LiDAR-Based Fail-Safe Emergency Maneuver for Autonomous Vehicles

<div class="section abstract"><div class="htmlview paragraph">In this research, an optimal real-time trajectory planning method is proposed for autonomous ground vehicles in case of overtaking a moving obstacle. When an autonomous vehicle detects a moving vehicle ahead of it in a proper speed and distance and the braking is not efficient due to the lost of its kinematic energy, the autonomous vehicle decides to overtake the obstacle by performing a double lane-change maneuver. A two-phase nonlinear optimal problem is developed for generating the path for the overtaking maneuver. The cost function of the first phase is defined in such a way that the vehicle approaches the moving obstacle as close as possible. Besides, the cost function of the second phase is defined as the minimization of the sum of the vehicle lateral deviation from the reference path and the rate of steering angle during the overtaking maneuver while the lateral acceleration of the vehicle does not exceed a safe limit. For the real-time path planning of a vehicle with high speed, the result of solving the optimal path planning are stored in the look-up table form for offline use. A full nonlinear vehicle modeled in CarSim software is used for path tracking simulation. The simulation results show that the generated path for the autonomous vehicle satisfies all the vehicle dynamics constraints, therefore it is applicable for a real autonomous vehicle.</div></div>

<div class="section abstract"><div class="htmlview paragraph">Autonomous vehicle is a vehicle capable of sensing its environment and taking decisions automatically with no human interventions. To achieve this goal, ADAS (Advance Driving Assistance System) technologies play an important role and the technologies are improving and emerging. The sensing of environment can be achieved with the help of sensors like Radar and Camera. Radar sensors are used in detecting the range, speed and directions of multiple targets using complex signal processing algorithms. Radar with long range and short range are widely used in the autonomous vehicles. Radar sensors with long range can be used to realize features like Adaptive Cruise Control, Advance Emergency Brake Assist. The short-range radar sensors are used for Blind Spot Monitoring, Lane Change Assist, Rear/Front Cross Traffic Alert and Occupant Safe Exit. To realize the Autonomous vehicle functionalities four short range radar sensors are required, two on front and two on rear (left and right).</div><div class="htmlview paragraph">This paper presents a detailed study on different solutions and methodologies for simulating radar signals and validation of short-range radar-based features. The various methodologies involve simulating of radar signals using Radar Target Simulator, Bypassing the radar sensing and injecting the radar raw signals, Bypassing the radar sensing injecting the target objects and Field and track testing in the real time environment. This paper also describes the challenges and comparison of different solutions.</div></div>

<div class="section abstract"><div class="htmlview paragraph">Autonomous vehicles have the potential to provide mobility to individuals who experience transportation disadvantages due to the inability to drive as a result of physical, cognitive or visual limitations/impairments as well as able-bodied individuals with no/limited desire to drive. Individuals who do not have easy access to transportation have social, academic, health, and career disadvantages in comparison to their peers. Fully autonomous vehicles have the potential to offer mobility solutions to these individuals.</div><div class="htmlview paragraph">A user-centered design approach was utilized by a multidisciplinary team of engineers, human factors specialists, and designers to develop future vehicle features for a broad range of users. In-depth interviews and day-in-the-life experiences provided the team with an understanding of the needs and constraints of very different types of users including:<ul class="list disc"><li class="list-item"><div class="htmlview paragraph">a millennial with a visual impairment,</div></li><li class="list-item"><div class="htmlview paragraph">a professional in a major metropolitan area who does not want to drive yet needs to transport influential clients to meetings throughout the city,</div></li><li class="list-item"><div class="htmlview paragraph">a full-time working mom with 3 kids under the age of 12, and.</div></li><li class="list-item"><div class="htmlview paragraph">a designer who is a quadriplegic who lives as independently as possible while using a large motorized wheelchair.</div></li></ul></div><div class="htmlview paragraph">User preferences, needs, and wants are discussed for each user. Future autonomous vehicles will have vastly different metrics for user satisfaction than what exists today.</div></div>

<div class="section abstract"><div class="htmlview paragraph">Autonomous vehicle technology has the potential to improve the safety, efficiency, and cost of our current transportation system by removing human error. With sensors available today, it is possible for the development of these vehicles, however, there are still issues with autonomous vehicle operations in adverse weather conditions (e.g. snow-covered roads, heavy rain, fog, etc.) due to the degradation of sensor data quality and insufficiently robust software algorithms. Since autonomous vehicles rely entirely on sensor data to perceive their surrounding environment, this becomes a significant issue in the performance of the autonomous system. The purpose of this study is to collect sensor data under various weather conditions to understand the effects of weather on sensor data. The sensors used in this study were one camera and one LiDAR. These sensors were connected to an NVIDIA Drive Px2 which operated in a 2019 Kia Niro. Two custom scenarios (static and dynamic objects) were chosen to collect sensor data operating in four real-world weather conditions: fair, cloudy, rainy, and light snow. An algorithm developed herein was used to provide a method of quantifying the data for comparison against the other weather conditions. The results from these performance algorithms show that sensor data quality degrades by an average of 13.88% for static objects and 16.16% for dynamic objects while operating in these conditions, with operations in rain proving to have the most significant effect on sensor data degradation. From this study, it is hypothesized that advancements in data processing algorithms can improve the usability of this degraded data. In future work, we seek to explore fault-tolerant sensor fusion algorithms that can overcome the effects of adverse weather.</div></div>

<div class="section abstract"><div class="htmlview paragraph">Connected and autonomous vehicles are different from traditional vehicles. The communication between vehicles (V2V) or between vehicles and infrastructures (V2I) renders it possible to convey traffic information (e.g. signal timing or speed advisory) from signal controllers to vehicles as well as vehicles to vehicles in real time. Taking this advantage, this paper aims to developing an algorithm which enables the interconnected autonomous vehicles running efficiently on arterials. A set of driving rules determining random behavior and swarm behavior of autonomous vehicles is developed based on swarm intelligence theory. Under control of these rules, each autonomous vehicle follows the same rules, which make it select target vehicle from all the optimal individuals in detection zone according to characteristics of itself, then approach to the target by changing lane, following former car, or accelerating. The result of simulation shows that this swarm algorithm enables an autonomous vehicle to meet its own requirements quickly and form a stable platoon within 30 seconds. Due to the consistency of the individuals in a platoon, autonomous vehicle can maintain the small car-following gap. This decreases the fragmentation of road, thereby greatly improves the formation of platoons compared to individuals under high density circumstances. Moreover, it was found that the proposed swarm intelligence based algorithm increases the accessibility of arterial significantly.</div></div>

<div class="section abstract"><div class="htmlview paragraph">The knowledge of representative load collectives and duty cycles is crucial for designing and dimensioning vehicles and their components. For human driven vehicles, various methods are known for deriving these load spectra directly or indirectly from fleet measurement data of the customer vehicle operation. Due to the lack of market penetration of highly automated and autonomous vehicles, there is no sufficient fleet data available to utilize these methods. As a result of increased demand for ride comfort compared to human driven vehicles, autonomous vehicle operation promises reduced driving speeds as well as reduced lateral and longitudinal accelerations. This can consequently lead to decreasing operation loads, thus enabling potentially more light-weight, cost-effective, resource-saving and energy-efficient vehicle components. In order to unlock this potential of dedicatedly dimensioned components for autonomous vehicles, a methodology for quantifying the loads in customer operation is required. Therefore, this paper proposes a novel methodology to quantify operation loads of highly automated and autonomous vehicles based on statistical long-term simulation, in which route characteristics, surrounding traffic and vehicle control algorithms are taken into account. The statistical synthesis of driving routes as the basis for further long-term simulation is addressed in detail in this paper. Furthermore, the impact of different lateral and longitudinal control strategies on drivetrain loads of an autonomous vehicle is showcased as an early result of the proposed methodology. Future work required to complete the proposed methodology is addressed in the outlook of this paper. Additional utilization of the driving route synthesis for the validation of autonomous driving functions is pointed out.</div></div>

<div class="section abstract"><div class="htmlview paragraph">Autonomous vehicle motion planning and control are vital components of next-generation intelligent transportation systems. Recent advances in both data- and physical model-driven methods have improved driving performance, yet current technologies still fall short of achieving human-level driving in complex, dynamic traffic scenarios. Key challenges include developing safe, efficient, and human-like motion planning strategies that can adapt to unpredictable environments. Data-driven approaches leverage deep neural networks to learn from extensive datasets, offering promising avenues for intelligent decision-making. However, these methods face issues such as covariate shift in imitation learning and difficulties in designing robust reward functions. In contrast, conventional physical model-driven techniques use rigorous mathematical formulations to generate optimal trajectories and handle dynamic constraints.</div><div class="htmlview paragraph"><b>Hybrid Data- and Physical Model-Driven Safe and Intelligent Motion Planning and Control for Autonomous Vehicles</b> presents a hybrid framework that combines data-driven insights with the robustness of physical models. It identifies key challenges in fusing these disparate methods and outlines potential solutions in developing robust fusion strategies, establishing generalized mixed dynamics models, and designing multi-objective robust control systems. In addition, the report explores future research directions to enhance learning efficiency, improve adaptability to rare but critical scenarios, and ultimately pave the way for secure, efficient, and human-like autonomous driving systems.</div><div class="htmlview paragraph"><a href="https://www.sae.org/publications/edge-research-reports" target="_blank">Click here to access the full SAE EDGE</a><sup>TM</sup><a href="https://www.sae.org/publications/edge-research-reports" target="_blank"> Research Report portfolio.</a></div></div>

<div class="htmlview paragraph">Due to protection applicances in the car, fewer persons sustain injuries in the course of traffic accidents. It can be pointed out that the injury pattern of car occupants was visibly changed by the seat belt, in earlier years the windscreen and steering wheel could hardly still be regarded as injury sources, but in the current situation with belt using of over 90% the injuries of all injured car drivers occur under other circumstances:</div> <div class="htmlview paragraph">19% of all injured car drivers suffered injuries by the steering wheel, 20% by the dashboard, 29% by belt load and 14% caused by parts of the footroom region.</div> <div class="htmlview paragraph">It can be summarized that the present car safety measures did not avoid all major injuries and lower limb injuries occur relatively often.</div> <div class="htmlview paragraph">This study will explain the injury mechanisms of lower limb injuries and show demands for car developments and dummy test work. The data has been derived from traffic accidents documented by scientific team at the Accident Research Unit of the Medical University Hannover / Germany, by order of the Federal Highway Research Institute BAST.</div> <div class="htmlview paragraph">Out of a sample of 6985 belted drivers in car crashes 2,605 belted car drivers with lower limb injuries could be analysed. Persons with pelvic fractures as well as isolated hip joint fractures were included. The accidents are documented during the years 1985 to 94 within a statistical random sample and weighting procedure.</div> <div class="htmlview paragraph">In the study it was established that the injury risk for the legs is different in various collision types as frontal and lateral impact. Impacts of the vehicle side against a tree cause the most frequent and the most severe consequences. The different kinds and localisations of injuries are shown related to accident severity parameter like Delta-v and the influence of intrusion will be analysed. The pelvis has to be included in the explanation of mechanisms. Important for the resulting injury are impulse direction and position of lateral force transmission.</div> <div class="htmlview paragraph">Isolated femural fractures are incured when a direct impact to the thigh region occurs distinctly in front of the pelvis laterally or transversally. A combination of femural and pelvic fractures can be found when the impact occurs transversally from the front. Isolated pelvic fractures are found when the lateral impact involves the pelvic region. Pelvic girdle fractures do also often determine a transverse longitudinal axis component. Pelvic fractures were exposed to high collision severity. They occur mainly in lateral impacts, especially with poles.</div> <div class="htmlview paragraph">The kind of interior deformation is responsible for the kind of injury pattern and the intrusion can be seen as an important influence factor.</div>

<div class="section abstract"><div class="htmlview paragraph">In the domain of advanced driver assistance systems and autonomous vehicles, precise perception and interpretation of the vehicle's environment are not merely requirements they are the very foundation upon which every aspect of functionality and safety is constructed. One prevalent method of representing the environment is through the use of an occupancy grid map. This map segments the environment into distinct grid cells, each of which is evaluated to determine if it is occupied or free. This evaluation operates under the assumption that each grid cell is independent of the others. The underlying mathematical structure of this system is the binary Bayes filter (BBF). The BBF integrates sensor data from various sources and can incorporate measurements taken at different times. The occupancy grid map does not rely on the identification of individual objects, which allows it to depict obstacles of any shape. This flexibility is a key advantage of this approach. Traditional occupancy grid maps fall short when it comes to predicting dynamic environments due to their lack of a process model. A notable enhancement to this static model is the Bayesian Occupancy Filter (BOF), which, unlike its predecessor, estimates a velocity distribution for each grid cell's occupancy using a histogram filter. However, the BOF's computational demands are high. To address this, research propose representing the dynamic state of grid cells using particles. This method enables the computation of dynamic grid maps in real-time applications, even with larger grid cell sizes and higher resolution. Despite these advancements, dynamic occupancy grid maps remain a relatively new field of study, especially when compared to more established object-tracking approaches. Until now, the BOF has been treated as a distinct research area with minimal overlap with other tracking methodologies. This methodology aims to bridge that gap and foster a more integrated approach to dynamic environment estimation.</div><div class="htmlview paragraph">This study introduces a novel approach to dynamic grid mapping, conceptualized as an approximation of a Random Finite Set (RFS) filter. An RFS is a probabilistic representation of a finite, random collection of objects and their respective states. Finite Set Statistics (FISST) provide a framework for Bayesian filtering of these random finite sets and form the foundation for several multi-object tracking methodologies, such as the Probability Hypothesis Density (PHD) filter. By characterizing the grid as an RFS, we can apply sophisticated concepts from the well-established domain of RFS filtering to dynamic grid mapping. The research develops a filter known as the Probability Hypothesis Density/Multi-Instance Bernoulli (PHD/MIB) filter. This filter alternately represents and propagates the dynamic grid map as a PHD and as multiple instances of Bernoulli filters, thereby offering a more integrated and efficient approach to dynamic environment estimation.</div><div class="htmlview paragraph">Furthermore, this research introduces a Sequential Monte Carlo (SMC) implementation of the PHD/MIB filter, as well as an approximation within the Dempster-Shafer framework, termed the Dempster-Shafer PHD/MIB (DS-PHD/MIB) filter. This DS-PHD/MIB filter necessitates fewer particles than the original PHD/MIB filter, thereby enhancing computational efficiency. The study provides a comprehensive description of an efficient, massively parallel implementation of the DS-PHD/MIB filter. The algorithm's pseudo code is also outlined, offering a clear and concise understanding of its workings. This approach further strengthens the integrated and efficient methodology for dynamic environment estimation.</div><div class="htmlview paragraph">In conclusion, the research delineates the attributes of the DS-PHD/MIB filter and debates its pros and cons in comparison to object-based tracking methodologies, using practical examples for illustration. A quantitative assessment using real-world data demonstrates that the DS-PHD/MIB filter yields consistent state estimation outcomes. It effectively models both the stochastic multi-object transition process and the stochastic multi-object observation process. Moreover, the evaluation affirms the real-time capability of the parallelized implementation of the DS-PHD/MIB filter. It validates its utility for state estimation in dynamic vehicle environments, thereby underscoring its potential for practical applications in dynamic environment estimation. This comprehensive approach offers a promising avenue for future research and development in this field.</div></div>

<div class="section abstract"><div class="htmlview paragraph">Technological advances in both hardware (Nano-electronics) and software (artificial intelligence) are increasingly influencing our lives on equipment and devices that surrounds us and more recently our means of locomotion. The autonomous vehicles, which previously appeared only in movie scenes, can already be found in our environment, such as ships, cars, trucks, tractors and aero engines. Considering the autonomous vehicles, its launching is much closer than we could imagine, since many companies signalize having the conditions to launch them in a large scale within 2018 year. The insertion of this type of technology opens a range of advances related to vehicles and the environment in which it is inserted.</div><div class="htmlview paragraph">The communication between the vehicles, roads and people can be highlighted. These advances reveal a series of benefits to the customer such as free time during the route, higher safety, etc. Moreover there are some other discussion about a new legislation, roads and traffic signs conditions and the economic impact regarding the driver’s workforce.</div></div>

Joint analysis of crash injury severities for autonomous and conventional vehicles in mixed traffic environments: Application of random parameter bivariate probit model.

<div class="section abstract"><div class="htmlview paragraph">Lane detection plays a critical role in autonomous vehicles for safe and reliable navigation. Lane detection is traditionally accomplished using a camera sensor and computer vision processing. The downside of this traditional technique is that it can be computationally intensive when high quality images at a fast frame rate are used and has reliability issues from occlusion such as, glare, shadows, active road construction, and more. This study addresses these issues by exploring alternative methods for lane detection in specific scenarios caused from road construction-induced lane shift and sun glare. Specifically, a U-Net, a convolutional network used for image segmentation, camera-based lane detection method is compared with a radar-based approach using a new type of sensor previously unused in the autonomous vehicle space: radar retro-reflectors. This evaluation is performed using ground truth data, obtained by measuring the lane positions and transforming them into pixel coordinates. The performance of each method is assessed using the statistical <i>R</i><sup>2</sup> score, indicating the correlation between the detected lane lines and the ground truth. The results show that the U-Net camera-based method exhibits limitations in accurately detecting and aligning the lane lines, particularly in challenging scenarios. However, the radar-based lane detection method demonstrates a strong correlation with the ground truth which implies that the use of this sensor may improve current reliability issues from conventional camera lane detection approach. Furthermore, the study highlights the limitations of the U-Net model for camera lane detection, especially in scenarios with sun glare. This study shows that infrastructure-based radar retro-reflectors can improve autonomous vehicle lane detection reliability. The integration of different sensor modalities and the development of advanced computer vision algorithms are crucial for improving the accuracy, reliability, and energy efficiency of lane detection systems. Addressing these challenges contributes to the advancement of autonomous vehicles and the realization of safer and more efficient transportation systems.</div></div>

<div class="section abstract"><div class="htmlview paragraph">Autonomous vehicles must guarantee safety in all road conditions, including driving on wet roads. Aquaplaning (or hydroplaning) is a phenomenon known since the beginning of automotive history, never solved by an active safety system. Currently, no countermeasure system on the market is able to effectively counteract aquaplaning: ABS, ESP or TCS are still inefficient in overcoming this situation. Latest statistical data confirm that the higher percentage of accidents, injuries and deaths are caused by wet road conditions. The aquaplaning happens when the water on the road is too much and the tires start to float causing the instantaneous loss of control. Such phenomenon occurs in human-driven vehicles, with the responsibility of the driver, but in autonomous vehicles (e.g. Level 5), the responsibility for the safety depends on the car and the reduction of the speed is not a solution. In this work, it is presented the second version of our anti-aquaplaning active safety system, which can identify, without any new sensor, if the vehicle is subject to aquaplaning. When the software detects the phenomenon, the hydraulic system, designed to have a very short reaction time, makes an intelligent injection of water in front of the tires restoring the adherence of any type of vehicle (human-driven or autonomous) in a few milliseconds. It will also be shown how the system could be integrated with sensorized tires (tested for the first time in the automotive history). Moreover, the effects coming from the synergy between the system, ADAS and 5G technology will finally be highlighted in terms of improvements for the future smart mobility.</div></div>

<div class="section abstract"><div class="htmlview paragraph">For high-level autonomous vehicles, under many circumstances, accidents are not caused by functional failures, but by system performance limitations and human misuses. ISO 21448 defines this kind of safety issue as safety of the intended functionality (SOTIF). However, most of SOTIF-related researches focus on hazard identification and risk evaluation, as well as verification and validation. There is still lack of public systematic identification method for triggering events. Therefore, this paper proposes an identification framework for triggering events which are related to system performance limitations and human misuses. In the aspect of system performance limitations, there are four steps, which are the specification of the research target, the analysis of influencing factors, the identification of triggering events, and the verification test. In the aspect of human misuses, triggering events can be identified based on the guide words for human error. Furthermore, based on the identification of triggering events, a safety analysis and verification framework for both high-level and low-level autonomous vehicles is proposed. The proposed framework contains five steps, which are hazard identification and risk evaluation, the identification of triggering events, the generation of test cases, test and results analysis, and the derivation of functional safety requirements. Besides, a SAE L3 autonomous vehicle is analyzed and corresponding tests are conducted. Two tests are illustrated in detail in this paper, which involve triggering events related to system performance limitations and human misuses, respectively. And the results show that the two triggering events could both lead to effective hazardous events, which proves the feasibility of the proposed framework.</div></div>

Human drivers naturally adapt their behaviour depending on the traffic conditions, such as the current weather and road type. Autonomous vehicles need to do the same, in a way that is both safe and efficient in traffic composed of both conventional and autonomous vehicles. In this paper, we demonstrate the applicability of a reconfigurable vehicle controller agent for autonomous vehicles that adapts the parameters of a used car‐following model at runtime, so as to maintain a high degree of traffic quality (efficiency and safety) under different weather conditions. We follow a dynamic software product line approach to model the variability of the car‐following model parameters, context changes and traffic quality, and generate specific configurations for each particular context. Under realistic conditions, autonomous vehicles have only a very local knowledge of other vehicles' variables. We investigate a distributed model predictive controller agent for autonomous vehicles to estimate their behavioural parameters at runtime, based on their available knowledge of the system. We show that autonomous vehicles with the proposed reconfigurable controller agent lead to behaviour similar to that achieved by human drivers, depending on the context.