scholarly journals Assessment of external interface of autonomous vehicles

2021 ◽  
Vol 61 (6) ◽  
pp. 733-739
Author(s):  
Adam Orlický ◽  
Alina Mashko ◽  
Josef Mík
Keyword(s):  
Decision Making ◽  
Traffic Safety ◽  
Autonomous Vehicles ◽  
Visual Cues ◽  
Autonomous Vehicle ◽  
Gaze Direction ◽  
Eye Tracker ◽  
Communication Interface ◽  
External Communication ◽  
External Interface

The paper deals with the problem of a communication interface between autonomous vehicles (AV) and pedestrians. The introduced methodology for assessing new and existing e-HMI (external HMI) contributes to traffic safety in cities. The methodology is implemented in a pilot experiment with a scenario designed in virtual reality (VR). The simulated scene represents an urban zebra crossing with an approaching autonomous vehicle. The projection is implemented with the help of a head-up display – a headset with a built-in eye tracker. The suggested methodology analyses the pedestrian’s decision making based on the visual cues – the signals displayed on the autonomous vehicle. Furthermore, the decision making is correlated to subjects’ eye behaviour, based on gaze-direction data. The method presented in this paper contributes to the safety of a vehicle-pedestrian communication of autonomous vehicles and is a part of a research that shall further contribute to the design and assessment of external communication interfaces of AV in general.

scholarly journals A Game Theory-Based Approach for Modeling Autonomous Vehicle Behavior in Congested, Urban Lane-Changing Scenarios

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1523
Author(s):  
Nikita Smirnov ◽  
Yuzhou Liu ◽  
Aso Validi ◽  
Walter Morales-Alvarez ◽  
Cristina Olaverri-Monreal
Keyword(s):  
Game Theory ◽  
Decision Making ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Urban Traffic ◽  
Road User ◽  
Lane Change ◽  
Traffic Light ◽  
User Interactions ◽  
Lane Changing

Autonomous vehicles are expected to display human-like behavior, at least to the extent that their decisions can be intuitively understood by other road users. If this is not the case, the coexistence of manual and autonomous vehicles in a mixed environment might affect road user interactions negatively and might jeopardize road safety. To this end, it is highly important to design algorithms that are capable of analyzing human decision-making processes and of reproducing them. In this context, lane-change maneuvers have been studied extensively. However, not all potential scenarios have been considered, since most works have focused on highway rather than urban scenarios. We contribute to the field of research by investigating a particular urban traffic scenario in which an autonomous vehicle needs to determine the level of cooperation of the vehicles in the adjacent lane in order to proceed with a lane change. To this end, we present a game theory-based decision-making model for lane changing in congested urban intersections. The model takes as input driving-related parameters related to vehicles in the intersection before they come to a complete stop. We validated the model by relying on the Co-AutoSim simulator. We compared the prediction model outcomes with actual participant decisions, i.e., whether they allowed the autonomous vehicle to drive in front of them. The results are promising, with the prediction accuracy being 100% in all of the cases in which the participants allowed the lane change and 83.3% in the other cases. The false predictions were due to delays in resuming driving after the traffic light turned green.

scholarly journals Lane-deviation penalty formulation and analysis for autonomous vehicle avoidance maneuvers

2021 ◽  
pp. 095440702110079
Author(s):  
Pavel Anistratov ◽  
Björn Olofsson ◽  
Lars Nielsen
Keyword(s):  
Objective Function ◽  
Traffic Safety ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Emergency Situation ◽  
Change Scenario ◽  
Initial Speed ◽  
Objective Functions ◽  
Double Lane Change ◽  
Tire Friction

Autonomous vehicles hold promise for increased vehicle and traffic safety, and there are several developments in the field where one example is an avoidance maneuver. There it is dangerous for the vehicle to be in the opposing lane, but it is safe to drive in the original lane again after the obstacle. To capture this basic observation, a lane-deviation penalty (LDP) objective function is devised. Based on this objective function, a formulation is developed utilizing optimal all-wheel braking and steering at the limit of road–tire friction. This method is evaluated for a double lane-change scenario by computing the resulting behavior for several interesting cases, where parameters of the emergency situation such as the initial speed of the vehicle and the size and placement of the obstacle are varied, and it performs well. A comparison with maneuvers obtained by minimum-time and other lateral-penalty objective functions shows that the use of the considered penalty function decreases the time that the vehicle spends in the opposing lane.

scholarly journals Disruptive Impacts of Automated Driving Systems on the Built Environment and Land Use: An Urban Planner’s Perspective

2019 ◽  
Vol 5 (2) ◽  
pp. 24 ◽  
Author(s):  
Yigitcanlar ◽  
Wilson ◽  
Kamruzzaman
Keyword(s):  
Land Use ◽  
Built Environment ◽  
Traffic Safety ◽  
Autonomous Vehicles ◽  
Capital Investment ◽  
Smart Cities ◽  
Autonomous Vehicle ◽  
Urban Transport ◽  
Current Status ◽  
Smart Mobility

Cities have started to restructure themselves into ‘smart cities’ to address the challenges of the 21st Century—such as climate change, sustainable development, and digital disruption. One of the major obstacles to success for a smart city is to tackle the mobility and accessibility issues via ‘smart mobility’ solutions. At the verge of the age of smart urbanism, autonomous vehicle technology is seen as an opportunity to realize the smart mobility vision of cities. However, this innovative technological advancement is also speculated to bring a major disruption in urban transport, land use, employment, parking, car ownership, infrastructure design, capital investment decisions, sustainability, mobility, and traffic safety. Despite the potential threats, urban planners and managers are not yet prepared to develop autonomous vehicle strategies for cities to deal with these threats. This is mainly due to a lack of knowledge on the social implications of autonomous capabilities and how exactly they will disrupt our cities. This viewpoint provides a snapshot of the current status of vehicle automation, the direction in which the field is moving forward, the potential impacts of systematic adoption of autonomous vehicles, and how urban planners can mitigate the built environment and land use disruption of autonomous vehicles.

scholarly journals Quick Routing in Autonomous Vehicles using Boosting Algorithms

2019 ◽  
Vol 9 (1S3) ◽  
pp. 539-542
Keyword(s):  
Artificial Intelligence ◽  
Shortest Path ◽  
Traffic Safety ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Fuel Efficiency ◽  
Time Span ◽  
Minimum Time ◽  
Novel Technique ◽  
Boosting Algorithms

Self-driving automobiles are understandably the most attention grabbing utility of artificial intelligence. Until recently, we have just considered the prototypes of these cars in Sci-fi movies, with the whole thing else left to our imagination. But with advances in technology, this super notion has acquired a lifestyles of its own. Autonomous vehicle promises to improve traffic safety while at the same time, it must increase the fuel efficiency, reduce congestion and arrive to the destination at a minimum time span. We propose a novel technique to boost the algorithm to take the shortest path while the vehicle is in movement.

scholarly journals Human-like Interactive Behavior Generation for Autonomous Vehicles: A Bayesian Game-theoretic Approach with Turing Test

2021 ◽  
Author(s):  
Yiran Zhang ◽  
Peng Hang ◽  
Chao Huang ◽  
Chen Lv
Keyword(s):  
Decision Making ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Turing Test ◽  
Theoretic Model ◽  
Theoretic Approach ◽  
Bayesian Game ◽  
Vehicle Simulation ◽  
Road Users ◽  
Game Theoretic

Interacting with surrounding road users is a key feature of vehicles and is critical for intelligence testing of autonomous vehicles. The Existing interaction modalities in autonomous vehicle simulation and testing are not sufficiently smart and can hardly reflect human-like behaviors in real world driving scenarios. To further improve the technology, in this work we present a novel hierarchical game-theoretical framework to represent naturalistic multi-modal interactions among road users in simulation and testing, which is then 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 utilized to model the decision-making process. Then, a probing behavior is generated by the proposed game theoretic model, and is further applied to control the vehicle via Markov chain. To validate the feasibility and effectiveness, 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 experiment 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. Corresponding author(s) Email:   [email protected]  

Risk Analysis of Autonomous Vehicles in Mixed Traffic Streams

2017 ◽  
Vol 2625 (1) ◽  
pp. 51-61 ◽  
Author(s):  
Parth Bhavsar ◽  
Plaban Das ◽  
Matthew Paugh ◽  
Kakan Dey ◽  
Mashrur Chowdhury
Keyword(s):  
Traffic Safety ◽  
Failure Probability ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Fault Tree ◽  
Communication Technologies ◽  
Transportation Infrastructure ◽  
New Combination ◽  
Motor Vehicles ◽  
Mixed Traffic

The introduction of autonomous vehicles in the surface transportation system could improve traffic safety and reduce traffic congestion and negative environmental effects. Although the continuous evolution in computing, sensing, and communication technologies can improve the performance of autonomous vehicles, the new combination of autonomous automotive and electronic communication technologies will present new challenges, such as interaction with other nonautonomous vehicles, which must be addressed before implementation. The objective of this study was to identify the risks associated with the failure of an autonomous vehicle in mixed traffic streams. To identify the risks, the autonomous vehicle system was first disassembled into vehicular components and transportation infrastructure components, and then a fault tree model was developed for each system. The failure probabilities of each component were estimated by reviewing the published literature and publicly available data sources. This analysis resulted in a failure probability of about 14% resulting from a sequential failure of the autonomous vehicular components alone in the vehicle’s lifetime, particularly the components responsible for automation. After the failure probability of autonomous vehicle components was combined with the failure probability of transportation infrastructure components, an overall failure probability related to vehicular or infrastructure components was found: 158 per 1 million mi of travel. The most critical combination of events that could lead to failure of autonomous vehicles, known as minimal cut-sets, was also identified. Finally, the results of fault tree analysis were compared with real-world data available from the California Department of Motor Vehicles autonomous vehicle testing records.

Research on decision-making of autonomous vehicle following based on reinforcement learning method

2019 ◽  
Vol 46 (3) ◽  
pp. 444-452 ◽  
Author(s):  
Hongbo Gao ◽  
Guanya Shi ◽  
Kelong Wang ◽  
Guotao Xie ◽  
Yuchao Liu
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Learning System ◽  
Explicit Calculation ◽  
Gradient Descent Method ◽  
Learning Method ◽  
Content Type ◽  
Car Following

Purpose Over the past decades, there has been significant research effort dedicated to the development of autonomous vehicles. The decision-making system, which is responsible for driving safety, is one of the most important technologies for autonomous vehicles. The purpose of this study is the use of an intensive learning method combined with car-following data by a driving simulator to obtain an explanatory learning following algorithm and establish an anthropomorphic car-following model. Design/methodology/approach This paper proposed car-following method based on reinforcement learning for autonomous vehicles decision-making. An approximator is used to approximate the value function by determining state space, action space and state transition relationship. A gradient descent method is used to solve the parameter. Findings The effect of car-following on certain driving styles is initially achieved through the simulation of step conditions. The effect of car-following initially proves that the reinforcement learning system is more adaptive to car following and that it has certain explanatory and stability based on the explicit calculation of R. Originality/value The simulation results show that the car-following method based on reinforcement learning for autonomous vehicle decision-making realizes reliable car-following decision-making and has the advantages of simple sample, small amount of data, simple algorithm and good robustness.

Multi-Player Dynamic Game-Based Automatic Lane-Changing Decision Model under Mixed Autonomous Vehicle and Human-Driven Vehicle Environment

2020 ◽  
Vol 2674 (11) ◽  
pp. 165-183
Author(s):  
Yuewen Yu ◽  
Shikun Liu ◽  
Peter J. Jin ◽  
Xia Luo ◽  
Mengxue Wang
Keyword(s):  
Game Theory ◽  
Decision Making ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Splitting Method ◽  
Dynamic Game ◽  
Cruise Control ◽  
Lane Changing ◽  
Bicycle Model ◽  
Decision Making Model

The lane-changing decision-making process is challenging but critical to ensure safe and smooth maneuvers for autonomous vehicles (AVs). Conventional Gipps-type algorithms lack the flexibility for practical use under a mixed autonomous vehicle and human-driven vehicle (AV-HV) environment. Algorithms based on utility ignore the reactions of surrounding vehicles to the lane-changing vehicle. Game theory is a good way to solve the shortcomings of current algorithms, but most models based on game theory simplify the game with surrounding vehicles to the game with the following vehicle in the target lane, which means that the lane-changing decision under a mixed environment is not realized. This paper proposes a lane-changing decision-making model which is suitable for an AV to change lanes under a mixed environment based on a multi-player dynamic game theory. The overtaking expectation parameter (OEP) is introduced to estimate the utility of the following vehicle, OEP can be calculated by the proposed non-lane-based full velocity difference model with the consideration of lateral move and aggressiveness. This paper further proposes a hybrid splitting method algorithm to obtain the Nash equilibrium solution in the multi-player game to obtain the optimal strategy of lane-changing decision for AVs. An adaptive cruise control simulation environment is developed with MATLAB’s Simulink toolbox using Next Generation Simulation (NGSIM) data as the background traffic flow. The classic bicycle model is used in the control of involved HVs. Simulation results show the efficiency of the proposed multi-player dynamic game-based algorithm for lane-changing decision making by AVs under a mixed AV-HV environment.

scholarly journals Securing Personal Data using Block chain in Autonomous Vehicle

2019 ◽  
Vol 8 (4S2) ◽  
pp. 760-763
Keyword(s):  
Science Fiction ◽  
Traffic Safety ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Personal Data ◽  
Testing Stage ◽  
The World ◽  
Driverless Cars ◽  
Block Chain ◽  
Manufacturing Stage

Autonomous vehicles like Driverless cars are seen only in science fiction movies but in 2019 they are becoming a veracity and reality. People all around the world are excited to watch the driverless car in reality. Complete driverless car is still at an advanced testing stage. An autonomous vehicle promises to improve traffic safety while at the same time it must not be prone to hacking. Even though the existence of the autonomous car is in reality there is a possibility of hackers to hack the vehicle and retrieve the precious data. To stop this kind of hacking we propose a block chain technique that safe guards the data that is fed to the autonomous car during the manufacturing stage and this cannot be deleted without proper permission.

scholarly journals Intention-Aware Autonomous Driving Decision-Making in an Uncontrolled Intersection

2016 ◽  
Vol 2016 ◽  
pp. 1-15 ◽  
Author(s):  
Weilong Song ◽  
Guangming Xiong ◽  
Huiyan Chen
Keyword(s):  
Decision Making ◽  
Autonomous Vehicles ◽  
Driving Simulator ◽  
Autonomous Vehicle ◽  
Transition Process ◽  
Autonomous Driving ◽  
Driving Safety ◽  
Time Step ◽  
Reward Function ◽  
Pass Through

Autonomous vehicles need to perform social accepted behaviors in complex urban scenarios including human-driven vehicles with uncertain intentions. This leads to many difficult decision-making problems, such as deciding a lane change maneuver and generating policies to pass through intersections. In this paper, we propose an intention-aware decision-making algorithm to solve this challenging problem in an uncontrolled intersection scenario. In order to consider uncertain intentions, we first develop a continuous hidden Markov model to predict both the high-level motion intention (e.g., turn right, turn left, and go straight) and the low level interaction intentions (e.g., yield status for related vehicles). Then a partially observable Markov decision process (POMDP) is built to model the general decision-making framework. Due to the difficulty in solving POMDP, we use proper assumptions and approximations to simplify this problem. A human-like policy generation mechanism is used to generate the possible candidates. Human-driven vehicles’ future motion model is proposed to be applied in state transition process and the intention is updated during each prediction time step. The reward function, which considers the driving safety, traffic laws, time efficiency, and so forth, is designed to calculate the optimal policy. Finally, our method is evaluated in simulation with PreScan software and a driving simulator. The experiments show that our method could lead autonomous vehicle to pass through uncontrolled intersections safely and efficiently.

Sign in / Sign up

Export Citation Format

Share Document