Molecular property prediction (MPP) is vital in drug discovery and drug reposition. Deep learning-based MPP models capture molecular property-related features from various molecule representations. In this paper, we propose a molecule sequence embedding and prediction model facing with MPP task. We pre-trained a bi-directional encoder representations from Transformers (BERT) encoder to obtain the semantic representation of compound fingerprints, called Fingerprints-BERT (FP-BERT), in a self-supervised learning manner. Then, the encoded molecular representation by the FP-BERT is input to the convolutional neural network (CNN) to extract higher-level abstract features, and the predicted properties of the molecule are finally obtained through fully connected layer for distinct classification or regression MPP tasks. Comparison with the baselines shows that the proposed model achieves high prediction performance on all of the classification tasks and regression tasks.

In this article, a deep reinforcement learning-based path-following control scheme is established for an under-actuated autonomous marine vehicle (AMV) in the presence of model uncertainties and unknown marine environment disturbances is presented. By virtue of light-of-sight guidance, a surge-heading joint guidance method is developed within the kinematic level, thereby enabling the AMV to follow the desired path accurately. Within the dynamic level, model uncertainties and time-varying environment disturbances are taken into account, and the reinforcement learning control method using the twin-delay deep deterministic policy gradient (TD3) is developed for the under-actuated vehicle, where path-following actions are generated via the state space and hybrid rewards. Additionally, actor-critic networks are developed using the long-short time memory (LSTM) network, and the vehicle can successfully make a decision by the aid of historical states, thus enhancing the convergence rate of dynamic controllers. Simulation results and comprehensive comparisons on a prototype AMV demonstrate the remarkable effectiveness and superiority of the proposed LSTM-TD3-based path-following control scheme.

This research introduces a two-stage deep reinforcement learning approach for the cooperative path planning of unmanned surface vehicles (USVs). The method is designed to address cooperative collision-avoidance path planning while adhering to the International Regulations for Preventing Collisions at Sea (COLREGs) and considering the collision-avoidance problem within the USV fleet and between USVs and target ships (TSs). To achieve this, the study presents a dual COLREGs-compliant action-selection strategy to effectively manage the vessel-avoidance problem. Firstly, we construct a COLREGs-compliant action-evaluation network that utilizes a deep learning network trained on pre-recorded TS avoidance trajectories by USVs in compliance with COLREGs. Then, the COLREGs-compliant reward-function-based action-selection network is proposed by considering various TS encountering scenarios. Consequently, the results of the two networks are fused to select actions for cooperative path-planning processes. The path-planning model is established using the multi-agent proximal policy optimization (MAPPO) method. The action space, observation space, and reward function are tailored for the policy network. Additionally, a TS detection method is introduced to detect the motion intentions of TSs. The study conducted Monte Carlo simulations to demonstrate the strong performance of the planning method. Furthermore, experiments focusing on COLREGs-based TS avoidance were carried out to validate the feasibility of the approach. The proposed TS detection model exhibited robust performance within the defined task.

With the rapid development of perception, decision-making, and control technologies, pursuit–evasion (PE) games with unmanned surface vehicles (USVs) have become an interesting research topic in military implementations and civilian areas. In this paper, we provide an overview of recent advances in the PE games with USVs. First, the motion model of USVs and successful criteria for PE games are presented. Next, some challenging issues in PE games with USVs are briefly discussed. Then, recent results on one-pursuer one-evader, multiple-pursuer one-evader, and multiple-pursuer multiple-evader with USVs are reviewed in detail. Finally, several theoretical and technical issues are suggested to direct future research, including target prediction, dynamic task allocation, brain-inspired decision-making, safe control, and PE experiments.

This study introduces a method for formation control and obstacle avoidance for multiple unmanned surface vehicles (USVs) by combining an artificial potential field with the virtual structure method. The approach involves a leader–follower formation structure, where the leader autonomously avoids collisions using an artificial potential field based on the target’s position as a reference. It also determines the ideal position of each follower in the formation based on its own position, heading angle, and the formation structure. To effectively avoid obstacles and maintain formation, the follower selects the position of the target or its ideal position as a reference during movement, depending on whether it is being repelled by obstacles. Additionally, this paper modifies the attractive force model of the traditional artificial potential field method to restrict the maximum magnitude of the attractive force when encountering repulsive forces, thus expediting departure from obstacle areas. The dynamic characteristics of USVs are taken into account by constraining the maximum linear speed and angular speed. Formation stability is ensured by maintaining a constant speed for the leader, while the linear speed of the follower varies based on the distance to the reference object during movement. Simulation experiments demonstrated that this method can effectively avoid obstacles and maintain formation.