In this article, we present an incentive mechanism for Vehicular Crowdsensing in the context of autonomous vehicles (AVs). In particular, we propose a solution to the problem of sensing coverage of regions located out of the AVs’ planned trajectories. We tackle this problem by dynamically modifying the AVs’ trajectories and collecting sensing samples from regions otherwise unreachable by originally planned routes. We model this problem as a non-cooperative game in which a set of AVs equipped with sensors are the players and their trajectories are the strategies. Thus, our solution corresponds to a model in which expected individual utility drives the mobility decision of participants. Using open-street maps, SUMO vehicular traffic simulator, and extensive simulations, we show our algorithm significantly outperforms traditional approaches for trajectory generation. In particular, our performance evaluation shows a significant lift in crowdsourcer coverage, road utilization, and average participant utility.

To embrace safety while bringing autonomous vehicles (AVs) to public roads, AV manufacturers need to validate and verify the functionality and reliability of the control software. Real-road testing is time-consuming, tedious, costly, and unsafe for validation. Hence, simulation testing has been playing an important role in the market as a viable solution. This paper presents an approach that exploits both methods to find edge case scenarios and evaluates the software reliability of an existing AV shuttle, iseAuto, currently operating at the Tallinn University of Technology campus. To show the method’s effectiveness, a range of scenarios are generated and simulated for avoidance maneuvers by means of a low-fidelity simulator. Then, the scenarios that are found to be jeopardizing the AV are filtered and simulated by a high-fidelity simulator with the AV control software in the loop. Finally, to investigate the methodology and simulation reliability, a real study case is proposed using the AV shuttle. Results of the study suggest that the proposed toolchain is capable of tuning simulation models for automated driving development as well as validating safe AV operations.

Scenario-based testing has been used for validation and verification of autonomous vehicles in various settings. In these efforts, simulation platforms are extensively utilized to run and analyze test scenarios, which is crucial for the validation of perception, decision-making and action in different traffic situations. Providing formal specification for scenarios used in these simulations is also critical for standardization, repeatability and verification. In this paper, we propose an approach which integrates an open-source network-based traffic simulator with an open-source formal scenario description language designed for formal scenario specification of autonomous vehicle validation scenarios. This approach provides the capability to describe, generate, and share abstract traffic scenarios for validation. It also allows integration with higher fidelity or physical testing methods as it utilizes a widely used scenario specification methodology. We provide an integration of formal specification and traffic simulation and also show the potential of such an integration through simulation examples.

The validation of autonomous vehicles remains a vexing challenge for the automotive industry’s goal of fully autonomous driving. The systematic hierarchization of the test scenarios would provide valuable insights for the development, testing, and verification of autonomous vehicles, enabling nuanced performance evaluations based on scenario complexity. In this paper, an information entropy-based quantification method is proposed to evaluate the complexity of autonomous vehicle validation scenarios. The proposed method addresses the dynamic uncertainties within driving scenarios in a comprehensive way which includes the unpredictability of dynamic agents such as autonomous vehicles, human-driven vehicles, and pedestrians. The numerical complexity calculation of the approach and the ranking of the scenarios are presented through sample scenarios. To automate processes and assist with the calculations, a novel software tool with a user-friendly interface is developed. The performance of the approach is also evaluated through six example driving scenarios, then through extensive simulation using an open-source microscopic traffic simulator. The performance evaluation results confirm the numerical classification and demonstrate the method’s adaptability to diverse scenarios with a comparison of complexity calculation ranking to the ratio of collision, near collision, and normal operation tests observed during simulation testing. The proposed quantification method contributes to the improvement of autonomous vehicle validation procedures by addressing the multifaceted nature of scenario complexities. Beyond advancing the field of validation, the approach also aligns with the broad and active drive of the industry for the widespread deployment of fully autonomous driving.

This article presents a novel scenario-based testing framework for the evaluation of black-box autonomous vehicles (AVs) in diverse traffic scenarios. The framework aims to bridge the gap between formal scenario description, simulation integration in the realm of safety validation, and modular explainability techniques. The proposed framework consists of a formal means of scenario specification and a testing template that exploits scenario description at the functional and concrete abstraction layers. The testing template is modularized using the terminology of these AV scenario description strategies; then, bottlenecks in the testing process are identified, and solutions are suggested, which we validate using experiments. To optimize the utilization of the generated scenario data, we also present an innovative data model and an Explainable Artificial Intelligence (XAI) component, demonstrating their practicality through a detailed AV case study. This comprehensive approach promises significant advances in the evaluation and understanding of complex system behavior, thereby paving the way for safer and more reliable AVs and various other applications. Furthermore, insights derived from the scenario interpretation component can be harnessed to refine the precision of the scenario selection process, potentially enhancing both performance and efficiency.

The vector cost bimatrix game is a method for multi-objective decision making that enables autonomous robotic systems to optimize for multiple goals at once while avoiding worst-case scenarios in neglected objectives. We expand this approach to arbitrary numbers of objectives and compare its performance to scalar weighted sum methods during competitive motion planning. Explainable Artificial Intelligence (XAI) software is used to aid in the analysis of high dimensional decision-making data. State-space Exploration of Multidimensional Boundaries using Adherence Strategies (SEMBAS) is applied to explore performance modes in the parameter space as a sensitivity study for the baseline and proposed frameworks. While some works have explored aspects of game theoretic planning and intelligent systems validation separately, we combine each of these into a novel and comprehensive simulation pipeline. This integration demonstrates a dramatic improvement of the vector cost method over scalarization and offers an interpretable and generalizable framework for robotic behavioral planning. Code available at https://github.com/toazbenj/race_simulation. The video companion to this work is available at https://tinyurl.com/vectorcostvideo.