Due to the strong adaptability and high flexibility, unmanned aerial vehicles (UAVs) have been extensively studied and widely applied in both civil and military applications. Although UAVs can achieve significant cost reduction and performance enhancement in large-scale systems by taking full advantage of their cooperation and coordination, they result in a serious cooperative behaviour control problem. Especially in dynamic environments, the cooperative behaviour control problem which has to quickly produce a safe and effective behaviour decision for each UAV to achieve group missions, is NP-hard and difficult to settle. In this work, we design a global-and-local attention-based reinforcement learning algorithm for the cooperative behaviour control problem of UAVs. First, with the motion and coordination models, we analyze the collision avoidance, motion state update, and task execution constraints of multiple UAVs, and abstract the cooperative behaviour control problem as a multi-constraint decision-making one. Then, inspired from the human-learning process where more attention is devoted to the important parts of data, we design a multi-agent reinforcement learning algorithm with a global-and-local attention mechanism to cooperatively control the behaviours of UAVs and achieve the coordination. Simulation experiments in a multi-agent particle environment provided by OpenAI are conducted to verify the effectiveness and efficiency of the proposed approach. Compared with baselines, our approach shows significant advantages in mean reward, training time, and coordination effect.

Due to their high flexibility and strong maneuverability, unmanned aerial vehicles (UAVs) have attracted lots of attention and are widely employed in many fields. Especially in target encirclement applications, UAVs have shown great advantages in adaptability and reliability, and can efficiently fly to and evenly surround the targets in complex and dynamic environments. In this paper, we concentrate on the cooperative target encirclement problem of heterogeneous UAVs and try to propose a multi-agent reinforcement learning approach to solve the problem. First, with the models of heterogeneous UAVs and obstacles, we analyze the collision avoidance, motion continuity, and energy consumption constraints of UAVs, and formulate the cooperative target encirclement problem as a multi-constraint combinatorial optimization one. Then, inspired by the humans’ learning experience that curiosity provides a powerful motivator for humans to explore, discover, and acquire new knowledge, we propose an extrinsic-and-intrinsic reward-based multi-agent reinforcement learning approach to cooperatively control the behaviors of UAVs and achieve the target encirclement missions. Simulation experiments with randomly generated environments are conducted to evaluate the performance of our approach, and the results show that our approach has a significant advantage in terms of average reward, encirclement success rate, encirclement time, and encirclement energy consumption.

Collaborative perception effectively mitigates issues such as limited field of view and occlusion by enabling multiple agents to share perceptual information. Despite its advantages, challenges persist in complex environments due to factors such as limited communication bandwidth and noisy poses, which may potentially degrade system performance. Meanwhile, a substantial amount of simulation data is widely adopted in collaborative perception to achieve high precision and real-time detection. However, the domain gap between simulated and real-world environments may result in weakened collaborative performance and hindered generalization ability. In this work, we focus on the multi-agent collaborative perception problem and propose a quantized communication and transferable fusion framework, named QCTF, to efficiently minimize the bandwidth overhead and enhance real-world perception by leveraging unlabeled data for improved adaptability. First, we present a quantized communication method that employs multi-scale residual indices and an optimized codebook to extract robust representations while minimizing bandwidth usage. Then, we design a channel-aware selection strategy that adjusts the bandwidth volume and compensates for the quantized representation by combining the prioritized critical features with the channel dimension. Finally, we adopt a transferable fusion module to effectively bridge the simulation-to-reality domain gaps and improve perceptual capability through multi-scale adaptation discriminators. Experiments on both simulated and real-world datasets are conducted to evaluate the effectiveness of the proposed framework, and the results demonstrate that our approach consistently outperforms the existing methods in limited communication bandwidth and domain adaptation scenarios.