Real-time following algorithm for the Unmanned Ground Vehicle using visual and spatial features

Advancements in technology and intelligence, as well as deliberate targeting of medical personnel and vehicles, have made casualty extraction increasingly hazardous. The Russo-Ukrainian War has further demonstrated that the rapid development of unmanned technologies may also enable novel approaches. Although some of these systems have been deployed, reporting on their performance is scarce and understandably incomplete, which limits their evidence-based and effective integration with fighting forces. This paper addresses this gap by presenting preliminary findings on potential ranges of evacuation unmanned ground vehicles (UGVs) utilisation. A virtual simulation experiment was conducted, where a platoon defended against a mechanised infantry company. The experiment was a repeated military exercise with different groups of participants. The defending force had evacuation UGVs, which were placed close behind the defensive line. The aim was to determine whether UGVs could survive long enough to support evacuation and whether evacuation could be carried out before the conflict ended. Furthermore, the availability of UGVs and the likelihood that an evacuation attempt could avoid enemy interference were assessed. The experiment involved 470 participants divided into 11 groups. Each participant completed four combat scenarios. Players of each group switched sides and environments. In total, 44 instances of skirmishes were fought in a virtual simulation environment. The simulation results indicated UGV loss rate of 53%. Evacuations were attempted in 45% of skirmishes. Furthermore, 81% of initiated evacuation attempts were successful. The experiment provided estimates of evacuation UGV loss rates near the defence line amid active conflict. It also offered evidence on the feasibility of initiating evacuation before the active conflict had fully ceased, and the likelihood of the moving evacuation vehicle encountering enemy fire. These findings can guide decisions on whether the risk of losing small evacuation vehicles and their equipment is acceptable when deployed near front lines.

Abstract. Simultaneous Localisation and Mapping (SLAM) is a technique that allows a vehicle to determine its location and map its surroundings simultaneously. This study was carried out to produce a 3-dimensional (3D) model of the environment using the SLAM technique by processing the data obtained from Light Detection and Ranging (LiDAR) and stereo camera sensors mounted on an Unmanned Ground Vehicle (UGV) capable of operating in an indoor-outdoor area. The environment was modelled using LiDAR-SLAM and Visual Simultaneous Localisation and Mapping (VSLAM) methods, using the LiDAR sensor and the stereo camera integrated into the UGV. The accuracy assessment of the produced models was made by comparing the real sizes of the objects in the environment with the sizes in the produced model. In addition, the model’s surface accuracies were tested by examining the linearity of flat surfaces selected from the study area.

Drivable area (DA) detection in unstructured off-road environments remains challenging for unmanned ground vehicles (UGVs) due to limited field-of-view, persistent occlusions, and the inherent limitations of individual sensors. While existing fusion approaches combine aerial and ground perspectives, they often struggle with misaligned spatiotemporal viewpoints, dynamic environmental changes, and ineffective feature integration, particularly at intersections or under long-range occlusion. To address these issues, this paper proposes a cooperative air–ground perception framework based on multi-source data fusion. Our three-stage system first introduces DynCoANet, a semantic segmentation network incorporating directional strip convolution and connectivity attention to extract topologically consistent road structures from UAV imagery. Second, an enhanced particle filter with semantic road constraints and diversity-preserving resampling achieves robust cross-view localization between UAV maps and UGV LiDAR. Finally, a distance-adaptive fusion transformer (DAFT) dynamically fuses UAV semantic features with LiDAR BEV representations via confidence-guided cross-attention, balancing geometric precision and semantic richness according to spatial distance. Extensive evaluations demonstrate the effectiveness of our approach: on the DeepGlobe road extraction dataset, DynCoANet attains an IoU of 61.14%; cross-view localization on KITTI sequences reduces average position error by approximately 10%; and DA detection on OpenSatMap outperforms Grid-DATrNet by 8.42% in accuracy for large-scale regions (400 m × 400 m). Real-world experiments with a coordinated UAV-UGV platform confirm the framework’s robustness in occlusion-heavy and geometrically complex scenarios. This work provides a unified solution for reliable DA perception through tightly coupled cross-modal alignment and adaptive fusion.

The rapid evolution of radar-based surveillance and targeting systems poses significant challenges to the survivability of unmanned ground vehicles (UGVs) operating in contested electromagnetic environments. This study presents the implementation framework of a wideband Radar Electronic Countermeasure–Electronic Counter-Countermeasure (ECM–ECCM) system integrated into an NRSM-class UGV, operating across a frequency range of 27 MHz to 10 GHz. The proposed system adopts a modular and software-defined architecture, enabling adaptive threat detection, real-time response, and electromagnetic resilience. The research focuses on system design, integration methodology, and performance evaluation using defined electronic warfare metrics. The results demonstrate that wideband ECM–ECCM integration significantly enhances UGV survivability and operational effectiveness against modern radar threats.

Digital-twins and machine learning-assisted stable, energy-aware unmanned aerial and ground vehicles delivery in blockchain-enabled crowdsourcing framework

Optimization strategy for longitudinal slip characteristics of unmanned ground vehicles with variable structures

Adaptive neural network fixed-time formation control of unmanned ground vehicles

At present, the UWB-assisted VIO scheme only uses range measurements to estimate the anchor position. The accuracy of the anchor location estimation algorithm can be affected by factors such as the trajectory being a straight line or having a small curvature, as well as changes in multi-observation noise. To address these problems, we propose an adaptive UWB anchor location estimation algorithm leveraging Unmanned Ground Vehicle (UGV) multi-source observations. The key innovations include the following: (1) a novel anchor initialization method that incorporates both distance and angles, including azimuth and elevation measurements, to overcome the limitation of the approach that relies solely on range for straight or small-curvature trajectories; (2) an adaptive nonlinear optimization anchor location estimation algorithm that dynamically adjusts measurement weights and addresses the accuracy decreasing under time-varying noise characteristics in both distance and angle measurements caused by environmental disturbances. In this paper, the robustness and anchor position estimation accuracy of the proposed algorithm are validated through simulation and UGV real experiments.

The variable-configuration wheel-track unmanned ground vehicle (VCWT-UGV) can adapt to complex environments with advantages of high maneuverability and strong passing ability. The analysis of steering dynamics characteristics is the theoretical basis to ensure UGVs can still maintain high maneuverability in different environments. This article proposes a universal steering dynamic modeling for UGVs and an efficient driving strategy suitable for VCWT-UGV, starting from requirements of analyzing steering dynamics characteristics. Firstly, based on the operation environments and the characteristics of the wheel-track composite locomotion mechanism (WTCLM), the normal balance during steady-state steering process on soft soil is established; Secondly, based on the model, the steering dynamics characteristics of traditional three axle-wheeled UGV and VCWT-UGV were compared; Then, the optimal driving strategy is designed combined with the analysis results based on the motion mode and driving configuration. Finally, the simulation and test results demonstrate the accuracy of the model and the feasibility of strategies. The combination of wheel-track and variable-configuration can significantly improve the lateral mobility. Under the premise of maintaining the same driving configuration, by adjusting the moving mode, the critical load for slip has been increased by 40%, the sinkage depth has been reduced by 33% and the traction has been increased by 16.8%. In addition, considering the steering path and time, without changing the differential input, the steering radius is increased or decreased by 16.7% by adjusting the driving configuration, and the corresponding steering time is also optimized. The research results provide valuable references for the general dynamic modeling methods of UGVs.

In Global Navigation Satellite System (GNSS)-denied urban environments, unmanned ground vehicles (UGVs) face significant difficulties in maintaining reliable localization due to occlusion and structural complexity. Unmanned aerial vehicles (UAVs), with their global perspective, provide complementary information for cross-view matching and localization of UGVs. However, robust cross-view matching and localization are hindered by geometric distortions, semantic inconsistencies, and the lack of stable spatial anchors, limiting the effectiveness of conventional methods. To overcome these challenges, we proposed a cross-view matching and localization (CVML) framework that contains two components. The first component is the Vision-Language Model (VLM)-guided and spatially consistent cross-view matching network (VSCM-Net), which integrates two novel attention modules. One is the VLM-guided positional correction module that leverages semantic cues to refine the projected UGV image within the UAV map, and the other is the shape-aware attention module that enforces topological consistency across ground and aerial views. The second component is a ground-to-aerial mapping module that projects cross-view correspondences from the UGV image onto the UAV-stitched map, thereby localizing the capture position of the UGV image and enabling accurate trajectory-level localization and navigation. Extensive experiments on public and self-collected datasets demonstrate that the proposed method achieves superior accuracy, robustness, and real-world applicability compared with state-of-the-art methods in both cross-view image matching and localization.

Unmanned Aerial Vehicles (UAVs) play crucial roles across various fields but face significant challenges when control is lost or securing a safe runway is not feasible. Under these circumstances, reliable UAV recovery systems are essential for safe retrieval, requiring precise and real-time localization. This paper proposes an automatic in-fight UAV recovery system using an unmanned ground vehicle when securing a safe runway is challenging such as unstructured road, and presents a practical approach for real-time six-degree-of-freedom (6-DOF) pose estimation of an in-flight UAV using monocular RGB images and deep learning-based heatmap keypoint detection. To enhance the accuracy of the pose estimation, we propose an Adaptive Sigma technique for keypoint detection, which adjusts the sigma values of the keypoint heatmap based on the distance between the camera and the UAV. Thus, the proposed method can robustly adapt to changes in the distance of UAV to improve the keypoint localization performance. By utilizing the predicted keypoints in a Perspective-n-Point algorithm, the 6-DOF pose information of the UAV can be obtained in real time. The proposed Adaptive Sigma to heatmap-based keypoint detection improves the Percentage of Correct Keypoints by up to 2.5%, with consistently high performance across various state-of-the-art backbone architectures. The proposed method qualitatively evaluated in challenging scenarios such as various altitudes, significant tilt, and motion blur.

This study proposes a keypoint-based structural anomaly analysis system using Electro-Optical(EO) sensors mounted on unmanned ground vehicles. Unlike conventional object detection approaches, which struggle to interpret fine-grained structural deviations, the proposed method extracts keypoints of components and evaluates their geometric relationships—such as relative height ratios and tilt angles—to assess structural integrity. A three-stage pipeline consisting of object detection, keypoint detection, and post-processing validation is implemented. Experiments under various rotated conditions (0°, 90°, 135°, and 180°) show that the proposed method achieves error rates below 0.5 %, significantly outperforming conventional bounding box-based methods, which show over 50 % error. The system also demonstrates strong robustness against occlusion, viewpoint variation, and partial visibility. These results highlight the system's potential for real-time autonomous diagnostics, predictive maintenance, and quantitative evidence-based monitoring in dynamic field environments.

Autonomous exploration in unknown, unstructured environments is critical for unmanned ground vehicles (UGVs) in applications like disaster rescue. While search-based methods are suitable for such settings, they often struggle with balancing nonholonomic constraints, exploration efficiency, and mission-specific goals such as target detection and return. This paper introduces a search-based path planning algorithm that addresses these challenges through multi-heuristic fusion and integrated real-time perception. Our approach features three key innovations: (1) a frontier point evaluation function that fuses information gain with Reeds-Shepp curve cost to ensure kinematic feasibility; (2) a multi-heuristic search strategy adopting a minimum-cost priority rule, which dynamically combines wavefront distance (for obstacle avoidance) and RS curve length (for kinematic constraints), incorporating a conflict-resolution mechanism to escape local minima; and (3) a closed-loop "detection-replanning-return" framework, where a YOLOv5s-based visual detector triggers a safe return upon target identification, leveraging LiDAR, GNSS, and IMU data. Extensive validation in simulation (ROS/V-REP) and real-world off-road scenarios (100×500 m) demonstrates the algorithm's robustness and efficiency. It reduces the number of expanded nodes to only 1.38% of a baseline method, with an average planning time of 99 ms. Real-vehicle tests achieved a personnel localization error of 0.327 m and sustained a planning frequency of 12.2-17.2 Hz, demonstrating superior reliability in complex navigation tasks. This work provides a comprehensive and practical solution for autonomous exploration and search-and-rescue missions in complex unknown environments.

Technical study on the efficiency and models of weed control methods using unmanned ground vehicles: A review

Collaborative control strategy of optimal trajectory tracking and braking energy recovery for unmanned ground vehicles

Dynamic path planning for multiple unmanned ground vehicles based on improved dynamic window approach

Low-altitude remote sensing and deep learning-based canopy detection method for the navigation of orchard unmanned ground vehicles

<div>With the rapid development of autonomous driving technology, unmanned ground vehicles (UGVs) are gradually replacing humans to perform tasks such as reconnaissance, target tracking, and search in special scenarios. Omnidirectional mobility based on rapid adjustment of vehicle heading posture enhances the applicability of UGVs in specialized scenarios. Omnidirectional mobility signifies the capability for rapid adjustments to the vehicle’s heading angle, longitudinal velocity, and lateral velocity. Traditional vehicles are constrained by the limitations of under-actuation, which prevents active regulation of lateral movement. Instead, they rely on the coordinated regulation of longitudinal and yaw movements, failing to meet the requirements for omnidirectional mobility. Distributed vehicles featuring steering distributed between the front/rear axles and four-wheel independent drive leverage the over-actuation advantages provided by multi-actuator coordinated control, making them particularly suitable for omnidirectional mobility at large sideslip angles. This feature enables the UGVs to achieve rapid adjustment of vehicle heading posture. However, existing control strategies centered on stabilizing yaw rate and suppressing sideslip angles cannot adapt to the decoupling control requirements of such platforms. Additionally, the strong coupling characteristics between actuator subsystems further exacerbate control difficulties. To this end, this article proposes a full-state decoupling motion control strategy, the nonlinear model is locally linearized at each equilibrium point of the vehicle, and a set of equilibrium state models is derived. The validity of this local linearization method is verified through phase diagram analysis and modal analysis. The Bayesian optimization (BO) algorithm is then employed to optimize and identify the cornering stiffness of the front/rear axles at each equilibrium point in these locally linearized models, thereby enhancing the characterization ability of the linear model for the nonlinear dynamic model at the corresponding equilibrium points. Subsequently, a full-state decoupling motion controller is designed by integrating the model predictive control (MPC) algorithm. Finally, the controller presented in this article is employed on the distributed vehicle experiment platform (DVEP). The experimental results demonstrate that in two drift-like scenarios with different sideslip angles, compared with the baseline controller, the path tracking error of this method is reduced by more than 13%, and the sideslip angle tracking error is reduced by more than 12%.</div>

The inspection of concrete box girders presents significant challenges due to their variable cross-sections and signal occlusion characteristics. To address these issues, this paper proposes an autonomous damage detection method for the roof of variable cross-section concrete box girders based on an unmanned ground vehicle (UGV). First, a comprehensive analysis of the concrete box girder environment is conducted and a robotic system is designed accordingly. Then a 3D mapping process is performed using a LiDAR-based SLAM algorithm, forming the foundation for inspection task planning. The system generates robot navigation waypoints and optimises path planning to ensure efficient coverage. To enhance detection accuracy for variable cross-section girder roofs, an image acquisition method is developed by integrating robot localisation, motion control, and camera coordination. Subsequently, instance segmentation model is employed for damage identification. Finally, experimental validation is conducted on a real bridge, demonstrating an average reconstruction error of 0.464 m, with the damage detection model achieving a Box (mAP@0.5) accuracy of 84.5% and a Mask (mAP@0.5) accuracy of 71.9%. The results confirm that the proposed method provides an effective automated solution for the inspection of internal concrete box girder roofs.