Browsing by Subject "Autonomous driving"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    On Evaluating Black-Box Explainable AI Methods for Enhancing Anomaly Detection in Autonomous Driving Systems
    (MDPI, 2024-05-29) Nazat, Sazid; Arreche, Osvaldo; Abdallah, Mustafa; Electrical and Computer Engineering, Purdue School of Engineering and Technology
    The recent advancements in autonomous driving come with the associated cybersecurity issue of compromising networks of autonomous vehicles (AVs), motivating the use of AI models for detecting anomalies on these networks. In this context, the usage of explainable AI (XAI) for explaining the behavior of these anomaly detection AI models is crucial. This work introduces a comprehensive framework to assess black-box XAI techniques for anomaly detection within AVs, facilitating the examination of both global and local XAI methods to elucidate the decisions made by XAI techniques that explain the behavior of AI models classifying anomalous AV behavior. By considering six evaluation metrics (descriptive accuracy, sparsity, stability, efficiency, robustness, and completeness), the framework evaluates two well-known black-box XAI techniques, SHAP and LIME, involving applying XAI techniques to identify primary features crucial for anomaly classification, followed by extensive experiments assessing SHAP and LIME across the six metrics using two prevalent autonomous driving datasets, VeReMi and Sensor. This study advances the deployment of black-box XAI methods for real-world anomaly detection in autonomous driving systems, contributing valuable insights into the strengths and limitations of current black-box XAI methods within this critical domain.
  • Thumbnail Image
    Item
    Planning Autonomous Driving with Compact Road Profiles
    (IEEE Xplore, 2021-09) Wang, Zheyuan; Cheng, Guo; Zheng, Jiang Yu; Computer and Information Science, School of Science
    Current sensing and control of self-driving vehicles based on full-view recognition is hard to keep a high-frequency with a fast moving vehicle, as increasingly complex computation is employed to cope with the variations of driving environment. This work, however, explores a light-weight sensing-planning framework for autonomous driving. Taking the advantage that a vehicle moves along a smooth path, we only locate several sampling lines in the view to scan the road, vehicles and environments continuously, which generates a fraction of full video data. We have applied semantic segmentation to the streaming road profiles without redundant data computing. In this paper, we plan vehicle path/motion based on this minimum data set that contains essential information for driving. Based on the lane, headway length, and vehicle motion detected from road/motion profiles, a path and speed of ego-vehicle as well as the interaction with surrounding vehicles are computed. This sensing-planning scheme based on spatially sparse yet temporally dense data can ensure a fast response to events, which yields smooth driving in busy traffic flow.
  • Thumbnail Image
    Item
    Social relation and physical lane aggregator: Integrating social and physical features for multimodal motion prediction
    (Emerald Publishing, 2022-10-11) Chen, Qiyuan; Wei, Zebing; Wang, Xiao; Li, Lingxi; Lv, Yisheng; Electrical and Computer Engineering, School of Engineering and Technology
    Purpose The purpose of this paper aims to model interaction relationship of traffic agents for motion prediction, which is critical for autonomous driving. It is obvious that traffic agents’ trajectories are influenced by physical lane rules and agents’ social interactions. Design/methodology/approach In this paper, the authors propose the social relation and physical lane aggregator for multimodal motion prediction, where the social relations of agents are mainly captured with graph convolutional networks and self-attention mechanism and then fused with the physical lane via the self-attention mechanism. Findings The proposed methods are evaluated on the Waymo Open Motion Dataset, and the results show the effectiveness of the proposed two feature aggregation modules for trajectory prediction. Originality/value This paper proposes a new design method to extract traffic interactions, and the attention mechanism is used in each part of the model to extract and fuse different relational features, which is different from other methods and improves the accuracy of the LSTM-based trajectory prediction method.