Scenarios Of Autonomous Vehicles Research Articles

Advancing VR simulators for autonomous vehicle–pedestrian interactions: A focus on multi-entity scenarios

Recent research has increasingly focused on how autonomous vehicles (AVs) communicate with pedestrians in complex traffic situations involving multiple vehicles and pedestrians. VR is emerging as an effective tool to simulate these multi-entity scenarios, offering a safe and controlled study environment. Despite its growing use, there is a lack of thorough investigation into the effectiveness of these VR simulations, leaving a notable gap in documented insights and lessons. This research undertook a retrospective analysis of two distinct VR-based studies: one focusing on multiple AV scenarios (N = 32) and the other on multiple pedestrian scenarios (N = 25). Central to our examination are the participants’ sense of presence and their crossing behaviour. The findings highlighted key factors that either enhance or diminish the sense of presence in each simulation, providing considerations for future improvements. Furthermore, they underscore the influence of controlled scenarios on crossing behaviour and interactions with AVs, advocating for the exploration of more natural and interactive simulations that better reflect real-world AV and pedestrian dynamics. Through this study, we set a groundwork for advancing VR simulators to study complex interactions between AVs and pedestrians.

Adaptive sensor attack detection and defense framework for autonomous vehicles based on density

The security of autonomous vehicles heavily depends on localization systems that integrate multiple sensors, which are vulnerable to sensor attacks and increase the risk of accidents. Given the diversity of sensor attacks and the dynamic changing of driving scenarios of autonomous vehicles, an adaptive and effective attack detection and defense framework faces a considerable challenge. This paper proposes a novel real-time adaptive attack detection and defense framework based on density, which can detect and identify attacked sensors and effectively recover data. We first develop a reinforcement learning multi-armed Bandit-based Density-Based Spatial Clustering of Applications with Noise (BDBSCAN) algorithm that selects hyperparameters adaptively. The Adaptive Extended Kalman Filter (AEKF) combines with the vehicle dynamic model on the localization system and extracts data features used for the BDBSCAN algorithm to monitor potential sensor attacks. If attack detection indicates possible system compromise, AEKF is further employed on localization sensors with anomalies identified through the BDBSCAN algorithm of the attacked sensors. To ensure precision and reliability, the data recovery incorporates a redundancy mechanism to apply a decision tree to select the optimal state estimation between AEKF and Extended Kalman Filter (EKF) to replace corrupted sensor data. To evaluate the effectiveness and adaptability of the proposed framework, we conducted 15,000 experiments using the real-world KITTI and V2V4Real datasets across various driving and sensor attack scenarios. The results demonstrate that our proposed framework achieves 100% accuracy and 0% false alarm rate in various driving scenarios for attack detection within 0.15 s, with a recovery time of 0.08 s.

Data tampering detection and recovery scheme based on multi-branch target extraction for internet of vehicles

With the rapid development of new networks such as 5 G/6 G, the Internet of Vehicles has been given features such as hyper-connectivity and hyper-intelligence, promoting the implementation of new scenarios for autonomous vehicles. However, on the Internet of vehicles, vehicles use many cameras, radars and other sensors to sense the environment and execute instructions, facing security issues such as road data tampering and hijacking. Consequently, this paper presents a data tampering detection and recovery scheme based on multi-branch target extraction. Specifically, for road images collected by sensors, this paper presents a target extraction method based on multi-branch spatial feature pyramid blocks to obtain road salient targets. Then, a tamper detection and recovery algorithm based on interval mapping is presented. Once the image road target is tampered with, this method can quickly detect the tampering traces and restore them to achieve the authenticity and integrity of the road image on the Internet of Vehicles. The availability of the proposed scheme is verified through comparative experiments, and the performance is improved satisfactorily compared with other works.

Generalization of cut-in pre-crash scenarios for autonomous vehicles based on accident data

The utilization of high-risk test cases constitutes an effective approach to enhance the safety testing of autonomous vehicles (AVs) and enhance their efficiency. This research paper presents a derivation of 2052 high-hazard pre-crash scenarios for testing autonomous driving, which were based on 23 high-hazard cut-in accident scenarios from the National Automobile Accident In-Depth Investigation System (NAIS) through combining importance sampling and combined testing methods. Compared to the direct combination of the original distribution after sampling, the proposed method has a 2.92 times higher crash rate of 69.32% for the test case set in this paper. It also has a 5.8 times higher rate of triggering Automatic Emergency Braking (AEB), improving hazardous scenario coverage. Using the proposed method, the generated parameters of the cut-in accident scenario test set were compared with those of the cut-in test scenarios included in existing Chinese autonomous driving test protocols and standards. The velocity of the ego-vehicle obtained using the proposed method matched those in the existing protocols, whereas the velocity, time gap, and time to collision of the target vehicle were significantly lower than those existing protocols indicating scenarios obtained from accident data can enrich the selection of testing scenarios for autonomous driving.

An Approach to Generating Scenarios for Autonomous Vehicles

An Approach to Generating Scenarios for Autonomous Vehicles

A Precrash Scenario Analysis Comparing Safety Performance across Autonomous Vehicle Driving Modes

Precrash scenario analysis for autonomous vehicles (AVs) is critical for improving the safety of autonomous driving, yet the scenario differences between different driving modes are unexplored. Using the precrash scenario typology of the USDOT, this study classified 484 AV crash reports from the California DMV from 2018 to 2022, revealing the differences in the scenario proportions of the three modes of autonomous driving, driving takeover, and conventional driving in 34 types of scenarios. The results showed that there were significant differences in the proportion of six scenarios such as “Lead AV stopped” and “Lead AV decelerating” among different driving modes p<0.05. To analyze the relative risk of different driving modes in specific scenarios, an evaluation model of the risk level of AV precrash scenarios was established using the analytic hierarchy process (AHP). The findings indicated that ​ autonomous driving has the highest risk rating and poses the greatest danger in Scenario 1, while conventional driving is associated with Scenario 2b, and driving takeover corresponds to Scenario 3, respectively. In-depth analysis of the crash characteristics and causes of these three typical scenarios was conducted, and suggestions were made from the perspectives of autonomous driving system (ADS) and drivers to reduce the severity of crashes. This study compared precrash scenarios of AV by different driving modes, providing references for the optimization of ADS and the safety of human-machine codriving.

Research on multitask model of object detection and road segmentation in unstructured road scenes

With the rapid development of artificial intelligence and computer vision technology, autonomous driving technology has become a hot area of concern. The driving scenarios of autonomous vehicles can be divided into structured scenarios and unstructured scenarios. Compared with structured scenes, unstructured road scenes lack the constraints of lane lines and traffic rules, and the safety awareness of traffic participants is weaker. Therefore, there are new and higher requirements for the environment perception tasks of autonomous vehicles in unstructured road scenes. The current research rarely integrates the target detection and road segmentation to achieve the simultaneous processing of target detection and road segmentation of autonomous vehicle in unstructured road scenes. Aiming at the above issues, a multitask model for object detection and road segmentation in unstructured road scenes is proposed. Through the sharing and fusion of the object detection model and road segmentation model, multitask model can complete the tasks of multi-object detection and road segmentation in unstructured road scenes while inputting a picture. Firstly, MobileNetV2 is used to replace the backbone network of YOLOv5, and multi-scale feature fusion is used to realize the information exchange layer between different features. Subsequently, a road segmentation model was designed based on the DeepLabV3+ algorithm. Its main feature is that it uses MobileNetV2 as the backbone network and combines the binary classification focus loss function for network optimization. Then, we fused the object detection algorithm and road segmentation algorithm based on the shared MobileNetV2 network to obtain a multitask model and trained it on both the public dataset and the self-built dataset NJFU. The training results demonstrate that the multitask model significantly enhances the algorithm’s execution speed by approximately 10 frames per scond while maintaining the accuracy of object detection and road segmentation. Finally, we conducted validation of the multitask model on an actual vehicle.

Autonomous High-Speed Overtaking of Intelligent Chassis Using Fast Iterative Model Predictive Control

High-speed overtaking is one of the structured driving scenarios of autonomous vehicles (AVs), and safety and real-time control requirements must be fulfilled during this scenario. In this work, we develop an overtaking path-planning and tracking framework for AVs based on the improved artificial potential field (APF) and fast iterative model predictive control (MPC). The improved APF is used to plan a feasible, high-speed overtaking path by considering the constraints of vehicle dynamics and introducing the adjustment factor into the potential function to avoid local optimization and target unreachability problems. In addition, to reduce the computational burden and fulfill the real-time control requirements of trajectory tracking, a fast iterative MPC algorithm is proposed herein. This algorithm adds disturbances that possess the nonlinear characteristics of the real model by using a linearized model. In terms of vehicle configuration, we consider that the target vehicle has the four-wheel steer (4WS)-four-wheel drive (4WD) chassis configuration and the fast iterative MPC is also used to coordinate the conflict between 4WS and direct yaw moment control (DYC) to improve tracking accuracy and vehicle stability during overtaking. Simulink/Carsim co-simulation and hardware-in-the-loop (HIL) tests are conducted to verify the effectiveness of the proposed controller.

Identifying and Explaining Safety-critical Scenarios for Autonomous Vehicles via Key Features

Ensuring the safety of autonomous vehicles (AVs) is of utmost importance, and testing them in simulated environments is a safer option than conducting in-field operational tests. However, generating an exhaustive test suite to identify critical test scenarios is computationally expensive as the representation of each test is complex and contains various dynamic and static features, such as the AV under test, road participants (vehicles, pedestrians, and static obstacles), environmental factors (weather and light), and the road’s structural features (lanes, turns, road speed, etc.). In this paper, we present a systematic technique that uses Instance Space Analysis (ISA) to identify the significant features of test scenarios that affect their ability to reveal the unsafe behaviour of AVs. ISA identifies the features that best differentiate safety-critical scenarios from normal driving and visualises the impact of these features on test scenario outcomes (safe/unsafe) in 2 D . This visualisation helps to identify untested regions of the instance space and provides an indicator of the quality of the test suite in terms of the percentage of feature space covered by testing. To test the predictive ability of the identified features, we train five Machine Learning classifiers to classify test scenarios as safe or unsafe. The high precision, recall, and F1 scores indicate that our proposed approach is effective in predicting the outcome of a test scenario without executing it and can be used for test generation, selection, and prioritisation.

What can be done with today’s budget and demand? Scenarios of rural public transport automation in Mühlwald (South Tyrol)

Rural public transport is typically limited in its coverage, frequency and service period. This is often linked to a low and dispersed demand, which makes the provision of competitive transport services often financially unsustainable. Autonomous vehicles (AVs) might change this condition, allowing for an upgrade of public transport in rural areas. Nevertheless, current studies are mostly focused on urban areas, while the potential for rural applications remains underexplored. This paper contributes to this research line by developing a set of so-called AV scenarios for a potential upgrade of public transport in the rural study area of Mühlwald (South Tyrol, Italy). These scenarios are designed following three core principles. First, line-based and on-demand applications of AVs are not only individually tested, but even combined over space and time in different manners to exploit their synergy. Second, the performances of the scenarios are quantified by assuming the today´s agency cost budget, public-transport demand and peak-hour system capacity to be fixed parameters to comply with. Third, the uncertainties regarding the impacts of AVs on the agency costs are taken into account by defining optimistic, neutral and pessimistic variants of each scenario. Results indicate that the full replacement of current bus lines with a system of on-demand shared taxis might provide the highest performance improvements with the same budget as today, but only with a much bigger fleet. At the same time, the combination of bus lines and on-demand services over time (and space) might provide similarly competitive results while keeping the needed fleet size, service distance and service time relatively low. With this study, policy makers may get insights into the potential improvements of rural public transport that might be initially obtained with different uses of AVs, given a fixed agency cost budget and demand.

Analysis of pre-crash scenarios and contributing factors for autonomous vehicle crashes at intersections

Intersections are high-risk locations for autonomous vehicles (AVs). Crash causation analysis based on pre-crash scenarios can provide new insight into these crashes that can lead to effective countermeasures, but there are significant differences in pre-crash scenarios between autonomous and conventional vehicles, and inadequate AV data has put limits on research. The association rule method, however, can yield useful results despite these limits. This study therefore aims to use the method with pre-crash scenarios to understand the characteristics and contributing factors of AV crashes at intersections from the latest 5-year AV crash data. Analysis of 197 AV crashes at intersections revealed 30 types of pre-crash scenarios. The rear-end crash (58.88%) and lane change crash (16.24%) were the most frequently occurring scenarios for AVs. The proportion of AVs being rear-ended by conventional vehicles was 58.38%. The main contributing factors of these two most common AV scenarios were identified by association rules and crash causes were analyzed from the perspective of AV decision-making. The main factors contributing to the AV rear-end scenario were location outside the intersection in the intersection-related area, traffic signal control, autonomous engaged mode, mixed-use or public land, and weekdays, while those for lane change scenarios were on-street parking and the time of 8:00 a.m. Important causes of rear-end crashes attributable to the AV were inadequate stop and deceleration decisions by the AV’s automated driving system (ADS) and insufficient collision avoidance decisions in lane change crashes. Identification of the pre-crash characteristics and contributing factors provide new insight into AV crash causation and can be used in the determination of the AV’s operational design domain and the development and optimization of the AV’s ADS at intersections. These findings can also play a role in guiding traffic safety agencies to discover AV hotspots and propose AV management regulations.

Decision-Making in Fallback Scenarios for Autonomous Vehicles: Deep Reinforcement Learning Approach

This paper proposes a decision-making algorithm based on deep reinforcement learning to support fallback techniques in autonomous vehicles. The fallback technique attempts to mitigate or escape risky driving conditions by responding to appropriate avoidance maneuvers essential for achieving a Level 4+ autonomous driving system. However, developing a fallback technique is difficult because of the innumerable fallback situations to address and eligible optimal decision-making among multiple maneuvers. We employed a decision-making algorithm utilizing a scenario-based learning approach to address these issues. First, we crafted a specific fallback scenario encompassing the challenges to be addressed and matched the anticipated optimal maneuvers as determined by heuristic methods. In this scenario, the ego vehicle learns through trial and error to determine the most effective maneuver. We conducted 100 independent training sessions to evaluate the proposed algorithm and compared the results with those of heuristic-derived maneuvers. The results were promising; 38% of the training sessions resulted in the vehicle learning lane-change maneuvers, whereas 9% mastered slow following. Thus, the proposed algorithm successfully learned human-equivalent fallback capabilities from scratch within the provided scenario.

Personalized Driving Styles in Safety-Critical Scenarios for Autonomous Vehicles: An Approach Using Driver-in-the-Loop Simulations

This paper explores the use of driver-in-the-loop simulations to detect personalized driving styles in autonomous vehicles. The driving simulator used in this study is modular and adaptable, allowing for the testing and validation of control and data-collecting systems, as well as the incorporation and proof of car models. The selected scenario is a double lane change maneuver to overtake a stationary obstacle at a relatively high speed. The user’s behavior was recorded, and lateral accelerations during the maneuver were used as criteria to compare the user-driven vehicle and the autonomous one. The tuning parameters of the lateral and longitudinal controllers were modified to obtain different lateral accelerations of the autonomous vehicle. A neural network was developed to find the combination of the two controllers’ tuning parameters to match the driver’s lateral accelerations in the same double lane change overtaking action. The results are promising, and this study suggests that driver-in-the-loop simulations can help increase autonomous vehicles’ safety while preserving individual driving styles. This could result in creating more individualized and secure autonomous driving systems that consider the preferences and behavior of the driver.

Research on Lane-Change Decision and Planning in Multilane Expressway Scenarios for Autonomous Vehicles

Taking into account the issues faced by self-driving vehicles in multilane expressway scenarios, a lane-change decision planning framework that considers two adjacent lanes is proposed. Based on this framework, the lateral stability of an autonomous vehicle under near-limit conditions during lane change is studied by the phase-plane method. Firstly, a state-machine-based driving logic is designed and a decision method is proposed to design the lane-change intention based on the surrounding traffic information and to consider the influence of the motion state of other vehicles in the adjacent lanes on the self-driving vehicle. In order to realize adaptive cruising under the full working conditions of the vehicle, a safety distance model is established for different driving speeds and switching strategies for fixed-speed cruising, following driving, and emergency braking are developed. Secondly, for the trajectory planning problem, a lane-change trajectory based on a quintuple polynomial optimization method is proposed. Then, the vehicle lateral stability boundary is investigated; the stability boundary and rollover boundary are incorporated into the designed path-tracking controller to improve the tracking accuracy while enhancing the rollover prevention capability. Finally, a simulation analysis is carried out through a joint simulation platform; the simulation results show that the proposed method can ensure the driving safety of autonomous vehicles in a multilane scenario.

THE REPRESENTATION-USAGE-IMPACT (RUI) METHOD TO BETTER FRAME THE POTENTIAL SOCIAL IMPACTS OF A HIGHLY DISRUPTIVE PRODUCT—APPLICATION TO THE AUTONOMOUS VEHICLE

AbstractInnovative products can be highly prospective and apt to disrupt usages profoundly. They can lead to multiple long-term social impacts influencing people's way of life and behaviour. So it is necessary to anticipate them without delay. Due to high uncertainty, designers may face the problem that conventional user-centred methods, which assess design performances from today's users, are not adapted. We think sociologists can help characterise the likely social impacts of future products. So we propose an original framework called the Representation-Usage-Impact (RUI) method to stimulate sociologists' projection and capture relevant knowledge about probable social impacts. The method includes a database structure encoding the knowledge of sociologists for further use in the design process. Its goal is to help designers avoid making choices today that may be regretted in decades. We illustrate the method and its process with the design of autonomous vehicle scenarios, as it will likely bring many new usages in the future. As the method is still under construction, we present an intermediate validation step involving sociologists. The first results suggest that the method might be a safeguard for the design of disruptive products.

Leveraging Autonomous Vehicles to Tally Cooperative Driving Behavior

The number of Autonomous Vehicles (AVs) coexisting with conventional human-driven vehicles is expected to increase significantly in the coming years. This coexistence will last decades before full AV adoption is achieved worldwide. However, the cautious nature of AVs and the aggressive behavior of some human drivers could create unprecedentedly challenging scenarios for AVs, such as being stuck on merge lanes and blocked by human-driven vehicles. On the other hand, the cooperative behavior of other human drivers could assist AVs in avoiding deadlock situations. In this paper, we propose to leverage AVs to tally the cooperative driving behavior of human-driven vehicles. To this end, we model cooperative driving behavior in a “highway merge” scenario, which tends to be challenging for AVs. We vary the percentage of cooperative human-driven vehicles and estimate the percentage of AVs required to tally cooperative acts. Results show that when fifty percent of the human drivers cooperate, cooperation leads to statistically significant reductions of up to 68%, 46%, 38%, and 5% in stop delay, number of stops, vehicle delay, and travel time, respectively. Finally, we demonstrate that a 30% penetration of AVs is sufficient to tally up to 78% of cooperative behavior in highway scenarios. To promote cooperation across the population, our future work revolves around the construction of vehicular profiles based on their cooperative behavior. These profiles will be regularly updated and disseminated among AVs to aid their cooperative decisions toward human-driven vehicles in the upcoming interactions.

Research on the Safety Characteristics of Mixed Traffic Flow under Different Penetration Scenarios of Autonomous Vehicles

Research on the Safety Characteristics of Mixed Traffic Flow under Different Penetration Scenarios of Autonomous Vehicles

Edge AIBench 2.0: A scalable autonomous vehicle benchmark for IoT–Edge–Cloud systems

Many emerging IoT–Edge–Cloud computing systems are not yet implemented or are too confidential to share the code or even tricky to replicate its execution environment, and hence their benchmarking is very challenging. This paper uses autonomous vehicles as a typical scenario to build the first benchmark for IoT–Edge–Cloud systems. We propose a set of distilling rules for replicating autonomous vehicle scenarios to extract critical tasks with intertwined interactions. The essential system-level and component-level characteristics are captured while the system complexity is reduced significantly so that users can quickly evaluate and pinpoint the system and component bottlenecks. Also, we implement a scalable architecture through which users can assess the systems with different sizes of workloads.We conduct several experiments to measure the performance. After testing two thousand autonomous vehicle task requests, we identify the bottleneck modules in autonomous vehicle scenarios and analyze their hotspot functions. The experiment results show that the lane-keeping task is the slowest execution module, with a tail latency of 77.49 ms for the 99th percentile latency. We hope this scenario benchmark will be helpful for Autonomous Vehicles and even IoT–edge–Cloud research. Now the open-source code is available from the official website https://www.benchcouncil.org/scenariobench/edgeaibench.html.

Research Scenarios of Autonomous Vehicles, the Sensors and Measurement Systems Used in Experiments.

Automated and autonomous vehicles are in an intensive development phase. It is a phase that requires a lot of modelling and experimental research. Experimental research into these vehicles is in its initial state. There is a lack of findings and standardized recommendations for the organization and creation of research scenarios. There are also many difficulties in creating research scenarios. The main difficulties are the large number of systems for simultaneous checking. Additionally, the vehicles have a very complicated structure. A review of current publications allowed for systematization of the research scenarios of vehicles and their components as well as the measurement systems used. These include perception systems, automated response to threats, and critical situations in the area of road safety. The scenarios analyzed ensure that the planned research tasks can be carried out, including the investigation of systems that enable autonomous driving. This study uses passenger cars equipped with highly sophisticated sensor systems and localization devices. Perception systems are the necessary equipment during the conducted study. They provide recognition of the environment, mainly through vision sensors (cameras) and lidars. The research tasks include autonomous driving along a detected road lane on a curvilinear track. The effective maintenance of the vehicle in this lane is assessed. The location used in the study is a set of specialized research tracks on which stationary or moving obstacles are often placed.

Development of Risk-Situation Scenario for Autonomous Vehicles on Expressway Using Topic Modeling

Growing interest has recently been paid to the development of autonomous vehicle scenarios, and corresponding research is being conducted on various methodologies and on the generation of scenarios including technological elements. However, most studies have focused on frequently-occurring accident types or representative accident situations; thus, there is a lack of studies on scenarios considering unpredictable accidents. Proper preparation is required for accident situations because even a small traffic accident that is less likely to occur can lead to fatalities if it is difficult to predict. Accordingly, this study established accident situations based on the Pegasus layer model by using unstructured text data to explain traffic accidents on expressways in Korea. The established accident situations were classified into three types (Typical Traffic/Critical Traffic/Edge Case) according to frequency. Topic modeling was applied to the Edge Case class, i.e., the least likely to occur and thus difficult to predict, to analyze the characteristics of groups and develop risk-situation scenarios for autonomous vehicles based on actual accident data.