Search Results

Improvement of vehicle path-tracking performance not only affects the vehicle driving safety and comfort but is also essential for autonomous driving technology. The current research focuses on vehicle path-tracking control study and application of dual-motor SBW system. The preview driver model is developed by considering the lateral and yaw tracking. MPC (model predictive control) and LQR (linear quadratic regulator) path following controllers are developed to compare the tracking control performance. A steer-by-wire (SBW) system of dual-motor configuration is designed with permanent magnet synchronous motor (PMSM) control scheme. Finally, the proposed control methods are verified with different driving cases, which shows that the system can effectively achieve small tracking errors in the simulation, and also can be applied in the future autonomous driving or advanced driver assistance system to maintain the lateral and yaw errors within a safe range during path-tracking.

Testing vision-based advanced driver assistance systems (ADAS) in a Camera-in-the-Loop (CiL) bench setup, where external visual inputs are used to stimulate the system, provides an opportunity to experiment with a wide variety of test scenarios, different types of vehicle actors, vulnerable road users, and weather conditions that may be difficult to replicate in the real world. In addition, once the CiL bench is setup and operating, experiments can be performed in less time when compared to track testing alternatives. In order to better quantify normal operating zones, track testing results were used to identify behavior corridors via a statistical methodology. After determining normal operational variability via track testing of baseline stationary surrogate vehicle and pedestrian scenarios, these operating zones were applied to screen-based testing in a CiL test setup to determine particularly challenging scenarios which might benefit from replication in a track testing environment.

The advancement of Advanced Driver Assistance System (ADAS) technologies offers tremendous benefits. ADAS features such as emergency braking, blind-spot monitoring, lane departure warning, adaptive cruise control, etc., are promising to lower on-road accident rates and severity. With a common goal for the automotive industry to achieve higher levels of autonomy, maintaining ADAS sensor performance and reliability is the core to ensuring adequate ADAS functionality. Currently, the challenges faced by ADAS sensors include performance degradation in adverse weather conditions and a lack of controlled evaluation methods. Outdoor testing encounters repeatability issues, while indoor testing with a stationary vehicle lacks realistic conditions. This study proposes a hybrid method to combine the advantages of both outdoor and indoor testing approaches in a Drive-thru Climate Tunnel (DCT).

In order to validate the operation of advanced driver assistance systems (ADAS), tests must be performed that assess the performance of the system in response to different scenarios. Some of these systems are designed for crash-imminent situations, and safely testing them requires large stretches of controlled pavement, expensive surrogate targets, and a fully functional vehicle. As a possible more-manageable alternative to testing the full vehicle in these situations, this study sought to explore whether these systems could be isolated, and tests could be performed on a bench via a hardware-in-the-loop methodology. For camera systems, these benches are called Camera-in-the-Loop (CiL) systems and involve presenting visual stimuli to the device via an external input.

Autonomous Driving (AD) and Advanced Driver Assistance Systems (ADAS) are being actively developed to prevent traffic accidents. As the complexity of AD/ADAS increases, the number of test scenarios increases as well. An efficient development process that meets AD/ADAS quality and performance specifications is thus required. The European New Car Assessment Programme (Euro NCAP®1) and the Japan Automobile Manufacturers Association (JAMA®2) have both defined test scenarios, but some of these scenarios are difficult to carry out with real-vehicle testing due to the risk of harm to human participants. Due to the challenge of covering various scenarios and situations with only real-vehicle testing, we utilize simulation-based testing in this work. Specifically, we construct a Model-in-the-Loop Simulation (MILS) environment for virtual testing of AD/ADAS control logic.

Image segmentation has historically been a technique for analyzing terrain for military autonomous vehicles. One of the weaknesses of image segmentation from camera data is that it lacks depth information, and it can be affected by environment lighting. Light detection and ranging (LiDAR) is an emerging technology in image segmentation that is able to estimate distances to the objects it detects. One advantage of LiDAR is the ability to gather accurate distances regardless of day, night, shadows, or glare. This study examines LiDAR and camera image segmentation fusion to improve an advanced driver-assistance systems (ADAS) algorithm for off-road autonomous military vehicles. The volume of points generated by LiDAR provides the vehicle with distance and spatial data surrounding the vehicle.

The use of platforms to carry vulnerable road user (VRU) targets has become increasingly necessary with the rise of automated driver assistance systems (ADAS) on vehicles. These ADAS features must be tested in a wide variety of collision-imminent scenarios which necessitates the use of strikable targets carried by an overrun-able platform. To enable the testing of ADAS sensors such as lidar, radar, and vision systems, S-E-A, a longtime supplier of vehicle testing equipment, has created the STRIDE robotic platform (Small Test Robot for Individuals in Dangerous Environments). This platform contains many of the key ingredients of other platforms on the market, such as a hot-swappable battery, E-stop, and mounting points for targets. However, the STRIDE platform additionally provides features which can enable non-routine testing such as: turning in place, driving with an app on a mobile phone, user-scripting, and steep grade climbing capability.

This study aimed to construct driver models for overtaking behavior using long short-term memory (LSTM). During the overtaking maneuver, an ego vehicle changes lanes to the overtaking lane while paying attention to both the preceding vehicle in the travel lane and the following vehicle in the overtaking lane and returns to the travel lane after overtaking the preceding vehicle in the travel lane. This scenario was segregated into four phases in this study: Car-Following, Lane-Change-1, Overtaking, and Lane-Change-2. In the Car-Following phase, the ego vehicle follows the preceding vehicle in the travel lane. Meanwhile, in the Lane-Change-1 phase, the ego vehicle changes from the travel lane to the overtaking lane. Overtaking is the phase in which the ego vehicle in the overtaking lane overtakes the preceding vehicle in the travel lane.

Accurate identification of driver’s braking intention is essential in advanced driver assistance system and can make the driving process more comfortable and trustworthy. In this paper, a novel method for driver braking intention identification in cut-in scenarios was proposed by using driver’s gaze information and motion information of cut-in vehicles. Firstly, a "looking in and looking out" experimental platform including three eye-tracking cameras and one front-view camera was built to collect driver's gaze information and the vehicle motion information. Secondly, driver’s gaze features and motion features of cut-in vehicles were selected and the braking intention identification performance of several decision tree-based ensemble learning algorithms was compared. Thirdly, the feature importance was analyzed by using SHAP (SHapley Additive exPlanations) values. This novel method of braking intention identification makes full use of in-vehicle camera sensors.

Acceptance criteria and validation target are the most important metrics used to measure/assure safety of the intended function (SOTIF) of an autonomous vehicle or advanced driver assistance system (ADAS). Often acceptance criteria are defined as acceptable number of fatalities, injuries or property damage events in certain hours of operation or for certain mileage driven. Validation target on the other hand is the amount of effort required in terms of hours of operation or mileage to be driven to show that the acceptance criteria is met. Although existing research details about potential values for acceptance criteria and validation target, they overlook various factors such as operational design domain, operational lifetime of a vehicle, average mileage of a vehicle, and length of roads. As a result, often acceptance criteria values are very small (e.g., 10-12 incidents/h or mi) and validation targets are very large (e.g., 1013 miles).

Ensuring the safety of vehicle occupants has always been the primary focus of automakers. To achieve this goal, they have invested in the development of active safety features, which are designed to prevent accidents from occurring in the first place. These innovations are driven by a desire to save lives and reduce the risk of injury or death on the road. The implementation of advanced driver assistance systems (ADAS) and automated driving functions requires a high level of complexity and coordination between various subsystems. To meet these challenges, modular design of the domain controller has emerged as a promising approach. By separating the controller into smaller, specialized modules, it is possible to more efficiently and effectively manage the various functions needed for ADAS and automated driving.

Due to the increasing complexities, the safety assurances for Automated Driving Systems (ADSs) and Advanced Driver Assistance Systems (ADASs) pose challenges. Recent development within the industry and academia suggests a scenario-based approach underpinned by the system’s Operational Design Domain (ODD) for its safety assurance. In such framework, the ODD defines the safe operating boundary, whereas the scenarios set out individual test conditions. To assess the behavior of the system, a critical element for road safety is the ability to respect the rules of the road. This paper joins together ODDs, scenarios, and rules of the road to form a scalable ODD-based safety assurance framework. The backbone of the framework contains a coherent and common taxonomy to describe the ODDs and behavior library, the scenario tagging structure from the ASAM OpenLABEL standard has been used in the example use case.

Testing was conducted to evaluate the performance of the 2014 Subaru Forester’s North American Generation 1 EyeSight system at speeds between 6 and 57 miles per hour (mph). The testing utilized a custom-built foam stationary vehicle target designed to withstand 60+ mph impact speeds. Testing measured the Time to Collision (TTC) values of the visual/audible component of the forward collision warning that was presented to the driver. In addition, the testing quantified the TTC and Time to Collision 2 (TTC2) response of the Automatic Emergency Braking (AEB) system including the timing and magnitude of the stage one braking response and the timing and magnitude of the stage two braking response. The results of the testing add higher speed Forward Collision Warning (FCW) and AEB testing scenarios to the database of publicly available tests from sources like the Insurance Institute for Highway Safety (IIHS), which currently evaluates vehicles’ AEB systems at speeds of 12 and 25 mph.

ADAS (Advanced Driver Assistance System) functions can help the driver avoid accidents or mitigate their effect when they occur, and are pre-cursors to full autonomous driving (SAE defined as Level 4+). The main goal of this work is to develop a Model-Based system to actuate the Evasive Maneuver Assist (EMA) function. A typical scenario is the situation in which longitudinal Autonomous Emergency Braking (AEB) is too late and the driver has to adopt an evasive maneuver to avoid an object suddenly appearing on the road ahead. At this time, EMA can help improve the driver’s steering and braking operation in a coordinated way. The vehicle maneuverability and response performance will be enhanced when the driver is facing the collision. The function will additionally let the vehicle steer in a predetermined optimized trajectory based on a yaw rate set point and stabilize the vehicle. The EMA function is introduced with some analysis of benchmarking data.

Vehicular odometers serve as a standard component in driver assistance system to provide continuous navigation. Odometer fraud is the disconnection, resetting, or alteration of a vehicle’s odometer with the intent to change the number of miles indicated. Odometer fraud occurs when the seller of a vehicle falsely represents the actual mileage of a vehicle to the buyer. But the Odometer readings are essential when it comes to ascertaining the fair market value of a used vehicle. Hence, there is a need to protect the odometer which resides in the instrument cluster of the digital cockpit. Any manipulation is very difficult to detect and to prove once made, even by expert technicians using specific On-Board Diagnostics (OBD) testing devices. One of the most critical issues is that currently odometers are not locked out from external access, in contrast to other vehicle components, which have higher protection levels.

Advanced driver assistance systems rely on external sensors that encompass the vehicle. The reliability of such systems can be compromised by adverse weather, with performance hindered by both direct impingement on sensors and spray suspended between the vehicle and potential obstacles. The transportation of road spray is known to be an unsteady phenomenon, driven by the turbulent structures that characterise automotive flow fields. Further understanding of this unsteadiness is a key aspect in the development of robust sensor implementations. This paper outlines an experimental method used to analyse the spray ejected by an automotive body, presented through a study of a simplified vehicle model with interchangeable rear-end geometries. Particles are illuminated by laser light sheets as they pass through measurement planes downstream of the vehicle, facilitating imaging of the instantaneous structure of the spray.

By 2030, about 95% of new vehicles sold globally will be connected, up from around 50% today. Around 45% of these vehicles will have intermediate and advanced connectivity features (source: McKinsey, 2021). Modernization, standardization, and automation are the key steps in the roadmap of data handling for connected vehicles. Vehicle software increasingly sits within a connected ecosystem of devices. Consumer expectations are shifting more towards digital compatibility, connectivity, and new functionalities offered in autonomous vehicles. Digitalization is turning the vehicles of the future into commodities that are as experimental as they are useful. Many OEMs are at the beginning of this transformation journey and have struggled on the software side of things. The entire automotive industry is putting its efforts into effectively monetizing the data captured during the development and management of autonomous vehicles.

The investigation of vehicle soiling by improvement of vehicle parts to optimize the surrounding airflow is of great importance not only because of the visibility through windows and at mirrors but also the functionality of different types of sensors (camera, lidar, radars, etc.) for the driver assistance systems and especially for autonomous driving vehicles has to be guaranteed. These investigations and corresponding developments ideally take place in the early vehicle development process since later changes are difficult to apply in the vehicle production process for many reasons. Vehicle soiling is divided into foreign soiling and self-soiling with respect to the source of the soiling water, e.g., direct rain impact, swirled (dirty) water of other road users and own rotating wheels. The investigations of the soiling behavior of vehicles were performed experimentally in a wind tunnel and street tests.

Driver distraction, or misjudgment is the most common causes of car accidents. As a result, the research and implementation of vehicle safety systems have accelerated in recent decades, making Advanced Driver Assistance Systems (ADAS) critical for improving road safety. The study here focuses on, how to test ADAS, namely Autonomous Emergency Braking System (AEBS), by taking into account, things like, appropriate test environments, and traffic scenarios, as well as verification, and validation methodologies. For simulation, we have used IPG Carmaker to measure the braking efficiency of the vehicle, on a curved road path. In this paper, Ackermann’s geometry and Bicycle Model are also studied, in order to understand the dynamics of the vehicle, to enhance the accuracy of lateral distance estimation, especially during curved maneuvers.

Multi-sensor fusion strategies have gradually become a consensus in autonomous driving research. Among them, radar-camera fusion has attracted wide attention for its improvement on the dimension and accuracy of perception at a lower cost, however, the processing and association of radar and camera data has become an obstacle to related research. Our approach is to build a concise framework for camera and radar detection and data association: for visual object detection, the state-of-the-art YOLOv5 algorithm is further improved and works as the image detector, and before the fusion process, the raw radar reflection data is projected onto image plane and hierarchically clustered, then the projected radar echoes and image detection results are matched based on the Hungarian algorithm. Thus, the category of objects and their corresponding distance and speed information can be obtained, providing reliable input for subsequent object tracking task.