Simulated Traffic Scenarios Research Articles

A Division-of-Labour Approach to Traffic Light Scheduling

Traffic light scheduling is a critical aspect of traffic management with many recently developed solutions that incorporate computational intelligence approaches. This paper presents a traffic light scheduling algorithm based on a task allocation model that simulates the division of labour among insects in a colony, specifically ant colonies. The developed algorithm switches the green light based on a probability calculated every second from the traffic volume around the traffic light. The application of this algorithm to several benchmark simulated traffic scenarios shows optimal performance compared to five other traffic scheduling algorithms.

An entropy‐based model for quantifying multi‐dimensional traffic scenario complexity

AbstractQuantifying the complexity of traffic scenarios not only provides an essential foundation for constructing the scenarios used in autonomous vehicle training and testing, but also enhances the robustness of the resulting driving decisions and planning operations. However, currently available quantification methods suffer from inaccuracies and coarse‐granularity in complexity measurements due to issues such as insufficient specificity or indirect quantification. The present work addresses these challenges by proposing a comprehensive entropy‐based model for quantifying traffic scenario complexity across multiple dimensions based on a consideration of the essential components of the traffic environment, including traffic participants, static elements, and dynamic elements. In addition, the limitations of the classical information entropy models applied for assessing traffic scenarios are addressed by calculating magnitude entropy. The proposed entropy‐based model is analyzed in detail according to its application to simulated traffic scenarios. Moreover, the model is applied to real world data within a naturalistic driving dataset. Finally, the effectiveness of the proposed quantification model is illustrated by comparing the complexity results obtained for three typical traffic scenarios with those obtained using an existing multi‐factor complexity quantification method.

Learning to Play Trajectory Games Against Opponents With Unknown Objectives

Many autonomous agents, such as intelligent vehicles, are inherently required to interact with one another. Game theory provides a natural mathematical tool for robot motion planning in such interactive settings. However, tractable algorithms for such problems usually rely on a strong assumption, namely that the objectives of all players in the scene are known. To make such tools applicable for ego-centric planning with only local information, we propose an adaptive model-predictive game solver, which jointly infers other players' objectives online and computes a corresponding generalized Nash equilibrium (GNE) strategy. The adaptivity of our approach is enabled by a differentiable trajectory game solver whose gradient signal is used for maximum likelihood estimation (MLE) of opponents' objectives. This differentiability of our pipeline facilitates direct integration with other differentiable elements, such as neural networks (NNs). Furthermore, in contrast to existing solvers for cost inference in games, our method handles not only partial state observations but also general inequality constraints. In two simulated traffic scenarios, we find superior performance of our approach over both existing game-theoretic methods and nongame- theoretic model-predictive control (MPC) approaches. We also demonstrate our approach's real-time planning capabilities and robustness in two-player hardware experiments.

Online and offline learning of player objectives from partial observations in dynamic games

Robots deployed to the real world must be able to interact with other agents in their environment. Dynamic game theory provides a powerful mathematical framework for modeling scenarios in which agents have individual objectives and interactions evolve over time. However, a key limitation of such techniques is that they require a priori knowledge of all players’ objectives. In this work, we address this issue by proposing a novel method for learning players’ objectives in continuous dynamic games from noise-corrupted, partial state observations. Our approach learns objectives by coupling the estimation of unknown cost parameters of each player with inference of unobserved states and inputs through Nash equilibrium constraints. By coupling past state estimates with future state predictions, our approach is amenable to simultaneous online learning and prediction in receding horizon fashion. We demonstrate our method in several simulated traffic scenarios in which we recover players’ preferences, for, e.g. desired travel speed and collision-avoidance behavior. Results show that our method reliably estimates game-theoretic models from noise-corrupted data that closely matches ground-truth objectives, consistently outperforming state-of-the-art approaches.

A Review of Virtual Reality Studies on Autonomous Vehicle–Pedestrian Interaction

An increasing number of studies employ virtual reality (VR) to evaluate interactions between autonomous vehicles (AVs) and pedestrians. VR simulators are valued for their cost-effectiveness, flexibility in developing various traffic scenarios, safe conduct of user studies, and acceptable ecological validity. Reviewing the literature between 2010 and 2020, we found 31 empirical studies using VR as a testing apparatus for both implicit and explicit communication. By performing a systematic analysis, we identified current coverage of critical use cases, obtained a comprehensive account of factors influencing pedestrian behavior in simulated traffic scenarios, and assessed evaluation measures. Based on the findings, we present a set of recommendations for implementing VR pedestrian simulators and propose directions for future research.

Data-Driven Forgetting and Discount Factors for Vehicle Speed Forecasting in Ecological Adaptive Cruise Control

Abstract This paper investigates temporal correlations in human driving behavior using real-world driving to improve speed forecasting accuracy. These correlations can point to a measurement weighting function with two parameters: a forgetting factor for past speed measurements that the vehicle itself drove with, and a discount factor for the speeds of vehicles ahead based on information from vehicle-to-vehicle communication. The developed weighting approach is applied to a vehicle speed predictor using polynomial regression, a prediction method well-known in the literature. The performance of the developed approach is then assessed in both real-world and simulated traffic scenarios for accuracy and robustness. The new weighting method is applied to an ecological adaptive cruise control system, and its influence is analyzed on the prediction accuracy and the performance of the ecological adaptive cruise control in an electric vehicle powertrain model. The results show that the new prediction method improves energy saving from the eco-driving by up to 4.7% compared to a baseline least-square-based polynomial regression. This is a 10% improvement over the constant speed/acceleration model, a conventional speed predictor.

Independent Reinforcement Learning for Weakly Cooperative Multiagent Traffic Control Problem

The adaptive traffic signal control (ATSC) problem can be modeled as a multiagent cooperative game among urban intersections, where intersections cooperate to counter the city's traffic conditions. Recently, reinforcement learning (RL) has achieved marked successes in managing sequential decision making problems, which motivates us to apply RL in the ATSC problem. One of the largest challenges of this problem is that the observation of intersection is typically partially observable, which limits the learning performance of RL algorithms. Considering the large scale of intersections in an urban traffic environment, we use independent RL to solve ATSC problem in this study. We model ATSC problem as a partially observable weak cooperative traffic model (PO-WCTM). Different from a traditional IRL task that averages the returns of all agents in fully cooperative games, the learning goal of each intersection in PO-WCTM is to reduce the cooperative difficulty of learning, which is also consistent with the traffic environment hypothesis. To achieve the optimal cooperative strategy of PO-WCTM, we propose an IRL algorithm called Cooperative Important Lenient Double DQN (CIL-DDQN), which extends Double DQN (DDQN) algorithm using two mechanisms: the forgetful experience mechanism and the lenient weight training mechanism. The former mechanism decreases the importance of experiences stored in the experience reply buffers, while the latter mechanism increases the weight experiences with high estimation and `leniently' trains the DDQN neural network. Experiments in two real traffic scenarios and one simulated traffic scenarios show that, CIL-DDQN outperforms other methods in almost all performance indicators of ATSC.

A Double-Level Model Checking Approach for an Agent-Based Autonomous Vehicle and Road Junction Regulations

Usually, the design of an Autonomous Vehicle (AV) does not take into account traffic rules and so the adoption of these rules can bring some challenges, e.g., how to come up with a Digital Highway Code which captures the proper behaviour of an AV against the traffic rules and at the same time minimises changes to the existing Highway Code? Here, we formally model and implement three Road Junction rules (from the UK Highway Code). We use timed automata to model the system and the MCAPL (Model Checking Agent Programming Language) framework to implement an agent and its environment. We also assess the behaviour of our agent according to the Road Junction rules using a double-level Model Checking technique, i.e., UPPAAL at the design level and AJPF (Agent Java PathFinder) at the development level. We have formally verified 30 properties (18 with UPPAAL and 12 with AJPF), where these properties describe the agent’s behaviour against the three Road Junction rules using a simulated traffic scenario, including artefacts like traffic signs and road users. In addition, our approach aims to extract the best from the double-level verification, i.e., using time constraints in UPPAAL timed automata to determine thresholds for the AVs actions and tracing the agent’s behaviour by using MCAPL, in a way that one can tell when and how a given Road Junction rule was selected by the agent. This work provides a proof-of-concept for the formal verification of AV behaviour with respect to traffic rules.

Impact of aircraft speed heterogeneity on contingent flow control in 4D en-route operation

Understanding the impact of aircraft speed heterogeneity on air traffic operation is crucial for airspace design and air traffic flow management. Speed heterogeneity (or aircraft mix) is recognized as a causal factor for complexity in air traffic operations, through qualitative or statistical analysis. Quantitative metrics on how it affects current and future Trajectory-Based Operation (TBO) is lacking, however. In this paper, we present an in-depth investigation of the impact of speed heterogeneity, by defining air traffic robustness at microscopic (aircraft pair) and macroscopic (air traffic flow) levels in nominal situations, derived mathematically and validated through fast-time computer simulations. A human-in-the-loop study follows investigating six 4D en route operation scenarios, where operators were instructed to resolve a large disturbance in a sector, using a novel interface. Results confirm the negative impact of speed heterogeneity on air traffic controller performance in terms of flow efficiency and workload. The mechanism of such impact is substantiated through analyzing several speed-based robustness metrics. Although the simulated traffic scenarios have similar baseline robustness, those with mixed speeds lead to significantly lower robustness and operational performance. This emphasizes the need to incorporate speed heterogeneity in robustness evaluations of air traffic control in current and future TBO environments.

Eco-Approach With Traffic Prediction and Experimental Validation for Connected and Autonomous Vehicles

This work proposes a fuel efficient vehicle speed control strategy for a connected and autonomous vehicle to pass the intersection (the eco-approach application). A control framework is developed to integrate traffic prediction (enabled by connectivity) and speed optimization. The traffic prediction is based on traffic flow model and can be applied to mixedtraffic scenarios where both connected and non-connected vehicles are on the road. Real-time information from connected vehicles and signal lights provides `partial' measurement of the traffic states. The unknown traffic states are estimated using an observer (Unscented Kalman Filter). Uncertainties in the traffic prediction are systematically considered during the vehicle speed optimization to improve the robustness of the optimal control. Effects of powertrain states (the transmission gear ratio) on fuel consumption are considered as well. The vehicle speed optimization problem is real-time implementable using an efficient nonlinear programming solver. The optimal speed control strategy is evaluated in both a simulated traffic scenario and a real-world traffic scenario. In the simulated traffic scenario, fuel benefits vary from 5.3% to 9.4% as the penetration rate of connectivity increases. This is satisfactory compared to 11.7% fuel benefits with perfect traffic prediction. In the realworld traffic scenario, experimental results show that 6.9% fuel benefits can be achieved with two connected preceding vehicles and 11.2% fuel benefits can be obtained with perfect prediction. The results demonstrate the effectiveness of the traffic prediction and the optimal vehicle speed control strategy.

Optimised Traffic Light Management Through Reinforcement Learning: Traffic State Agnostic Agent vs. Holistic Agent With Current V2I Traffic State Knowledge

Traffic light control falls into two main categories: Agnostic systems that do not exploit knowledge of the current traffic state, e.g., the positions and velocities of vehicles approaching intersections, and holistic systems that exploit knowledge of the current traffic state. Emerging fifth generation (5G) wireless networks enable Vehicle-to-Infrastructure (V2I) communication to reliably and quickly collect the current traffic state. However, to the best of our knowledge, the optimized traffic light management without and with current traffic state information has not been compared in detail. This study fills this gap in the literature by designing representative Deep Reinforcement Learning (DRL) agents that learn the control of multiple traffic lights without and with current traffic state information. Our agnostic agent considers mainly the current phase of all traffic lights and the expired times since the last change. In addition, our holistic agent considers the positions and velocities of the vehicles approaching the intersections. We compare the agnostic and holistic agents for simulated traffic scenarios, including a road network from Barcelona, Spain. We find that the holistic system substantially increases average vehicle velocities and flow rates, while reducing CO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> emissions, average wait and trip times, as well as a driver stress metric.

A Jam-Absorption Driving Strategy for Mitigating Traffic Oscillations

To mitigate traffic oscillations that usually sustainably propagate upstream, this paper proposes a jam-absorption driving (JAD) strategy in the framework of Newell's car-following theory. The basic idea of the JAD strategy is to guide a vehicle to move slowly before being captured by an oscillation and terminate the slow movement when the vehicle would start to leave the jam if no such slow movement was implemented. To practically implement the idea, a two-step method is proposed to estimate the time–space ending point of the strategy, and a proper vehicle is selected to implement the JAD strategy based on a given expected absorbing speed and current traffic conditions. To test the JAD strategy, two simulated traffic scenarios are constructed based on a realistic data-driven car-following model. The first scenario, which only reproduces one oscillation, directly shows the effectiveness of the JAD idea in preventing wave propagation and capacity drop. The second scenario, which contains a series of traffic oscillations induced by the rubbernecking behavior, validates the proposed JAD strategy in more complicated and realistic conditions. It is indicated that the JAD strategy is able to absorb traffic oscillations; thus, the side effects incurred by the oscillations could be subsequently mitigated. The significance of this paper is to provide us a new idea to mitigate traffic oscillations, i.e., the JAD strategy.

Toward Self-Referential Autonomous Learning of Object and Situation Models.

Most current approaches to scene understanding lack the capability to adapt object and situation models to behavioral needs not anticipated by the human system designer. Here, we give a detailed description of a system architecture for self-referential autonomous learning which enables the refinement of object and situation models during operation in order to optimize behavior. This includes structural learning of hierarchical models for situations and behaviors that is triggered by a mismatch between expected and actual action outcome. Besides proposing architectural concepts, we also describe a first implementation of our system within a simulated traffic scenario to demonstrate the feasibility of our approach.

Traffic Displays for Visual Flight Indicating Track and Priority Cues

This study addresses problems in pilots’ interaction with conventional traffic advisory systems during simulated visual flight. A predictive traffic visualization concept is proposed, which attempts to fill the gap between the traffic information needed by pilots in visual flight and the information provided by conventional traffic advisory systems. The method and the reasoning for the need to display predictive traffic features are explained. Four display variants that combined various predictive features and a conventional display were evaluated in an experiment with 21 pilots. The pilots’ tasks were to watch simulated traffic scenarios on a display and to make conflict and priority decisions. They also provided ratings for mental demand and display preferences. The results show that pilots preferred two display variants: one which combined oriented air vehicle symbols and the relative track, and one with an additional priority cue. With both display variants, the pilots made significantly faster conflict decisions and reported lower mental demand as compared with the variants using conventional TCAS-like symbols and other predictive cues such as the oriented air vehicle symbols and the absolute track. These findings can be applied to improve future traffic advisory systems for visual flight.

Strategies in coping with complexity: Development of a behavioural marker system for air traffic controllers

To meet the increasing air traffic volume, organizations seek better tools to assess the traffic handling capacity of air traffic control (ATC) systems. This effort requires a better understanding of how complex situations are related to controller strategies and how controllers intervene to maintain control. Recent empirical studies and reviews have shown that controllers cope with complexity by adapting priorities, managing their cognitive resources, and regulating their own performance. This study discusses the development of a behavioural marker system to evaluate and provide feedback on the strategies that controllers use to cope with complexity. An extensive literature review provided the basis for an initial classification of strategies for coping with complexity which was tested in an observational study for reliability. After three iterations of adaptation to the taxonomy, two independent raters were able to reach acceptable levels of reliability in classifying video segments of simulated traffic scenarios. A potential application of the study regards the design of refresher training enriched with the principles of error management and the assessment of new technologies and controller tools on the handling capacity of ATC systems.

Optimal trajectories for time-critical street scenarios using discretized terminal manifolds

This paper deals with the trajectory generation problem faced by an autonomous vehicle in moving traffic. Being given the predicted motion of the traffic flow, the proposed semi-reactive planning strategy realizes all required long-term maneuver tasks (lane-changing, merging, distance-keeping, velocity-keeping, precise stopping, etc.) while providing short-term collision avoidance. The key to comfortable, human-like as well as physically feasible trajectories is the combined optimization of the lateral and longitudinal movements in street-relative coordinates with carefully chosen cost functionals and terminal state sets (manifolds). The performance of the approach is demonstrated in simulated traffic scenarios.

Graphical Presentation of AIS Information on Ships

This paper describes a research project carried out for the German Federal Ministry of Transport, Building, and Housing to evaluate the graphical presentation of AIS information. The implementation of AIS on ship bridges requires a suitable presentation and integration of its information in the bridge information systems. To support the decision which symbols should be used for the presentation of AIS information two experiments were conducted with simulated traffic scenarios on ECDIS and on Radar with mariners as subjects. Additionally, a questionnaire was administered and analyzed. Results show higher detection performance for the orientated triangle symbol as ship symbol, which also was rated higher in the subjective preference analysis than the diamond shaped symbol. The results for symbols for the display of course and speed and the heading information led to the conclusion to display the vector as plain line and the heading as dashed line with a flag indicating the rate of turn. A draft for AIS symbols was recommended.