Frequent bad weather at sea severely damages the quality of visual images captured by imaging equipment. Ship instance segmentation in adverse weather conditions remains a major challenge because of poor visibility at sea. Existing approaches for instance segmentation are primarily designed for clear days and rarely consider the aforementioned severe weather. Blurred ship objects can easily cause missed ship detection and decrease the instance segmentation performance on ship images, especially in the case of frequent fog at sea. To this end, we propose a ship instance segmentation framework (IRDCLNet) based on Interference Reduction and Dynamic Contour Learning in foggy scenes. The Interference Reduction Module is proposed to reduce the interference caused by fog and solves the problem of missed ship detection. Meanwhile, we present Dynamic Contour Learning to predict the overall contour of the blurred ships to assist in mask prediction. To handle the scarcity of ocean data in foggy weather, we build the Foggy ShipInsseg dataset, which contains 5,739 real and simulated foggy ship images with 10,900 fine instance mask annotations. Experiments on the Foggy ShipInsseg dataset show that our IRDCLNet outperforms the Mask R-CNN and CondInst baselines and achieves the state-of-the-art performance.

Learning variable impedance control is a powerful method to improve the performance of force control. However, current methods typically require too many interactions to achieve good performance. Data-inefficiency has limited these methods to learn force-sensitive tasks in real systems. In order to improve the sampling efficiency and decrease the required interactions during the learning process, this paper develops a data-efficient learning variable impedance control method that enables the industrial robots automatically learn to control the contact force in the unstructured environment. To this end, a Gaussian process model is learned as a faithful proxy of the system, which is then used to predict long-term state evolution for internal simulation, allowing for efficient strategy updates. The effects of model bias are reduced effectively by incorporating model uncertainty into long-term planning. Then the impedance profiles are regulated online according to the learned humanlike impedance strategy. In this way, the flexibility and adaptivity of the system could be enhanced. Both simulated and experimental tests have been performed on an industrial manipulator to verify the performance of the proposed method.

Data driven model predictive control (DMPC) has become an effective trajectory tracking approach for unmanned surface vessel (USV). However, its offline-trained prediction models and event-triggered (ET) mechanisms result in reduced control accuracy and efficiency under time-varying ocean disturbances. To effectively improve the control accuracy and efficiency of the DMPC method under environmental influences, a two-step ET DMPC (TETDMPC) algorithm is proposed. Traditional mechanism prediction models fail to effectively account for time-varying USV dynamics, which can degrade the accuracy of control algorithms. To enhance the control accuracy of the algorithm, a v-support vector regression (vSVR)-based data driven model is introduced into the model predictive control algorithm to replace mechanism prediction model. However, the rolling horizon calculations of the DMPC and the online updates of the vSVR suffer from extensive computation. To improve the control efficiency and enable vSVR model online updates, a two-step ET mechanism is designed. The performance of the online vSVR model depends on the quality of the training data. Therefore, a spatiotemporal data updating algorithm is also developed to construct the model training dataset online. The trajectory tracking performance of the proposed TETDMPC algorithm is validated based on the CyberShip II and Dolphin 1 USVs, respectively. The results demonstrate that the TETDMPC algorithm has desirable control performance.

Point cloud-based detection focuses on land traffic, rarely marine, facing issues with ships: it struggles in bad weather due to reliance on adverse weather data and fails to detect ships effectively due to overlooking size and appearance differences. Addressing the above challenges, our work introduces point cloud data of marine scenarios under realistically simulated adverse weather conditions and a dedicated Ship Detector tailored for marine environments. To adapt to various maritime weather conditions, we simulate realistic rain and fog in collected marine scene point cloud data. Additionally, addressing the issue of losing geometric and height information during feature extraction for large objects, we propose a Ship Detector. It employs a dual-branch sparse convolution layer for extracting multi-scale 3D feature maps, effectively minimizing height information loss. Additionally, a multi-scale 2D convolution module is utilized, which encodes and decodes feature maps and directly employs 3D feature maps for target prediction. To reduce dependency on existing data and enhance model robustness, our training dataset includes simulated point cloud data representing adverse weather conditions. In maritime point cloud ship detection, our Ship Detector, compared to adjusted small object detectors, demonstrates the best performance.

Multi-fidelity modeling is a common approach for predicting the drag coefficient of airfoil, offering high accuracy and low computational cost. Low-fidelity data are acquired by simplifying high-fidelity models. However, existing multi-fidelity modeling techniques fail to consider the relative importance of different low-fidelity samples and treat them uniformly, which reduces the accuracy of multi-fidelity models. To effectively utilize different low-fidelity samples, this paper proposes a hierarchical clustering weighted Gaussian process regression (HCWGPR) low-fidelity model and applies it to the multi-fidelity modeling of the airfoil drag coefficient. First, principal component analysis is used to extract the key information of low-fidelity samples. Then, empirical mode decomposition is employed to decompose the key information into high-frequency energy fluctuations and low-frequency feature vectors. Next, a hierarchical clustering weight calculation algorithm based on high-frequency energy differences and low-frequency feature similarity is proposed to assign weights to low-fidelity samples. Finally, a weighted Gaussian process regression framework is used to construct the HCWGPR. A Gaussian process regression is also adopted as a discrepancy model. The effectiveness of the proposed method is verified by 9 sets of analytical test cases and the drag coefficient prediction of 6 airfoils.

Multiple ship tracking (MST) is an important task in marine surveillance and ship situational awareness systems. Considerable work has been conducted on multiple object tracking in recent years, but it has focused primarily on pedestrians and automobiles, leaving a gap in studies on MST due to the particularities of complex marine scenes, such as ship scale variations, the long-tailed distribution of ships, and long-term occlusions caused by ship movements. In this article, we present a robust deep affinity network (RoDAN) for MST. To overcome the above difficulties in MST, we start with the basic deep affinity network (DAN) and improve it in three aspects: scale, region, and motion. For the scale dimension, we integrate an atrous spatial pyramid pooling (ASPP) module to improve the modeling ability for multiscale ships. For the region dimension, we propose the joint global region modeling (JGRM) module, which further strengthens the modeling ability of DAN and exploit it to overcome the long-tailed distribution property of ships. For the motion dimension, we propose the motion-matching optimization (MMO) module to fine-tune the tracking results and make our tracker more robust, less reliant on the front-end detector, and ameliorate long-term occlusions. The experimental results demonstrate that our MST method outperforms the state-of-the-art methods. In particular, it reduces the number of ID switches (IDSs) and trajectory fragmentations (FMs), achieving holistically preferable performance. Meanwhile, our method achieves a comparable speed.