Despite the advancements in the technologies of autonomous driving, it is still challenging to study the safety of a self-driving vehicle. Trajectory prediction is one core function of an autonomous vehicle. This study proposes an Attention-based Interaction-aware Trajectory Prediction (AI-TP) for traffic agents around the autonomous vehicle. With an encoder-decoder architecture, the AI-TP model uses Graph Attention Networks (GAT) to describe the interactions of traffic agents and Convolutional Gated Recurrent Units (ConvGRU) to carry out predictions. Based on the attention mechanism, the AI-TP model con-structs graphs from various traffic scenes to predict trajectories of different types of traffic agents. Traffic data from both the high-way (i.e., NGSIM) and urban road areas (i.e., ApolloScape and Argoverse) are used to evaluate the performance of the AI-TP model. Numerical results demonstrate that the AI-TP model requires less inference time and achieves better prediction accuracy than state-of-the-art methods. Specifically, the AI-TP model improves the performance by 36% on average with much less inference time on the NGSIM dataset, which shows the promise of predicting trajectories under various scenarios. The code of the AI-TP model will be available at https://github.com/KP-Zhang/AI-TP.

Advancements in technology hold significant prom-ise for the future of smart agriculture. Drones, serving as innovative tools for data acquisition, play a pivotal role in this context. Traditional pollination drones, which rely on extensive spraying methods, suffer from poor efficiency. To address this challenge, our focus is on enhancing pollination through object detection technology, leading to the introduction of the YOLO-FT detection algorithm based on YOLOv7. To validate our algorithm, we have curated a dataset of fruit tree flowers. Our approach involves several key components. Firstly, we propose a lightweight adaptive backbone network, which effectively extracts feature information through partial convolution and seamlessly integrates feature data from diverse channels. Secondly, we intro-duce a non-parametric attention module into neck network, bolstering the fusion of critical feature information. Finally, we leverage a rapid convergence function based on centroid distance to enhance bounding box regression performance. Experimental results demonstrate the superiority of the YOLO-FT algorithm, achieving mAP50 of 92.8%, mAP50-95 of 48.8%, and F1 score of 0.90, marking improvements of 3.6%, 1.6%, and 0.17, respectively, over the baseline. Furthermore, YOLO-FT exhibits a signifi-cant reduction in model complexity, with parameters decreased by 13.4% and FLOPs by 17.8%. This research serves as a valuable theoretical reference for advancements in smart agriculture.

Underwater target detection plays a crucial role in marine environmental monitoring and early warning systems. It involves utilizing optical images acquired from underwater imaging devices to locate and identify aquatic organisms in challenging environments. However, the color deviation and low illumination in these images, caused by harsh working conditions, pose significant challenges to an effective target detection. Moreover, the detection of numerous small or tiny aquatic targets becomes even more demanding, considering the limited storage and computing power of detection devices. To address these problems, we propose the YOLOv7-CHS model for underwater target detection, which introduces several innovative approaches. Firstly, we replace efficient layer aggregation networks (ELAN) with the high-order spatial interaction (HOSI) module as the backbone of the model. This change reduces the model size while preserving accuracy. Secondly, we integrate the contextual transformer (CT) module into the head of the model, which combines static and dynamic contextual representations to effectively improve the model’s ability to detect small targets. Lastly, we incorporate the simple parameter-free attention (SPFA) module at the head of the detection network, implementing a combined channel-domain and spatial-domain attention mechanism. This integration significantly improves the representation capabilities of the network. To validate the implications of our model, we conduct a series of experiments. The results demonstrate that our proposed model achieves higher mean average precision (mAP) values on the Starfish and DUO datasets compared to the original YOLOv7, with improvements of 4.5% and 4.2%, respectively. Additionally, our model achieves a real-time detection speed of 32 frames per second (FPS). Furthermore, the floating point operations (FLOPs) of our model are 62.9 G smaller than those of YOLOv7, facilitating the deployment of the model. Its innovative design and experimental results highlight its effectiveness in addressing the challenges associated with underwater object detection.

In this paper, a sliding mode observer (SMO) for the speed-sensorless direct torque vector control of linear induction motor(LIM) is proposed, considering the influence of dynamic end effects. The proposed SMO estimate the motor speed, the rotor flux, the angular position of the rotor flux, and the speed dependent parameter w, only by using the measured stator voltages and stator currents. The nonlinear sliding mode technique guarantees very good performance for different situations of motor speed. The proposed SMO does not use complicated observer gains and robust to the parameter variation over the full-speed range. Moreover, the convergence of SMO is proven by using the Lyapunov theory. Furthermore, LIM Drive state observability is presented with detailed analysis. The performance of the proposed SMO is verified by hardware-in-the-loop test (HIL) system. Furthermore, a comparative study with and Luenberger observer(LO) and model reference adaptive system(MRAS) is presented.

Most existing traffic sign detection models suffer from high computational complexity and superior performance but cannot be deployed on edge devices with limited computational capacity, which cannot meet the direct needs of autonomous vehicles for detection model performance and efficiency. To address the above concerns, this paper proposes an improved SEDG-Yolov5 traffic sign detection method based on knowledge distillation. Firstly, the Slicing Aided Hyper Inference method is used as a local offline data augmentation method for the model training. Secondly, to solve the problems of high-dimensional feature information loss and high model complexity, the inverted residual structure ESGBlock with a fused attention mechanism is proposed, and a lightweight feature extraction backbone network is constructed based on it, while we introduce the GSConv in the feature fusion layer to reduce the computational complexity of the model further. Eventually, an improved response-based objectness scaled knowledge distillation method is proposed to retrain the traffic sign detection model to compensate for the degradation of detection accuracy due to light-weighting. Extensive experiments on two challenging traffic sign datasets show that our proposed method has a good balance on detection precision and detection speed with 2.77M parametric quantities. Furthermore, the inference speed of our method achieves 370 FPS with TensorRT and 35.6 FPS with ONNX at FP16-precision, which satisfies the requirements for real-time sign detection and edge deployment.

In intelligent transportation systems, accurate vehicle target recognition within road scenarios is crucial for achieving intelligent traffic management. Addressing the challenges posed by complex environments and severe vehicle occlusion in such scenarios, this paper proposes a novel vehicle-detection method, YOLO-BOS. First, to bolster the feature-extraction capabilities of the backbone network, we propose a novel Bi-level Routing Spatial Attention (BRSA) mechanism, which selectively filters features based on task requirements and adjusts the importance of spatial locations to more accurately enhance relevant features. Second, we incorporate Omni-directional Dynamic Convolution (ODConv) into the head network, which is capable of simultaneously learning complementary attention across the four dimensions of the kernel space, therefore facilitating the capture of multifaceted features from the input data. Lastly, we introduce Shape-IOU, a new loss function that significantly enhances the accuracy and robustness of detection results for vehicles of varying sizes. Experimental evaluations conducted on the UA-DETRAC dataset demonstrate that our model achieves improvements of 4.7 and 4.4 percentage points in mAP@0.5 and mAP@0.5:0.95, respectively, compared to the baseline model. Furthermore, comparative experiments on the SODA10M dataset corroborate the superiority of our method in terms of precision and accuracy.