Mobile robots contributed significantly to the intelligent development of human society, and the motion-planning policy is critical for mobile robots. This paper reviews the methods based on motion-planning policy, especially the ones involving Deep Reinforcement Learning (DRL) in the unstructured environment. The conventional methods of DRL are categorized to value-based, policy-based and actor-critic-based algorithms, and the corresponding theories and applications are surveyed. Furthermore, the recently-emerged methods of DRL are also surveyed, especially the ones involving the imitation learning, meta-learning and multi-robot systems. According to the surveys, the potential research directions of motion-planning algorithms serving for mobile robots are enlightened.

Unmanned air vehicle (UAV) systems for performing forestry applications have expanded in recent decades and have great economic benefits. They are validated to be more appealing than traditional platforms in various aspects, such as repeat rate, spatial resolution, and accuracy. This paper consolidates the state-of-the-art unmanned systems in the forestry field with a major focus on UAV systems and heterogeneous platforms, which are applied in a variety of forestry applications, such as wood production, tree quantification, disease control, wildfire management, wildlife conservation, species classification, etc. This review also studies practical applications under multiple forestry environments, including wild and managed forests, grassland, urban green parks, and stockyards. Special forest environments and terrains present customized demands for unmanned systems. The challenges of unmanned systems deployment are analyzed from environmental characterization, maneuverability and mobility improvement, and global regulatory interpretation. To better apply UAV systems into forestry, future directions are analyzed in terms of mobility enhancement and customized sensory adaption, which need to be further developed for synchronizing all possible agents into automatic functioning systems for forestry exploration.

The efficiency and accuracy for parallel robot play a significant role in the industrial production process. In order to further improve the motion performance of parallel robot, this paper focuses on the study of mechanism design, dynamic modeling and error analysis of a cable-linkage serial-parallel palletizing robot (CSPR). Firstly, the CSPR is designed as a series-parallel hybrid mechanism driven by flexible cables, which can effectively reduce the inertia and improve the dynamic response. As is known that kinematic design optimization of compliant mechanisms requires accurate yet efficient mathematical models, the kinematics and dynamic models are established by the homogeneous coordinate transformation method and Lagrange equation. Based on the dynamic mathematical model of the robot, a variety of sensors are chosen to construct the hardware control system and the sliding mode variable structure control strategy is also designed based on motion errors. Then, the motion performance and load carrying capacity of the CSPR were analyzed and compared in different operating conditions respectively, and the results verify the validity and efficiency of the mechanism.

Monitoring wildlife in remote areas is vital for biodiversity research, yet infrared‐triggered cameras often produce large numbers of false or empty images due to environmental interference, causing data overload and power waste. To address this, this manuscript proposes WS‐YOLO, a lightweight edge‐optimized wildlife detection model based on improved YOLOv11n, which aims to integrate false‐trigger filtering and accurate animal detection in a single model for field applications. Specifically, the model introduces three key enhancements: it adopts a Wavelet Convolution (WTConv) module to capture multi‐scale and frequency‐aware features, boosting robustness to complex backgrounds and small‐target detection accuracy; meanwhile, a Spatial‐Channel Synergistic Attention (SCSA) mechanism is incorporated to enhance spatial localization and channel‐wise semantic encoding, enabling the model to focus on salient regions of wildlife; additionally, a SlideLoss function is designed to prioritize training on boundary cases, improving the handling of ambiguous detection instances. Experiments on four wildlife datasets demonstrate that WS‐YOLO achieves excellent mAP@0.50 performance: 93.0% on African Wildlife, 98.0% on Amur Tiger, 98.5% on the NTLNP infrared dataset, and 79.4% on PASCAL VOC, confirming its robustness across diverse scenarios. Deployment on a Jetson Nano further validates its feasibility for real‐time, energy‐efficient use in the field. WS‐YOLO enables accurate animal recognition and classification directly at edge devices, significantly reducing communication load and enhancing monitoring efficiency.