In this article, a novel vehicle positioning system architecture based on direction-of-arrival (DOA) estimation of incoherently distributed (ID) sources is proposed employing massive multiple-input–multiple-output (MIMO) arrays. Such an architecture with the associated signal model is more consistent with the actual array application and multipath transmission scenarios. First, an end-to-end two-dimensional (2-D) DOA estimation of ID sources utilizing a dual one-dimensional (1-D) convolutional neural network (D1D-CNN) under the deep learning (DL) framework is performed, where the normalized covariance matrix data is used for both offline training and online estimation. Then, the received SNR information is exploited to select a set of DOA estimates provided by multiple collaborative BSs for positioning. Moreover, transfer learning and an attention mechanism are employed to promote its generalization ability and achieve robustness against array perturbations. Simulation results are provided to show that the proposed method outperforms the state-of-the-art methods in terms of computational complexity, positioning accuracy, and robustness against array perturbations.

It is a challenging task for an aerial manipulator to complete dual-arm cooperative manipulation in an outdoor environment. In this study, a new dual-arm aerial manipulator system with flexible operation is developed. The dual-arm manipulator system is designed for the application of aerial manipulation, and it has the characteristics of low weight, low inertia, and a humanoid arm structure. The arm structure is composed of customized aluminum parts, each manipulator contains four degrees of freedom, similar to the arrangement of human joints, including shoulder yaw, shoulder pitch, elbow pitch, and wrist roll. Next, the workspace of the dual-arm manipulator is simulated and analyzed, and the relevant kinematic and dynamic models are deduced. Finally, through the lift load, accuracy and repeatability, cooperative bimanual manipulation tests on the test bench, and multiple groups of outdoor flight tests, the relevant performance analysis and verification of the dual-arm aerial manipulator system are carried out. The test results evaluate the feasibility of the designed dual-arm aerial manipulator system for outdoor cooperative manipulation.

Reinforcement learning needs to learn policies through trial and error. The unstable policies in the early stage of training make it expensive (and time-consuming) to train directly in the real environment, which may cause disastrous consequences. The popular solution is to use the simulator to train the policy and deploy it in a real environment. However, the modeling error and external disturbance between the simulation and the real environment may fail the physical deployment, resulting in the sim2real transfer problem. In this letter, we propose a novel robust adversarial reinforcement learning framework, which uses the ensemble training of multi-adversarial agents that can adaptively adjust adversaries' strength to enhance RL policy's robustness. More specifically, we take the accumulative reward as feedback and construct a PID controller to adjust the adversary's output magnitude to perform the adversarial training well. Experiments in the simulated and the real environment show that our algorithm improves the generalization ability of the policy for the modeling error and the uncertain disturbance simultaneously, outperforming the next best prior methods across all domains. The algorithm was further proven to be effective in a sim2real transfer task through the load experiment of a real racing drone, and the tracking performance is better than the PID-based flight controller.