B, we provide specific network architecture and more details about the target center parameterization for the voxel-to-BEV target localization network. As shown in Figure 1, we illustrate the specific network structure. Then, we present the 2D network to aggregate features in the BEV space. Finally, we provide more details on the target center parameterization. We also use a concatenated skip connection to fuse low-level and high-level features.

To this end, we first perform template feature embedding to embed the template's feature into

Path planning has long been an important and active research area in robotics. To address challenges in high-dimensional motion planning, this study introduces the Force Direction Informed Trees (FDIT*), a sampling-based planner designed to enhance speed and cost-effectiveness in pathfinding. FDIT* builds upon the state-of-the-art informed sampling planner, the Effort Informed Trees (EIT*), by capitalizing on often-overlooked information in invalid vertices. It incorporates principles of physical force, particularly Coulomb's law. This approach proposes the elliptical $k$-nearest neighbors search method, enabling fast convergence navigation and avoiding high solution cost or infeasible paths by exploring more problem-specific search-worthy areas. It demonstrates benefits in search efficiency and cost reduction, particularly in confined, high-dimensional environments. It can be viewed as an extension of nearest neighbors search techniques. Fusing invalid vertex data with physical dynamics facilitates force-direction-based search regions, resulting in an improved convergence rate to the optimum. FDIT* outperforms existing single-query, sampling-based planners on the tested problems in R^4 to R^16 and has been demonstrated on a real-world mobile manipulation task.

To this end, we first perform template feature embedding to embed the template's feature into

Then, it proposes a hybrid AI system, integrating deep reinforcement learning in a multi-agent centralized swarm architecture. The proposed system is tailored to perform surveillance of a specific area, searching and tracking ground targets, for security and law enforcement applications. The swarm is governed by a central swarm controller responsible for distributing different search and tracking tasks among the cooperating UAVs. Each UAV agent is then controlled by a collection of cooperative sub-agents, whose behaviors have been trained using different deep reinforcement learning models, tailored for the different task types proposed by the swarm controller. More specifically, proximal policy optimization (PPO) algorithms were used to train the agents' behavior. In addition, several metrics to assess the performance of the swarm in this application were defined. The results obtained through simulation show that our system searches the operation area effectively, acquires the targets in a reasonable time, and is capable of tracking them continuously and consistently.

Predicting the location where a lost person could be found is crucial for search and rescue operations with limited resources. To improve the precision and efficiency of these predictions, simulated agents can be created to emulate the behavior of the lost person. Within this study, we introduce an innovative agent-based model designed to replicate diverse psychological profiles of lost persons, allowing these agents to navigate real-world landscapes while making decisions autonomously without the need for location-specific training. The probability distribution map depicting the potential location of the lost person emerges through a combination of Monte Carlo simulations and mobility-time-based sampling. Validation of the model is achieved using real-world Search and Rescue data to train a Gaussian Process model. This allows generalization of the data to sample initial starting points for the agents during validation. Comparative analysis with historical data showcases promising outcomes relative to alternative methods. This work introduces a flexible agent that can be employed in search and rescue operations, offering adaptability across various geographical locations.

Today, Search and Rescue (SAR) teams are increasingly leveraging advanced technologies such as artificial intelligence and Unmanned Aerial Vehicles (UAVs) to enhance the efficiency of their operations (Martinez-Alpiste et al., 2021). In this context, UAVs, with their high flight speed and ability to scan areas at night or in low-light conditions, can address one of the challenges in SAR operations: monitoring large or hard-to-reach search areas. In ground SAR operations, additional methods such as employing dogs and volunteers can be used alongside UAVs to expedite target searching. However, in maritime SAR operations, fewer options are available, making UAVs particularly important for enhancing operational efficiency. In this regard, one of the main questions is how UAVs should fly to cover the search area in the shortest possible time, a challenge addressed in the literature under the Coverage Path Planning (CPP) problem. Various objective functions were considered in CPP, including the number of turning maneuvers (Maza & Ollero, 2007), path length (Bouzid et al., 2017), flight time (Forsmo et al., 2013), energy consumption (Di Franco and Buttazzo, 2016), and total coverage time (Kazemdehbashi and Liu, 2025). Additionally, two main types of decomposition are used in the CPP problem: exact cell decomposition and grid-based decomposition. In exact cell decomposition, the search area is divided into smaller sub-areas, whereas in grid-based decomposition, the area is represented as a grid, and each grid's cell must be covered to achieve full coverage. In this paper, we propose an Adaptive Grid-based Decomposition (AGD) algorithm to reduce the number of cells in the grid required to cover the primary search area.

The application of Multiple Unmanned Aerial Vehicles (Multi-UAV) in Wilderness Search and Rescue (WiSAR) significantly enhances mission success due to their rapid coverage of search areas from high altitudes and their adaptability to complex terrains. This capability is particularly crucial because time is a critical factor in searching for a lost person in the wilderness; as time passes, survival rates decrease and the search area expands. The probability of success in such searches can be further improved if UAVs leverage terrain features to predict the lost person's position. In this paper, we aim to enhance search missions by proposing a smart agent-based probability model that combines Monte Carlo simulations with an agent strategy list, mimicking the behavior of a lost person in the wildness areas. Furthermore, we develop a distributed Multi-UAV receding horizon search strategy with dynamic partitioning, utilizing the generated probability density model as prior information to prioritize locations where the lost person is most likely to be found. Simulated search experiments across different terrains have been conducted to validate the search efficiency of the proposed methods compared to other benchmark methods.

The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of the point clouds and the motion of the objects across neighboring frames are smooth, failing to cope with high temporal variation data. In this paper, we present a novel framework for 3D SOT in point clouds with high temporal variation, called HVTrack. HVTrack proposes three novel components to tackle the challenges in the high temporal variation scenario: 1) A Relative-Pose-Aware Memory module to handle temporal point cloud shape variations; 2) a Base-Expansion Feature Cross-Attention module to deal with similar object distractions in expanded search areas; 3) a Contextual Point Guided Self-Attention module for suppressing heavy background noise. We construct a dataset with high temporal variation (KITTI-HV) by setting different frame intervals for sampling in the KITTI dataset.