Supervised object detection models based on deep learning technologies cannot perform well in domain shift scenarios where annotated data for training is always insufficient. To this end, domain adaptation technologies for knowledge transfer have emerged to handle the domain shift problems. A stepwise domain adaptive YOLO (S-DAYOLO) framework is developed which constructs an auxiliary domain to bridge the domain gap and uses a new domain adaptive YOLO (DAYOLO) in cross-domain object detection tasks. Different from the previous solutions, the auxiliary domain is composed of original source images and synthetic images that are translated from source images to the similar ones in the target domain. DAYOLO based on YOLOv5s is designed with a category-consistent regularization module and adaptation modules for image-level and instance-level features to generate domain invariant representations. Our proposed method is trained and evaluated by using five public driving datasets including Cityscapes, Foggy Cityscapes, BDD100K, KITTI, and KAIST. Experiment results demonstrate that object detection performance is significantly improved when using our proposed method in various domain shift scenarios for autonomous driving applications.

Driver’s emotion recognition is vital to improving driving safety, comfort, and acceptance of intelligent vehicles. This article presents a cognitive-feature-augmented driver emotion detection method that is based on emotional cognitive process theory and deep networks. Different from the traditional methods, both the driver’s facial expression and cognitive process characteristics (age, gender, and driving age) were used as the inputs of the proposed model. Convolutional techniques were adopted to construct the model for driver’s emotion detection simultaneously considering the driver’s facial expression and cognitive process characteristics. A driver’s emotion data collection was carried out to validate the performance of the proposed method. The collected dataset consists of 40 drivers’ frontal facial videos, their cognitive process characteristics, and self-reported assessments of driver emotions. Another two deep networks were also used to compare recognition performance. The results prove that the proposed method can achieve well detection results for different databases on the discrete emotion model and dimensional emotion model, respectively.

There are many constraints to be considered to plan a safe and feasible trajectory for autonomous mining trucks due to the rough terrain in open-pit mines. It is difficult to handle these constraints uniformly within a trajectory planning framework. To overcome this limitation, a novel trajectory planning framework is proposed in this paper. Different from many existing studies which characterized the spatial positions of vehicles at the sampling time points as decision variables, we characterize the time points at the sampling spatial positions as decision variables to conveniently address the terrain constraints. Based on such a formulation, we further consider the kinematic constraints, engine power constraints and time window constraints. Various objectives (e.g., transport efficiency, fuel economy) can be considered in this trajectory planning framework, and the formulated trajectory planning problems can be efficiently solved. Finally, several case studies are conducted to validate the effectiveness of the proposed trajectory planning framework.

Wind power has great uncertainty and short-term wind power forecasting technology can provide great help to power system scheduling after wind power integration. In this paper, a Convolutional neural network -bidirectional long and short-term memory network combination modeliCNN-BiLITMjbased on feature selection is proposed. Firstly, high correlation feature parameters were optimized based on effective feature screening of multidimensional feature datasets. Secondly, the input data are weighted according to the feature correlation to form a multi-dimensional feature data set. Finally, CNN-BiLSTM developed the wind energy forecast model. For verification, the KDD Cup 2022 wind power generation prediction data set was employed. The outcomes demonstrate that CNN-BiLSTM has a greater time series data utilization rate and prediction accuracy.

Virtual testing plays a vital role in developing connected and automated vehicles. To ensure the safety of CAV, millions of miles of testing are required. The scenario library defines the parameter of each testing scenario, which reduces testing by merging similar scenarios and focusing on challenging scenarios. However, current scenario generation methods still bear some disadvantages, such as lack of data and low efficiency. In order to overcome the lack of data, this paper proposed a genetic algorithm-based framework for the cut-in event and car-following event. In this study, the genetic algorithm searches for one of the most challenging scenarios within the boundaries. The challenging scenario is acquired by the brute force search algorithm which searches from the start scenario. The result shows the ratio of accident scenarios to challenging scenarios in our scenario set is more than 40%. Compared with natural driving data scenarios, our method performs well without natural driving data. In addition, the genetic algorithm converges in ten iterations which indicates its efficiency and suitability in scenario generation. More specifically, whole challenging scenarios which probably occur in the real world are collected in the scenario set.

Virtual testing requires hazardous scenarios to effectively test autonomous vehicles (AVs). Existing studies have obtained rarer events by sampling methods in a fixed scenario space. In reality, heterogeneous drivers behave differently when facing the same situation. To generate more realistic and efficient scenarios, we propose a two-stage heterogeneous driver model to change the number of dangerous scenarios in the scenario space. We trained the driver model using the HighD dataset, and generated scenarios through simulation. Simulations were conducted in 20 experimental groups with heterogeneous driver models and 5 control groups with the original driver model. The results show that, by adjusting the number and position of aggressive drivers, the percentage of dangerous scenarios was significantly higher compared to that of models not accounting for driver heterogeneity. To further verify the effectiveness of our method, we evaluated two driving strategies: car-following and cut-in scenarios. The results verify the effectiveness of our approach. Cumulatively, the results indicate that our approach could accelerate the testing of AVs.