In order to realize the autonomous cutting for tunneling robot, the method of cutting trajectory planning of sections with complex composition was proposed. Firstly, based on the multi-sensor parameters, the existence, the location, and size of the dirt band were determined. The roadway section environment was modeled by grid method. Secondly, according to the cutting process and tunneling cutting characteristics, the cutting trajectory ant colony algorithm was proposed. To ensure the operation safety and avoid the cutting head collision, the expanding operation was adopt for dirt band, and the aborting strategy for the ants trapped in the local optimum was put forward to strengthen the pheromone concentration of the found path. The simulation results showed that the proposed method can be used to plan the optimal cutting trajectory. The ant colony algorithm was used to search for the shortest path to avoid collision with the dirt band, and the S-path cutting was used for the left area to fulfill section forming by following complete cover principle. All the ants have found the optimal path within 50 times iteration of the algorithm, and the simulation results were better than particle swarm optimization and basic ant colony optimization.

With the increasingly widespread application of unmanned aerial vehicle (UAV) systems in disaster monitoring, urban management, logistics transportation, and reconnaissance, efficient dynamic task allocation has become a key issue in improving task execution efficiency. To address the challenges posed by dynamic changes in task objectives and resource constraints that traditional task allocation methods struggle with in complex environments, this paper proposes a multi-objective particle swarm optimization algorithm, DCMPSO, for UAV dynamic reconnaissance task allocation. First, the framework of DCMPSO is constructed, dividing the optimization of dynamic problems into three parts: environment change detection, environment change response, and actual optimization, with the designed strategy of range prediction strategy based on centroid translation. Then, simulation experiments are conducted to verify the effectiveness of the algorithm mechanisms through ablation experiments and to demonstrate the superiority of DCMPSO in convergence and distribution compared to DNSGA-II and SGEA through comparative experiments. Finally, a multi-UAV dynamic task allocation model is established and optimized, proving that DCMPSO can correctly solve the UAV dynamic multi-objective allocation problem and effectively find its optimal solution, providing an effective solution for practical applications.

Reinforcement learning has achieved significant success in sequential decision-making problems but exhibits poor adaptability in non-stationary environments with unknown dynamics, a challenge particularly pronounced in multi-agent scenarios. This study aims to enhance the adaptive capability of multi-agent systems in such volatile environments. We propose a novel cooperative Multi-Agent Reinforcement Learning (MARL) algorithm based on MADDPG, termed MACPH, which innovatively incorporates three mechanisms: a Composite Experience Replay Buffer (CERB) mechanism that balances recent and important historical experiences through a dual-buffer structure and mixed sampling; an Adaptive Parameter Space Noise (APSN) mechanism that perturbs actor network parameters and dynamically adjusts the perturbation intensity to achieve coherent and state-dependent exploration; and a Huber loss function mechanism to mitigate the impact of outliers in Temporal Difference errors and enhance training stability. The study was conducted in standard and non-stationary navigation and communication task scenarios. Ablation studies confirmed the positive contributions of each component and their synergistic effects. In non-stationary scenarios featuring abrupt environmental changes, experiments demonstrate that MACPH outperforms baseline algorithms such as DDPG, MADDPG, and MATD3 in terms of reward performance, adaptation speed, learning stability, and robustness. The proposed MACPH algorithm offers an effective solution for multi-agent reinforcement learning applications in complex non-stationary environments.

Most current studies on multi-agent evolution based on deep learning take a cooperative equilibrium strategy, while interactive self-learning is not always considered. An interactive self-learning game and evolution method based on non-cooperative equilibrium (ISGE-NCE) is proposed to take the benefits of both game theory and interactive learning for multi-agent confrontation evolution. A generative adversarial network (GAN) is designed combining with multi-agent interactive self-learning, and the non-cooperative equilibrium strategy is well adopted within the framework of interactive self-learning, aiming for high evolution efficiency and interest. For assessment, three typical multi-agent confrontation experiments are designed and conducted. The results show that, first, in terms of training speed, the ISGE-NCE produces a training convergence rate of at least 46.3% higher than that of the method without considering interactive self-learning. Second, the evolution rate of the interference and detection agents reaches 60% and 80%, respectively, after training by using our method. In the three different experiment scenarios, compared with the DDPG, our ISGE-NCE method improves the multi-agent evolution effectiveness by 43.4%, 50%, and 20%, respectively, with low training costs. The performances demonstrate the significant superiority of our ISGE-NCE method in swarm intelligence.

In nature, organisms often rely on the integration of local sensory information and prior experience to flexibly adapt to complex and dynamic environments, enabling efficient path selection. This bio-inspired mechanism of perception and behavioral adjustment provides important insights for path planning in mobile robots operating under uncertainty. In recent years, the introduction of deep reinforcement learning (DRL) has empowered mobile robots to autonomously learn navigation strategies through interaction with the environment, allowing them to identify obstacle distributions and perform path planning even in unknown scenarios. To further enhance the adaptability and path planning performance of robots in complex environments, this paper develops a deep reinforcement learning framework based on the Soft Actor–Critic (SAC) algorithm. First, to address the limited adaptability of existing transfer learning methods, we propose an action-level fusion mechanism that dynamically integrates prior and current policies during inference, enabling more flexible knowledge transfer. Second, a bio-inspired radar perception optimization method is introduced, which mimics the biological mechanism of focusing on key regions while ignoring redundant information, thereby enhancing the expressiveness of sensory inputs. Finally, a reward function based on ineffective behavior recognition is designed to reduce unnecessary exploration during training. The proposed method is validated in both the Gazebo simulation environment and real-world scenarios. Experimental results demonstrate that the approach achieves faster convergence and superior obstacle avoidance performance in path planning tasks, exhibiting strong transferability and generalization across various obstacle configurations.

We report a heavily Yb ³⁺ /Al ³⁺ /B ³⁺ /F ⁻ co-doped high silica rod with a negative refractive index relative to pure silica. The high silica rod was fabricated from nanoporous silica rod using glass phase-separation technology. To lower the refractive index, B ³⁺ and F ⁻ were simultaneously introduced into the silica rod and the optical properties of the silica rod were investigated. The fiber preform was prepared with the rod-in-tube method by which the Yb ³⁺ doped high silica rod was only used as an active core. The fiber has a core diameter of 80 μ m and a cladding diameter of 400 μ m. The measurements show that the Yb ³⁺ in the high silica fiber core is 15856 ppm by weight, while the refractive index is 0.0024 lower than that of the inner cladding. The amplification performance of the fiber was investigated. The results indicate that nanoporous silica glass based on the glass phase-separation technology has great potential for gain-guided index anti-guided high silica fiber.