Autonomous Vehicle Simulation Research Articles

Human‐Like Interactive Behavior Generation for Autonomous Vehicles: A Bayesian Game‐Theoretic Approach with Turing Test

Interacting with surrounding road users is a key feature of autonomous vehicles and is critical for their intelligence testing. Existing interaction modalities in autonomous vehicle simulation and testing are not sufficiently smart, and they barely reflect human‐like behaviors in real‐world driving scenarios. Therefore, a novel hierarchical game‐theoretical framework is presented to represent naturalistic multimodal interactions among road users during simulation and testing, which is subsequently validated by the Turing test. Given that human drivers have no access to the complete information of the surrounding road users, the Bayesian game theory is used to model the decision‐making process. Next, a probing behavior is generated by the proposed game‐theoretic model, and is further applied to control the vehicle via the Markov chain. The proposed method is tested through a series of experiments and compared with existing approaches. In addition, Turing tests are conducted to quantify the human‐likeness of the proposed algorithm. The experimental results show that the proposed Bayesian game‐theoretic framework can effectively generate representative scenes of human‐like decision‐making during autonomous vehicle interactions, demonstrating its feasibility and effectiveness. An interactive preprint version of the article can be found at: https://www.authorea.com/doi/full/10.22541/au.163482630.00283278.

Evaluating Tradeoffs for Swarm Reconnaissance With Autonomous Ground Vehicles

AbstractAutonomous ground vehicles (AGVs) operating collaboratively have several advantages over vehicles operating alone. An AGV team may be more resilient and efficient than a single AGV. Other advantages of AGV teams include increased coverage and multiple viewing angles of terrain features as well as resistance to failure from any single AGV. Additionally, AGV teams can explore large terrains more quickly and thoroughly than a single system. In this work, the feasibility of using a team of high-mobility AGV to explore a navigation corridor, map the terrain, and autonomously flag obstacles for future navigation is evaluated. Focusing on negative obstacles, the value of using multiple vehicles to map a navigation corridor is quantified. This study is the first to evaluate large teams of AGV collaborating in realistic off-road, 3D environments. The feasibility of the large-scale AGV team is demonstrated while avoiding the high cost of purchasing and testing large numbers of vehicles using the Mississippi State University autonomous vehicle simulator (MAVS), a high-fidelity, physics-based simulation tool. The cost and benefits of increasing the AGV team size are evaluated. The simulation results show how factors like fuel use, map coverage, and obstacle detection are influenced by increasing numbers of AGV in the team. The simulation architecture is presented and experiments quantifying the performance of the simulator are shown. Finally, a model for evaluating the tradeoff between mission effectiveness and fuel use is developed and presented to demonstrate the utility of this approach.

Modeling Cameras for Autonomous Vehicle and Robot Simulation: An Overview

Simulation is increasingly important in the development and testing of robots and autonomous vehicles as it opens the door for candidate navigation, perception, and sensor fusion algorithms to be expeditiously probed in complex and safety-critical scenarios. As most robots and autonomous vehicles make heavy use of cameras to perceive their surroundings, camera modeling becomes a prerequisite for the successful simulation of these autonomous agents. This contribution outlines the context in which camera models are used; provides a component-by-component analysis of the image acquisition pipeline along with algorithms used for its modeling; and closes with a discussion of data-driven approaches that embrace a different perspective on camera modeling.

Advanced Double Layered Multi-Agent Systems Based on A3C in Real-Time Path Planning

In this paper, we propose an advanced double layered multi-agent system to reduce learning time, expressing a state space using a 2D grid. This system is based on asynchronous advantage actor-critic systems (A3C) and reduces the state space that agents need to consider by hierarchically expressing a 2D grid space and determining actions. Specifically, the state space is expressed in the upper and lower layers. Based on the learning results using A3C in the lower layer, the upper layer makes decisions without additional learning, and accordingly, the total learning time can be reduced. Our method was verified experimentally using a virtual autonomous surface vehicle simulator. It reduced the learning time required to reach a 90% goal achievement rate by 7.1% compared to the conventional double layered A3C. In addition, the goal achievement by the proposed method was 18.86% higher than that of the traditional double layered A3C over 20,000 learning episodes.

Virtualization of Self-Driving Algorithms by Interoperating Embedded Controllers on a Game Engine for a Digital Twining Autonomous Vehicle

Computer simulation based on digital twin is an essential process when designing self-driving cars. However, designing a simulation program that is exactly equivalent to real phenomena can be arduous and cost-ineffective because too many things must be implemented. In this paper, we propose the method using the online game GTA5 (Grand Theft Auto5), as a groundwork for autonomous vehicle simulation. As GTA5 has a variety of well-implemented objects, people, and roads, it can be considered a suitable tool for simulation. By using OpenCV (Open source computer vision) to capture the GTA5 game screen and analyzing images with YOLO (You Only Look Once) and TensorFlow based on Python, we can build a quite accurate object recognition system. This can lead to writing of algorithms for object avoidance and lane recognition. Once these algorithms have been completed, vehicles in GTA5 can be controlled through codes composed of the basic functions of autonomous driving, such as collision avoidance and lane-departure prevention. In addition, the algorithm tested with GTA5 has been implemented with a programmable RC car (Radio control car), DonkeyCar, to increase reliability. By testing those algorithms, we can ensure that the algorithms can be conducted in real time and they cost low power and low memory size. Therefore, we have found a way to approach digital twin technology one step more easily.

Safety Assessment and Simulation of Autonomous Vehicle in Urban Environments

The Autonomous Vehicle (AV) industry aims to design strategic plans to ensure the safety of the developed systems before their mass deployment. Real-road testing is shown to be impractical for validating these systems as it requires many years if not decades of testing in different environmental conditions. Therefore, this method must be complemented with simulation for a feasible solution. The primary goal of this research is to develop advanced techniques in the safety validation area by using immersive simulation technologies. This study led to a simulation approach for safety evaluation of an AV shuttle, ise Auto, currently operating at the TalTech campus. First, we create a virtual environment based on the specified path on the university campus including all relevant features. The environment is created by using geospatial data which is collected by a drone, then they are converted to a 3D map applicable for the LGSVL simulator. Next, the developed shuttle 3D model is imported to the simulation environment and with the aim of the LGSVL, sensor data are provided for the Autoware perception algorithms, which is the control software of the shuttle. This system enables us to evaluate AV’s decision-making performance and safety in different situations.

Co-Design of Fault Detection and Consensus Control Protocol for Multi-Agent Systems Under Hidden DoS Attack

This article is concerned with the co-design of fault detection and consensus control protocol for a class of multi-agent systems (MASs) subject to Denial-of-Service attack, where the attack behavior is hidden to the defender as the adversary may launch the attack with different durations but the defender may not know the real situation at each time instant. Due to the complicated attack behavior, a hidden semi-Markov process is introduced where only the observed attack modes emitted by the inaccessible ones are available. The probability density functions of sojourn time and the semi-Markov kernel are adopted to help analyze the combined fault detection and consensus control system. Sufficient conditions on the σ-error mean square stability of MASs with mixed H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> /H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-</sub> performance are established by using a set of Lyapunov functions that depend on the hidden and the observed attack modes. Moreover, the gain matrices of controller and detector are obtained by solving an optimization problem with some matrix inequality constraints. Finally, the simulation of autonomous unmanned underwater vehicles is used to show the effectiveness of the proposed results.

Trace-Length Independent Runtime Monitoring of Quantitative Policies

Metric linear-time logic (MTL) has been widely used to specify runtime policies. Traditionally this use of MTL is to capture the qualitative aspects of the monitored systems, but recent developments in its extensions with aggregate operators allow some quantitative policies to be specified. Our interest in MTL-based policy languages is driven by applications in runtime malware or intrusion detection in platforms like Android and autonomous vehicles, which requires the monitoring algorithm to be independent of the length of the system event traces so that its performance does not degrade as the traces grow. We propose a policy language based on a past-time variant of MTL, extended with an aggregate operator called the metric temporal counting quantifier to specify a policy based on the number of times some sub-policies are satisfied in the specified past time interval. We show that a broad class of policies, but not all policies, specified with our language can be monitored in a trace-length independent way, and provide a concrete algorithm to do so. We implement and test our algorithm in both an existing Android monitoring framework and an autonomous vehicle simulation platform, and show that our approach can effectively specify and monitor quantitative policies drawn from real-world studies.

On-road virtual reality autonomous vehicle (VRAV) simulator: An empirical study on user experience

Autonomous-vehicle (AV) technologies are rapidly advancing, but a great deal remains to be learned about their interaction and perception on public roads. Research in this area usually relies on AV trials using naturalistic driving which are expensive with various legal and ethical obstacles designed to keep the general public safe. The emerging concept of Wizard-of-Oz simulation is a promising solution to this problem wherein the driver of a standard vehicle is hidden from the passenger using a physical partition, providing the illusion of riding in an AV. Furthermore, head-mounted display (HMD) virtual reality (VR) has been proposed as a means of providing a Wizard-of-Oz protocol for on-road simulations of AVs. Such systems have potential to support a variety of study conditions at low cost, enabling simulation of a variety of vehicles, driving conditions, and circumstances. However, the feasibility of such systems has yet to be shown. This study makes use of a within-subjects factorial design for examining and evaluating a virtual reality autonomous vehicle (VRAV) system, with the aim of better understanding the differences between stationary and on-road simulations, both with and without HMD VR. More specifically, this study examines the effects on user experience of conditions including presence, arousal, simulator sickness and task workload. Participants indicated a realistic and immersive driving experience as part of subjective evaluation of the VRAV system, indicating the system is a promising tool for human-automation interaction and future AV technology developments.

Investigating user activities and the corresponding requirements for information and functions in autonomous vehicles of the future

The potential benefits of autonomous vehicles, including safety, convenience, fuel economy, and low emissions can only be achieved when consumers are comfortable with the vehicle design. There are only a limited number of user studies in the design of future autonomous vehicles, owing to the difficulties of shifting focus “from the present to the future.” An integrated method of simulator study and user enactment was applied in the research to bridge the gap between the current and the future. Thirty drivers participated in the study to experience enacted driving scenarios in an autonomous vehicle simulator. The participants were divided into two groups, i.e., driving-alone drivers and driving-with-a-passenger drivers, to investigate the effect of passenger presence. Rich data were elicited about possible in-vehicle activities, the corresponding requirements of information and functions to support any such activities. Also identified were the preferred methods of interacting with the information and functions. Passenger presence was found to have an influence on the attributes of activities undertaken as well as the preferences for in-vehicle information and functions. Dominant themes were identified in future autonomous vehicle designs, including a more flexible and adaptive design language, concerns of trust and safety, and trade-offs between safety and convenience and between privacy and social connection. Based on the findings, design implications for future autonomous vehicles are discussed.

Integrating Supply and Demand Perspectives for a Large-Scale Simulation of Shared Autonomous Vehicles

Transportation Network Companies (TNCs) have been steadily increasing the share of total trips in metropolitan areas across the world. Micro-modeling TNC operation is essential for large-scale transportation systems simulation. In this study, an agent-based approach for analyzing supply and demand aspects of ride-sourcing operation is done using POLARIS, a high-performance simulation tool. On the demand side, a mode-choice model for the agent and a vehicle-ownership model that informs this choice are developed. On the supply side, TNC vehicle-assignment strategies, pick-up and drop-off operations, and vehicle repositioning are modeled with congestion feedback, an outcome of the mesoscopic traffic simulation. Two case studies of Bloomington and Chicago in Illinois are used to study the framework’s computational speed for large-scale operations and the effect of TNC fleets on a region’s congestion patterns. Simulation results show that a zone-based vehicle-assignment strategy scales better than relying on matching closest vehicles to requests. For large regions like Chicago, large fleets are seen to be detrimental to congestion, especially in a future in which more travelers will use TNCs. From an operational point of view, an efficient relocation strategy is critical for large regions with concentrated demand, but not regulating repositioning can worsen empty travel and, consequently, congestion. The TNC simulation framework developed in this study is of special interest to cities and regions, since it can be used to model both demand and supply aspects for large regions at scale, and in reasonably low computational time.

LiDAR Data Segmentation in Off-Road Environment Using Convolutional Neural Networks (CNN)

&lt;div class="section abstract"&gt;&lt;div class="htmlview paragraph"&gt;Recent developments in the area of autonomous vehicle navigation have emphasized algorithm development for the characterization of LiDAR 3D point-cloud data. The LiDAR sensor data provides a detailed understanding of the environment surrounding the vehicle for safe navigation. However, LiDAR point cloud datasets need point-level labels which require a significant amount of annotation effort. We present a framework which generates simulated labeled point cloud data. The simulated LiDAR data was generated by a physics-based platform, the Mississippi State University Autonomous Vehicle Simulator (MAVS). In this work, we use the simulation framework and labeled LiDAR data to develop and test algorithms for autonomous ground vehicle off-road navigation. The MAVS framework generates 3D point clouds for off-road environments that include trails and trees. The important first step in off-road autonomous navigation is the accurate segmentation of 3D point cloud data to identify the potential obstacles in the vehicle path. We use simulated LiDAR data to segment and detect obstacles using convolutional neural networks (CNN). Our analysis is based on SqueezeSeg, a CNN-based model for point cloud segmentation. The CNN was trained with a labelled dataset of off-road imagery generated by MAVS and evaluated on the simulated dataset. The segmentation of the LiDAR data is done by point-wise classification and the results show excellent accuracy in identifying different objects and obstacles in the vehicle path. In this paper, we evaluated the segmentation performance at different LiDAR vertical resolutions: the 8-beam and 16-beam. The results showed that there is about 5% increase in accuracy with 16-beam sensors compared with the 8-beam sensors in detecting obstacles and trees. However, the 8-beam LiDAR performance is comparable with the 16-beam sensor in segmenting vegetation, trail-road and ground.&lt;/div&gt;&lt;/div&gt;

Agent-Based Simulation of Autonomous Vehicles: A Systematic Literature Review

Autonomous vehicles (AVs) may have a transformative influence on transportation systems. AV use is expected to reduce crash, transport costs, and land use. However, the net effects of the autonomous vehicle are unknown because there are no fully-autonomous vehicles in reality. The simulation systems are indispensable to be built up not only for cost but also for obtaining massive data. An agent-based simulation is capable of simulating the entities in a complex system, such as the AV system. Considering the potential of agent-based models to complement existing models and the difficulty to understand, to duplicate and to compare different agent-based models, this paper review existing agent-based modeling of autonomous vehicles with the help of ODD protocol, which has been applied in the review of agent-based land-use change models and agricultural policy evaluation. The significant variables that researchers have taken into consideration in sensitivity analysis and in the different scenarios are explored in the paper. Fleet size is the primary variable researchers considered, and we also discussed the probable causes of different AV replacement rates. We have assessed the quality of reviewed articles to gain more acceptance from the agent-based modeling community. Most of the reviewed papers follow the ODD protocol of agent decision making. However, in order to improve the level of modeling transparency, the executable and related data shall be available, at least the data source and the programming language/simulation platform should be provided. Several recommendations for further research are also presented.

Shared autonomous vehicle simulation and service design

Today, driverless cars, as a new technology that allows a more accessible, dynamic and intelligent form of Shared Mobility, are expected to revolutionize urban transportation. One of the conceivable mobility services based on driverless cars is shared autonomous vehicles (SAVs). This service could merge cabs, carsharing, and ridesharing systems into a singular transportation mode. However, the success and competitiveness of future SAV services depend on their operational models, which are linked intrinsically to the service configuration and fleet specification. In addition, any change in operational models will result in a different demand. Using a comprehensive framework of SAV simulation in a multimodal dynamic demand system with integrated SAV user taste variation, this study evaluates the performance of various SAV fleets and vehicle capacities serving travelers across the Rouen Normandie metropolitan area in France. Also, the impact of ridesharing and rebalancing strategies on service performance is investigated.Research results suggest that the performance of SAV is strongly correlated with the fleet size and the strategy of individual or shared rides. Further analysis indicates that for the pricing scheme proposed in this study (i.e., 20% lower for ridesharing scenario), the standard 4-seats car with shared ride remains the best option among all scenarios. The results also underline that enabling vehicle-rebalancing strategies may have an important effect on both user and service-related metrics. The estimated SAV average and maximum driven distance prove the importance of vehicle range and charging station deployment.

High-Fidelity Autonomous Surface Vehicle Simulator for the Maritime RobotX Challenge

This paper presents a high-fidelity autonomous surface vehicle (ASV) and an above-water environment simulator developed for, and used by, the Queensland University of Technology (QUT) team at the 2016 Maritime RobotX Challenge. This simulator was developed to address a gap in an existing robotic marine vehicle simulation software by producing high-fidelity sensor data from a realistic operating environment and simulating ASV motion dynamics as a direct interface for hardware-in-the-loop simulation. The key functions required for the simulator to be an effective model of the QUT ASV included a high-fidelity camera, LiDAR (Velodyne HDL-32E), Inertial Measurement Unit (IMU), and GPS sensor simulation, as well as buoyancy and physics simulation for vehicle motion and control performance in a spatiotemporally varying modeled sea state. Another key feature of the simulator was the provision to directly interface the Robotic Operating System (ROS) to publish and subscribe to sensor topics (in real time) and allow hardware-in-the-loop simulation of the ASV systems for algorithm development. The fidelity and performance of the simulator was benchmarked against the existing best available alternative simulator, V-Rep, with results shown to demonstrate that the autonomous marine surface vessel simulator achieved improved computational performance and sensor fidelity when simulating above surface marine environments.

Rule‐based searching for collision test cases of autonomous vehicles simulation

Research and development in the field of autonomous vehicles has increased along with related work on automated driving (AD) software. Thorough testing of AD software using simulations must be conducted in advance of testing AD cars on the road. Parameters of the many objects around an AD car, such as other cars, traffic lanes and pedestrians are required as inputs of the simulation. Therefore, the number of parameter combinations becomes extremely large. A combination of parameters is called a test case; hence, the challenge is to search collision test cases from the extremely large number of combinations. A rule-based method is the main focus because an explicit method of searching test cases is required in certain industries in the real world. In this study, a method of rule-based searching for collision test cases of autonomous vehicles simulations is proposed. Simulation models that have rules between an AD car and other cars are defined. Algorithms were also developed to search collision test cases that generate test cases incrementally. Experiments on AD simulations involving the simulation models of a three-lane highway and a signalised intersection were conducted. The results indicate the efficiency of the method.

Intelligent autonomous vehicles in digital supply chains

PurposeThe purpose of this paper is twofold: first, to discuss key challenges associated with the use of either simulation or real-world application of intelligent autonomous vehicles (IAVs) in supply network operations; and second, to provide a theoretical and empirical evidence-based methodological framework that supports the integrated application of conceptualisation, simulation, emulation and physical application of IAVs for the effective design of digital supply networks.Design/methodology/approachFirst, this study performs a critical review of the extant literature to identify major benefits and shortcomings related to the use of either simulation modelling or real-word application of physical IAVs. Second, commercial and bespoke software applications, along with a three-dimensional validation and verification emulation tool, are developed to evaluate an IAV’s operations in a conceptual warehouse. Third, a commercial depth-sensor is used as a test bed in a physical setting.FindingsThe results demonstrate that conceptual and simulation modelling should be initially used to explore alternative supply chain operations in terms of ideal performance while emulation tools and real-world IAV test beds are eminent in validating preferred digital supply chain design options.Research limitations/implicationsThe provided analysis framework was developed using literature evidence along with experimental work and research experience, without consulting any industry experts. In addition, this study was developed based on the application of a single physical device application as a test bed and, thus, the authors should further progress with the testing of a physical IAV in an industrial warehouse.Practical implicationsThe study provides bespoke simulation modelling and emulation tools that can be useful for supply chain practitioners in effectively designing network operations.Originality/valueThis work contributes in the operations management field by providing both a multi-stage methodological framework and a practical “toolbox” for the proactive assessment and incorporation of IAVs in supply network operations.

Real time implementation of socially acceptable collision avoidance of a low speed autonomous shuttle using the elastic band method

This paper presents the real time implementation of socially acceptable collision avoidance using the elastic band method for low speed autonomous shuttles operating in high pedestrian density environments. The modeling and validation of the research autonomous vehicle used in the experimental implementation is presented first, followed by the details of the Hardware-In-the-Loop connected and autonomous vehicle simulator used. The socially acceptable collision avoidance algorithm is formulated using the elastic band method as an online, local path modification algorithm. Parameter space based robust feedback plus feedforward steering controller design is used. Model-in-the-loop, Hardware-In-the-Loop and road testing in a proving ground are used to demonstrate the effectiveness of the real time implementation of the elastic band based socially acceptable collision avoidance method of this paper.

Electrodermal Response and Automation Trust during Simulated Self-Driving Car Use

The integration of self-driving vehicles may expose individuals with health concerns to undue amounts of stress. Psychophysiological indicators of stress were used to determine changes in tonic and phasic stress levels brought about by a high-fidelity autonomous vehicle simulation. Twenty-eight participants completed one manual driving task and two automated driving tasks. Participants reported their subjective level of trust in the automated systems using the Automation Trust Survey. Psychophysiological stress was indexed using skin conductance and trapezius muscle tension. Results indicate that users show more signs of physiological stress when the vehicle drives autonomously than when the users is in control. Results also indicate that users show an additional increase in stress when the user reports low trust in the autonomous vehicle. These findings suggest that health-care professionals and manufactures should be aware of additional stress associated with self-driving technology.

Distributed Data Fusion for Multirobot Search

This paper presents novel data fusion methods that enable teams of vehicles to perform target search tasks without guaranteed communication. Techniques are introduced for merging estimates of a target's position from vehicles that regain contact after long periods of time, and a fully distributed team-planning algorithm is proposed, which utilizes limited shared information as it becomes available. The proposed data fusion techniques are shown to avoid overcounting information, which ensures that combining data from different vehicles will not decrease the performance of the search. Motivated by the underwater search domain, a realistic underwater acoustic communication channel is used to determine the probability of successful data transfer between two locations. The channel model is integrated into a simulation of multiple autonomous vehicles in both open water and harbor environments. The results demonstrate that the proposed distributed coordination techniques provide performance competitive with full communication.