Driven by the rapid development of deep learning technology, the YOLO series has set a new benchmark for real-time object detectors. Additionally, transformer-based structures have emerged as the most powerful solution in the field, greatly extending the model's receptive field and achieving significant performance improvements. However, this improvement comes at a cost, as the quadratic complexity of the self-attentive mechanism increases the computational burden of the model. To address this problem, we introduce a simple yet effective baseline approach called Mamba YOLO. Our contributions are as follows: 1) We propose that the ODMamba backbone introduce a State Space Model (SSM) with linear complexity to address the quadratic complexity of self-attention. Unlike the other Transformer-base and SSM-base method, ODMamba is simple to train without pretraining. 2) For real-time requirement, we designed the macro structure of ODMamba, determined the optimal stage ratio and scaling size. 3) We design the RG Block that employs a multi-branch structure to model the channel dimensions, which addresses the possible limitations of SSM in sequence modeling, such as insufficient receptive fields and weak image localization. This design captures localized image dependencies more accurately and significantly. Extensive experiments on the publicly available COCO benchmark dataset show that Mamba YOLO achieves state-of-the-art performance compared to previous methods. Specifically, a tiny version of Mamba YOLO achieves a 7.5% improvement in mAP on a single 4090 GPU with an inference time of 1.5 ms.

Geo-localization has been widely applied as an important technique to get the longitude and latitude for unmanned aerial vehicle (UAV) navigation in outdoor flight. Due to the possible interference and blocking of GPS signals, the method based on image retrieval, which is less likely to be interfered with, has received extensive attention in recent years. The geo-localization of UAVs and satellites can be achieved by querying pre-obtained satellite images with GPS-tagged and drone images from different perspectives. In this paper, an image transformation technique is used to extract cross-view geo-localization information from UAVs and satellites. A single-stage training method in UAV and satellite geo-localization is first proposed, which simultaneously realizes cross-view feature extraction and image retrieval, and achieves higher accuracy than existing multi-stage training techniques. A novel piecewise soft-margin triplet loss function is designed to avoid model parameters being trapped in suboptimal sets caused by the lack of constraint on positive and negative samples. The results illustrate that the proposed loss function enhances image retrieval accuracy and realizes a better convergence. Moreover, a data augmentation method for satellite images is proposed to overcome the disproportionate numbers of image samples. On the benchmark University-1652, the proposed method achieves the state-of-the-art result with a 6.67% improvement in recall rate (R@1) and 6.13% in average precision (AP). All codes will be publicized to promote reproducibility.

In this paper, a digital twin system is designed for intelligent management of a unit level wheeled mobile robot (WMR). A framework of the digital twin system is arranged from four main parts, i.e., physical WMR, virtual WMR, data processing, and application service. To realize high-fidelity mod-eling of the physical WMR, a 3D model of the virtual WMR is established in Webots from aspects on geometric structures, kinematic analysis, and actuator control. Based on the digital twin system, a virtual-physical mapping control strategy is proposed for remote motion interaction between the physical WMR and the virtual WMR. Finally, effectiveness of application service is shown in a synchronous-motion experiment with the digital twin system via a Mecanum wheeled mobile robot.

In this article, a digital twin system is investigated to achieve virtual–physical tracking control for a car-like mobile robot (CLMR). The digital twin system consisted of a physical entity, a virtual entity, and a virtual–physical interaction module for the CLMR. The virtual–physical tracking control is used to complete motion mapping from the physical entity to the virtual entity. Although external disturbances acting on the physical entity are different from the virtual entity, only one nonlinear extended state observer is designed in this article, which is suitable in estimating the external disturbances for both the physical and the virtual entities. A backstepping controller and an integral sliding mode controller are designed for both the physical and the virtual entities to realize motion mapping. Experiment results show effectiveness and superiority of the virtual–physical tracking control by digital twin technology for the CLMR.