Attention-based Neural Network for Driving Environment Complexity Perception
This addresses a gap in autonomous vehicle perception by introducing an environment complexity parameter, though it is incremental as it builds on existing object detection and feature extraction methods.
The paper tackles the problem of predicting driving environment complexity for autonomous vehicles by proposing an attention-based neural network that achieves 91.22% average classification accuracy on the Berkeley DeepDrive dataset.
Environment perception is crucial for autonomous vehicle (AV) safety. Most existing AV perception algorithms have not studied the surrounding environment complexity and failed to include the environment complexity parameter. This paper proposes a novel attention-based neural network model to predict the complexity level of the surrounding driving environment. The proposed model takes naturalistic driving videos and corresponding vehicle dynamics parameters as input. It consists of a Yolo-v3 object detection algorithm, a heat map generation algorithm, CNN-based feature extractors, and attention-based feature extractors for both video and time-series vehicle dynamics data inputs to extract features. The output from the proposed algorithm is a surrounding environment complexity parameter. The Berkeley DeepDrive dataset (BDD Dataset) and subjectively labeled surrounding environment complexity levels are used for model training and validation to evaluate the algorithm. The proposed attention-based network achieves 91.22% average classification accuracy to classify the surrounding environment complexity. It proves that the environment complexity level can be accurately predicted and applied for future AVs' environment perception studies.