dynamic interaction between the driver model and the haptic-based A…
Haptic shared control is expected to achieve a smooth collaboration between humans and automated systems, because haptics facilitate mutual communication. A methodology for sharing a given task is important to achieve effective shared control. Therefore, the appropriate cooperative relationship between a human operator and automated system should be considered. This paper proposes a methodology to evaluate the cooperative status between the operator and the automated system in the haptic shared control of a steering operation using a pseudo-power pair of torque from each agent and the vehicle …
University of Oxford（牛津大学）；FiveAI（FiveAI公司）；University of Colorado Boulder（科罗拉多大学博尔德分校）
Research into safety in autonomous and semi-autonomous vehicles has, so far, largely been focused on testing and validation through simulation. Due to the fact that failure of these autonomous systems is potentially life-endangering, formal methods arise as a complementary approach. This paper studies the application of formal methods to the verification of a human driver model built using the cognitive architecture ACT-R, and to the design of correct-by-construction Advanced Driver Assistance Systems (ADAS). The novelty lies in the integration of ACT-R in the formal analysis and an abstractio…
This paper presents the experimental comparison of fourteen stereo matching algorithms in variant illumination conditions. Different adaptations of global and local stereo matching techniques are chosen for evaluation The variant strength and weakness of the chosen correspondence algorithms are explored by employing the methodology of the prediction error strategy. The algorithms are gauged on the basis of their performance on real world data set taken in various indoor lighting conditions and at different times of the day
Human-computer interaction (HCI) is crucial for the safety of lives as autonomous vehicles (AVs) become commonplace. Yet, little effort has been put toward ensuring that AVs understand humans on the road. In this paper, we present GLADAS, a simulator-based research platform designed to teach AVs to understand pedestrian hand gestures. GLADAS supports the training, testing, and validation of deep learning-based self-driving car gesture recognition systems. We focus on gestures as they are a primordial (i.e, natural and common) way to interact with cars. To the best of our knowledge, GLADAS is t…
Pohang University of Science and Technology（浦项科技大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Samsung research（三星研究院）
This paper addresses a data-driven framework, modeling expert driving skills for performance-based haptic assistance using neural networks (NNs). We have built a haptic driving training simulator to collect expert driving data and to provide proper haptic feedback. We establish an expert driving skill model by training NNs with the collected data. Then, the skill model is applied to performance-based haptic assistance to provide optimized references of the steering/pedaling movements. We evaluate the skill model and its application to performance-based haptic assistance in two user experiments…
Institute of Industrial Science, the University of Tokyo（东京大学工业科学研究所）
Haptic guidance in a shared steering assistance system has drawn significant attention in intelligent vehicle fields, owing to its mutual communication ability for vehicle control. By exerting continuous torque on the steering wheel, both the driver and support system can share lateral control of the vehicle. However, current haptic guidance steering systems demonstrate some deficiencies in assisting lane changing. This study explored a new steering interaction method, including the design and evaluation of an intention-based haptic shared steering system. Such an intention-based method can su…
Modern driver assistance systems as well as autonomous vehicles take their decisions based on local maps of the environment. These maps include, for example, surrounding moving objects perceived by sensors as well as routes and navigation information. Current research in the field of environment mapping is concerned with two major challenges. The first one is the integration of information from different sources e.g. on-board sensors like radar, camera, ultrasound and lidar, offline map data or backend information. The second challenge comprises in finding an abstract representation of this ag…
Autonomous vehicles are being deployed with a spectrum of capability, extending from driver assistance features for the highway in personal vehicles (SAE Level 2+) to fully autonomous fleet ride sharing services operating in complex city environments (SAE Level 4+). This spectrum of autonomy often operates in different physical environments with different degrees of assumed driver in-the-loop oversight and hence have very different system and subsystem requirements. At the heart of SAE Level 2 to 5 systems is localization and mapping, which ranges from road determination for feature geofencing…
Dr. Ing. h.c. F. Porsche AG（保时捷股份公司）；Robert Bosch GmbH（罗伯特·博世有限公司）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；NEC Laboratories Europe GmbH（NEC欧洲实验室有限公司）；Leibniz University Hannover（汉诺威莱布尼茨大学）
In recent years, computer vision algorithms have become more powerful. However, current algorithms mainly share one limitation: They rely on directly visible objects. This is a significant drawback compared to human behavior, where visual cues caused by objects (e.g., shadows) are already used intuitively to retrieve information or anticipate occurring objects. While driving at night, this performance deficit becomes even more obvious: Humans already process the light artifacts caused by the headlamps of oncoming vehicles to estimate where they appear, whereas current object detection systems …
This paper presents the state-of-the-art on Collision Avoidance and Collision Warning (CA,CW) systems. Traffic accidents result from driver errors or situations that are unpredictable for the driver. CA,CW systems are developed for reducing traffic accidents and saving peoples lives by warning drivers or taking compensatory action when drivers can not react fast enough. Besides these initiatives, this paper explains the importance of CA,CW driving assistance systems by considering economic issues as well. Technological developments are investigated in the context of finished and ongoing projec…
Mercedes-Benz AG（梅赛德斯-奔驰集团）；Princeton University（普林斯顿大学）；MESSRING Active Safety GmbH（MESSRING主动安全有限公司）
Current driver assistance systems and autonomous driving stacks are limited to well-defined environment conditions and geo fenced areas. To increase driving safety in adverse weather conditions, broadening the application spectrum of autonomous driving and driver assistance systems is necessary. In order to enable this development, reproducible benchmarking methods are required to quantify the expected distortions. In this publication, a testing methodology for disturbances from spray is presented. It introduces a novel lightweight and configurable spray setup alongside an evaluation scheme to…
Crash data of autonomous vehicles (AV) or vehicles equipped with advanced driver assistance systems (ADAS) are the key information to understand the crash nature and to enhance the automation systems. However, most of the existing crash data sources are either limited by the sample size or suffer from missing or unverified data. To contribute to the AV safety research community, we introduce AVOID: an open AV crash dataset. Three types of vehicles are considered: Advanced Driving System (ADS) vehicles, Advanced Driver Assistance Systems (ADAS) vehicles, and low-speed autonomous shuttles. The c…
Vehicle control algorithms exploiting connectivity and automation, such as Connected and Automated Vehicles (CAVs) or Advanced Driver Assistance Systems (ADAS), have the opportunity to improve energy savings. However, lower levels of automation involve a human-machine interaction stage, where the presence of a human driver affects the performance of the control algorithm in closed loop. This occurs for instance in the case of Eco-Driving control algorithms implemented as a velocity advisory system, where the driver is displayed an optimal speed trajectory to follow to reduce energy consumption…
University of Applied Sciences HTWG Konstanz（康斯坦茨应用技术大学）；Continental - A.D.C. GmbH（大陆集团ADC有限责任公司）
Driver assistance systems are increasingly becoming part of the standard equipment of vehicles and thus contribute to road safety. However, as they become more widespread, the requirements for cost efficiency are also increasing, and so few and inexpensive sensors are used in these systems. Especially in challenging situations, this leads to the fact that target discrimination cannot be ensured which in turn leads to a false reaction of the driver assistance system. Typically, the interaction between moving traffic participants is not modeled directly in the environmental model so that tracked…
Performance evaluation of a ROS2 based Automated Driving System
Fraunhofer Institute for Open Communication Systems (FOKUS)（弗劳恩霍夫开放通信系统研究所）；Daimler Center for Automotive Information Technology Innovations (DCAITI)（戴姆勒汽车信息技术创新中心）；University of Potsdam（波茨坦大学）
With the advent of Advanced Driver Assistance Systems (ADAS), there is an increasing need to evaluate driver behavior while using such technology. In this unique study, a forward collision warning (FCW) system using connected vehicle technology, was introduced in a driving simulator environment, to evaluate driver braking behavior and then the results are validated using data from field tests. A total of 93 participants were recruited for this study, for which a virtual network of South Baltimore was created. A one sample t-test was conducted, and it was found that the mean reduction in speed …
Ford AV, LLC（福特自动驾驶汽车有限责任公司）；Ford Motor Company（福特汽车公司）；Xona Space Systems（Xona空间系统公司）
There is a growing need for vehicle positioning information to support Advanced Driver Assistance Systems (ADAS), Connectivity (V2X), and Autonomous Driving (AD) features. These range from a need for road determination ($<$5 meters), lane determination ($<$1.5 meters), and determining where the vehicle is within the lane ($<$0.3 meters). This paper presents the Ford Highway Driving RTK (Ford-HDR) dataset. This dataset includes nearly 30,000 km of data collected primarily on North American highways during a driving campaign designed to validate driver assistance features in 2018. This includes …
