A decentralized four-dimensional (4D) trajectory generation method for unmanned aerial vehicles (UAVs), which uses the improved intrinsic tau gravity (tau-G) guidance strategy, is presented in this paper. Based on general tau theory, the current tau-G strategy can only generate the 4D trajectory with zero initial and final velocities, which is not appropriate for decentralized applications. By adding an initial velocity to the intrinsic movement of tau-G strategy, the improved tau-G strategy can synchronously guide the position and velocity to the desired values at the arrival time. In our decentralized 4D trajectory generation method, the improved tau-G strategy is used to plan the 4D trajectories for UAVs. To deal with environmental uncertainty and communication limitations, the receding horizon optimization driven by both sampling time and conflict events is utilized to renew trajectory parameters continually. The simulation results of challenging time-constrained tasks demonstrate that the proposed method can efficiently provide safer and lower-cost 4D trajectories.

Nowadays, transfer learning (TL) has become a crucial technique to accelerate the slow optimization procedure of reinforcement learning (RL) by re-utilizing knowledge acquired in a previous related task. Nevertheless, most of the current relevant research acquires knowledge through RL training in the source task, which would be too time-consuming. In view of this situation, in this paper, we propose a novel TL framework where the agent extracts knowledge from human-demonstration trajectories of the source task and reuses the knowledge in RL in the target task. As for what to transfer, two forms of knowledge deduced from the demonstration trajectories, which are the k-nearest neighbour of the current state in source samples and visit frequency of homologous states, are adopted. For how to transfer, the two forms of knowledge are respectively used to recommend a preferred action when random exploration is needed and to shape an instantaneous reward for RL. Simulation experiments of balancing Cart-Poles with different difficulties suggest that both the two forms of knowledge accelerate the learning process of RL obviously. What is more, the effect is even more significant when they are used in combination. In this case, the experimental results manifest the positive role of our framework in RL.

In this paper, we present an iterative scenario approach (ISA) to design robust controllers for complex linear parameter-varying (LPV) systems with uncertainties. The robust controller synthesis problem is transformed to a scenario design problem, with the scenarios generated by identically extracting random samples on both uncertainty parameters and scheduling parameters. An iterative scheme based on the maximum volume ellipsoid cutting-plane method is used to solve the problem. Heuristic logic based on relevance ratio ranking is used to prune the redundant constraints, and thus, to improve the numerical stability of the algorithm. And further, a batching technique is presented to remarkably enhance the computational efficiency. The proposed method is applied to design an output-feedback controller for a small helicopter. Multiple uncertain physical parameters are considered, and simulation studies show that the closed-loop performance is quite good in both aspects of model tracking and dynamic decoupling. For robust LPV control problems, the proposed method is more computationally efficient than the popular stochastic ellipsoid methods.

In the field of real-time autonomous decision-making for Unmanned Combat Aerial Vehicles (UCAVs), reinforcement learning is widely used to enhance their decision-making capabilities in high-dimensional spaces. These enhanced capabilities allow UCAVs to better respond to the maneuvers of various opponents, with the win rate often serving as the primary optimization metric. However, relying solely on the terminal outcome of victory or defeat as the optimization target, but without incorporating additional rewards throughout the process, poses significant challenges for reinforcement learning due to the sparse reward structure inherent in these scenarios. While algorithms enhanced with densely distributed artificial rewards show potential, they risk deviating from the primary objectives. To address these challenges, we introduce a novel approach: the homotopy-based soft actor–critic (HSAC) method. This technique gradually transitions from auxiliary tasks enriched with artificial rewards to the main task characterized by sparse rewards through homotopic paths. We demonstrate the consistent convergence of the HSAC method and its effectiveness through deployment in two distinct scenarios within a 3D air combat game simulation: attacking horizontally flying UCAVs and a combat scenario involving two UCAVs. Our experimental results reveal that HSAC significantly outperforms traditional algorithms, which rely solely on using sparse rewards or those supplemented with artificially aided rewards.

Federated domain generalization addresses the crucial challenge of developing models that can generalize across diverse domains while maintaining data privacy in federated learning settings. Current approaches either compromise privacy constraints or focus narrowly on specific aspects of model invariance, often incurring significant computational overhead. We propose a novel approach FedDIM, which leverages the concept of “insight matrix” - a fine-grained representation of the model's decision-making process derived from element-wise products between feature vectors and classifier weights. By introducing a regularization term that promotes consistency between individual sample insight matrices and their class-wise mean representations, our method effectively captures both feature and classifier invariance. This approach not only maintains strict privacy requirements but also introduces minimal computational overhead as it utilizes intermediate computations already present in the forward pass. Extensive experiments demonstrate that our method achieves superior out-of-distribution generalization compared to existing federated learning approaches while being simple to implement. Our work provides a new perspective on achieving robust generalization in federated learning settings through the lens of decision-making processes.