Search Results (53)

This paper explores the capability of Large Language Models (LLMs) to perform zero-shot planning through multimodal reasoning, with a particular emphasis on applications to Unmanned Ground Vehicles (UGVs) and unmanned platforms in general. We present a modular system architecture that integrates a general-purpose LLM with visual and spatial inputs for adaptive planning to iteratively guide UGV behavior. Although the framework is demonstrated in a ground-based setting, it directly extends to other unmanned systems, where semantic reasoning and adaptive planning are increasingly critical for autonomous mission execution. To assess performance, we employ a continuous evaluation metric that jointly considers distance and orientation, offering a more informative and fine-grained alternative to binary success measures. We evaluate a foundational LLM (i.e., Gemini 2.0 Flash, Google DeepMind) on a suite of zero-shot navigation and exploration tasks in simulated environments. Unlike prior LLM-robot systems that rely on fine-tuning or learned waypoint policies, we evaluate a purely zero-shot, stepwise LLM planner that receives no task demonstrations and reasons only from the sensed data. Our findings show that LLMs exhibit encouraging signs of goal-directed spatial planning and partial task completion, even in a zero-shot setting. However, inconsistencies in plan generation across models highlight the need for task-specific adaptation or fine-tuning. These findings highlight the potential of LLM-based multimodal reasoning to enhance autonomy in UGV and drone navigation, bridging high-level semantic understanding with robust spatial planning. Full article

3D object detection and tracking technology are increasingly being adopted in unmanned ground vehicles, as robust perception systems significantly improve the obstacle avoidance performance of a UGV. However, most existing algorithms depend heavily on computationally intensive point cloud neural networks, rendering them unsuitable for resource-constrained platforms. In this work, we propose an efficient 3D object detection and tracking method specially designed for deployment on low-cost vehicle platforms. For the detection phase, our method integrates an image-based 2D detector with data fusion techniques to coarsely extract object point clouds, followed by an unsupervised learning approach to isolate objects from noisy point cloud data. For the tracking process, we propose a multi-target tracking algorithm based on multi-level data association. This method introduces an additional data association step to handle targets that fail in 3D detection, thereby effectively reducing the impact of detection errors on tracking performance. Moreover, our method enhances association precision between detection outputs and existing trajectories through the integration of 2D and 3D information, thereby further mitigating the adverse effects of detection inaccuracies. By adopting unsupervised learning as an alternative to complex neural networks, our approach demonstrates strong compatibility with both low-resolution LiDAR and GPU-free computing platforms. Experiments on the KITTI benchmark demonstrate that our tracking framework achieves significant computational efficiency gains while maintaining detection accuracy. Furthermore, experimental evaluations on the real-world UGV platform demonstrated the deployment feasibility of our approach. Full article

In low-risk and open environments, such as farms and mining sites, efficient cargo transportation is essential. Despite the suitability of autonomous driving for these environments, its high deployment and maintenance costs limit large-scale adoption. To address this issue, a modular unmanned ground vehicle (UGV) system is proposed, which is adapted from existing platforms and supports both autonomous and manual control modes. The autonomous mode uses environmental perception and trajectory planning algorithms for efficient transport in structured scenarios, while the manual mode allows human oversight and flexible task management. To mitigate the control latency and execution delays caused by platform modifications, an enhanced transformer-based general dynamics model is introduced. Specifically, the model is trained on a custom-built dataset and optimized within a bicycle kinematic framework to improve control accuracy and system stability. In road tests allowing a positional error of up to 0.5 m, the transformer-based trajectory estimation method achieved 94.8% accuracy, significantly outperforming non-transformer baselines (54.6%). Notably, the test vehicle successfully passed all functional validations in autonomous driving trials, demonstrating the system’s reliability and robustness. The above results demonstrate the system’s stability and cost-effectiveness, providing a potential solution for scalable deployment of autonomous transport in low-risk environments. Full article

In recent years, the rapid development of moving platforms, especially unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), has promoted their widespread applications in various fields such as precision agriculture and formation flight. In these applications, for accurate real-time kinematic positioning between two moving platforms, receiver autonomous integrity monitoring (RAIM) is necessary to assure the reliability of the obtained relative positioning. However, the existing carrier phase-based RAIM (CRAIM) algorithms are mainly a direct extension of pseudorange-based RAIM (PRAIM), whose availability is also a major challenge in signal-harsh environments. Learning from the integrated system between Global Navigation Satellite System (GNSS) and INS and based on a multiple hypothesis solution separation (MHSS) algorithm, we have developed an improved CRAIM algorithm, which combines Beidou Navigation Satellite System (BDS) and INS to offer integrity information for real-time kinematic relative positioning between two moving platforms in challenging environments. To achieve more robust and efficient fault detection and exclusion (FDE) results, an algorithm of observation-domain outlier detection combined with MHSS (OOD-MHSS) is also proposed. In this algorithm, the kinematic relative positioning method with INS addition is performed first, then, based on double-difference (DD) phase observations with known integer ambiguities and the OOD-MHSS method, the integrity monitoring information can be provided for the kinematic relative positioning between two moving platforms. To assess the performance of the OOD-MHSS and the improved CRAIM algorithm, a series of kinematic experiments between different platforms was analyzed and discussed. The results show that the improved CRAIM algorithm can perform effective FDE and provide reliable integrity information, which offers centimeter-level relative position solutions with decimeter-level protection levels (PLs) (integrity budget: ${1\times 10}^{-5}$/h). Both observation outlier detection and INS improve the continuity and availability of kinematic relative positioning and the PLs in horizontal and vertical directions. The PL values have been improved by up to 24.3%, and availability has reached 96.67% in harsh urban areas. This is of great significance for applications requiring higher precision and integrity in kinematic relative positioning. Full article

In recent years, UAV (unmanned aerial vehicle)-UGV (unmanned ground vehicle) collaborative systems have played a crucial role in emergency disaster rescue. To improve rescue efficiency, heterogeneous network and task chain methods are introduced to cooperatively develop rescue sequences within a short time for collaborative systems. However, current methods also overlook resource overload for heterogeneous units and limit planning to a single task chain in cross-platform rescue scenarios, resulting in low robustness and limited flexibility. To this end, this paper proposes Gemini, a cascaded dual-agent deep reinforcement learning (DRL) framework based on the Heterogeneous Service Network (HSN) for multiple task chains planning in UAV-UGV collaboration. Specifically, this framework comprises a chain selection agent and a resource allocation agent: The chain selection agent plans paths for task chains, and the resource allocation agent distributes platform loads along generated paths. For each mission, a well-trained Gemini can not only allocate resources in load balancing but also plan multiple task chains simultaneously, which enhances the robustness in cross-platform rescue. Simulation results show that Gemini can increase rescue effectiveness by approximately 60% and improve load balancing by approximately 80%, compared to the baseline algorithm. Additionally, Gemini’s performance is stable and better than the baseline in various disaster scenarios, which verifies its generalization. Full article

This study deals with a fuel-cell-based power supply system created from a fuel cell stack with a proton exchange membrane fuel cell (PEMFC) and controller monitoring system (Horizon Fuell Cell Technologies (HFCT)). In the fuel cell (FC) stack H60, the reactants are air and hydrogen. Reactants are used for the generation of electricity. The reactants supply fuel cell stacks with hydrogen through the hydrogen supply valve, and redundant reactants are extruded from the region of the 20 fuel cells of the H60 stack through the purge valve, both controlled by an FC controller. The main contribution of this study is the proposal, practical design and integration of an embedded monitoring system into the function of a fuel-cell-based power supply system for monitoring its operation parameters in mobile applications (such as in UGVs—Unmanned Ground Vehicles). The next contribution is the usage of INA226 power monitors for the measurement of input/output parameters in selected parts of the fuel-cell-based power supply system for the evaluation of electrical efficiency or power loss in the system. The third contribution is the integration of Bluetooth technology for the transfer of data from a fuel-cell-based power supply system in a mobile platform to a smartphone or PC for monitoring and data processing. At the end of this study, the computed efficiency values of the fuel cell stack, controller and switching power supply outputs are analysed, and the advantages, disadvantages and practical experience are summarized. Full article

Future smart cities will consist of a heterogeneous environment, including UGVs (Unmanned Ground Vehicles) and UAVs (Unmanned Aerial Vehicles), used for different applications such as last mile delivery. Considering the vulnerabilities of GNSS (Global Navigation System Satellite) in urban environments, a resilient PNT (Position, Navigation, Timing) solution is needed. A key research question within the PNT community is the capability to deliver a robust and resilient time solution to multiple devices simultaneously. The paper is proposing an innovative time dissemination framework, based on IQuila’s SDN (Software Defined Network) and quantum random key encryption from Quantum Dice to multiple users. The time signal is disseminated using a wireless IEEE 802.11ax, through a wireless AP (Access point) which is received by each user, where a KF (Kalman Filter) is used to enhance the timing resilience of each client into the framework. Each user is equipped with a Jetson Nano board as CC (Companion Computer), a GNSS receiver, an IEEE 802.11ax wireless card, an embedded RTC (Real Time clock) system, and a Pixhawk 2.1 as FCU (Flight Control Unit). The paper is presenting the performance of the fusion framework using the MUEAVI (Multi-user Environment for Autonomous Vehicle Innovation) Cranfield’s University facility. Results showed that an alternative timing source can securely be delivered fulfilling last mile delivery requirements for aerial platforms achieving sub millisecond offset. Full article

The autonomous navigation of unmanned ground vehicles (UGVs) in unstructured environments, such as agricultural or forestry settings, has been the subject of extensive research by various investigators. The navigation capability of a UGV in unstructured environments requires considering numerous factors, including the quality of data reception that allows reliable interpretation of what the UGV perceives in a given environment, as well as the use these data to control the UGV’s navigation. This article aims to study different PID control algorithms to enable autonomous navigation on a robotic platform. The robotic platform consists of a forestry tractor, used for forest cleaning tasks, which was converted into a UGV through the integration of sensors. Using sensor data, the UGV’s position and orientation are obtained and utilized for navigation by inputting these data into a PID control algorithm. The correct choice of PID control algorithm involved the study, analysis, and implementation of different controllers, leading to the conclusion that the Vector Field control algorithm demonstrated better performance compared to the others studied and implemented in this paper. Full article

This paper considers the swarm confrontation problem for two teams of unmanned ground vehicles (UGVs). Different from most of the existing works where the two teams are identical, we consider the scenario of two heterogenous teams. In particular, one team has the quantity advantage while the other has the resilience advantage. Nevertheless, it is verified by standard tests to show that the overall capabilities of these two heterogenous teams are almost the same. The objective of this article is to design a swarm confrontation algorithm for the team with quantity advantage based on the multi-agent reinforcement learning training method. To address the issue of sparse reward which would result in inefficient learning and poor training performance, a novel macro states reward mechanism based on multi-agent posthumous credit assignment (MSRM-MAPOCA) is proposed in this paper, which together with fine-tuned smooth reward design can fully exploit the advantage in quantity and thus leads to outstanding training performance. Based on the Unity 3D platform, comprehensive direct and indirect comparative tests have been conducted, where the results show that the swarm confrontation algorithm proposed in this article triumphs over other classic or up-to-date swarm confrontation algorithms in terms of both win rate and efficiency. Full article

In this paper, we propose an adaptive fuzzy pure pursuit trajectory tracking algorithm for autonomous unmanned ground vehicles (UGVs), addressing the challenges of accurate and stable navigation in complex environments. Traditional pure pursuit methods with fixed look-ahead distances struggle to maintain precision in dynamic and uneven terrains. Our approach uniquely integrates a fuzzy control algorithm that allows for real-time adjustments of the look-ahead distance based on environmental feedback, thereby enhancing tracking accuracy and smoothness. Additionally, we combine this with model predictive control (MPC) and whole-body motion control (WBC), where MPC forecasts future states and optimally adjusts control actions, while WBC ensures coordinated motion of the UGV, maintaining balance and stability, especially in rough terrains. This integration not only improves responsiveness to changing conditions but also enables dynamic balance adjustments during movement. The proposed algorithm was validated through simulations in Gazebo and real-world experiments on physical platforms. In real-world tests, our algorithm reduced the average trajectory tracking error by 45% and the standard deviation by nearly 50%, significantly improving stability and accuracy compared to traditional methods. Full article

The heterogeneous unmanned system, which is composed of unmanned aerial vehicles (UAV) and unmanned ground vehicles (UGV), has been broadly applied in many domains. Collaborative fault diagnosis (CFD) among UAVs and UGVs has become a key technology in these unmanned systems. However, collaborative fault diagnosis in unmanned systems faces the challenges of the dynamic environment and limited communication bandwidth. This paper proposes an event-triggered collaborative fault diagnosis framework for the UAV–UGV system. The framework aims to achieve autonomous fault monitoring and cooperative diagnosis among unmanned systems, thus enhancing system security and reliability. Firstly, we propose a fault trigger mechanism based on broad learning systems (BLS), which utilizes sensor data to accurately detect and identify faults. Then, under the dynamic event triggering mechanism, the network communication topology between the UAV–UGV system and BLS is used to achieve cooperative fault diagnosis. To validate the effectiveness of our proposed scheme, we conduct experiments on a software-in-the-loop (SIL) simulation platform. The experimental results demonstrate that our method achieves high diagnosis accuracy for the UAV–UGV system. Full article

In this paper, we propose a three-layer distributed simulation network architecture, which consists of a distributed virtual simulation network, a perception and control subnetwork, and a cooperative communication service network. The simulation architecture runs on a distributed platform, which can provide unique virtual scenarios and multiple simulation services for the verification of basic perception, control, and planning algorithms of a single-robot system and can verify the distributed collaboration algorithms of heterogeneous multirobot systems. Further, we design simulation experimental scenarios for classic heterogeneous robotic systems such as unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs). Through the analysis of experimental measurement data, we draw several important conclusions: firstly, the replication time characteristics and update frequency characteristics of entity synchronization in our system indicate that the replication time of entity synchronization in our system is relatively short, and the update frequency can meet the needs of multirobot collaboration and ensure the real-time use and accuracy of the system; secondly, we analyze the bandwidth usage of data frames in the whole session and observe that the server side occupies almost half of the data throughput during the whole session, which indicates that the allocation and utilization of data transmission in our system is reasonable; and finally, we construct a bandwidth estimation surface model to estimate the bandwidth requirements of the current model when scaling the server-side scale and synchronization-state scale, which provides an important reference for better planning and optimizing of the resource allocation and performance of the system. Based on this distributed simulation framework, future research will improve the key technical details, including further refining the coupling object dynamic model update method to support the simulation theory of the coupling relationship between system objects, studying the impact of spatiotemporal consistency of distributed systems on multirobot control and decision making, and in-depth research on the impact of collaborative frameworks combined with multirobot systems for specific tasks. Full article

This research presents a cooperation strategy for a heterogeneous group of robots that comprises two Unmanned Aerial Vehicles (UAVs) and one Unmanned Ground Vehicles (UGVs) to perform tasks in dynamic scenarios. This paper defines specific roles for the UAVs and UGV within the framework to address challenges like partially known terrains and dynamic obstacles. The UAVs are focused on aerial inspections and mapping, while UGV conducts ground-level inspections. In addition, the UAVs can return and land at the UGV base, in case of a low battery level, to perform hot swapping so as not to interrupt the inspection process. This research mainly emphasizes developing a robust Coverage Path Planning (CPP) algorithm that dynamically adapts paths to avoid collisions and ensure efficient coverage. The Wavefront algorithm was selected for the two-dimensional offline CPP. All robots must follow a predefined path generated by the offline CPP. The study also integrates advanced technologies like Neural Networks (NN) and Deep Reinforcement Learning (DRL) for adaptive path planning for both robots to enable real-time responses to dynamic obstacles. Extensive simulations using a Robot Operating System (ROS) and Gazebo platforms were conducted to validate the approach considering specific real-world situations, that is, an electrical substation, in order to demonstrate its functionality in addressing challenges in dynamic environments and advancing the field of autonomous robots. Full article

The paper presents a study of the performance and development of unmanned ground vehicles (UGVs), establishing mathematical and numerical models of the chassis system. The model analysis is performed by 3D software package SolidWorks 2018 with finite element discretization. The mesh modelling and analysis are focused on studying the strength and stiffness of the robotic platform chassis and the distribution of stress and deformation in the extremal condition. The paper also presents an autopilot design with a new cascade control system for the autonomous motion of an unmanned ground vehicle based on proportional–integral–derivative (PID) and feedforward (FF) control. The PID-FF controller is part of a UGV used in a hybrid control system for precise control and stabilization, which is necessary to increase the vehicle motion stability and maneuver precision. The hybrid PID-FF control system proposed for the ground vehicle model gives satisfactory control quality while maintaining the simplicity of the control system. The presented tests performed in mechanical design and control analysis give good results and prove the usefulness of the designed unmanned device. Full article

The introduction of Unmanned Ground Vehicles (UGVs) into the field of rescue operations is an ongoing process. New tools, such as UGV platforms and dedicated manipulators, provide new opportunities but also come with a steep learning curve. The best way to familiarize operators with new solutions are hands-on courses but their deployment is limited, mostly due to high costs and limited equipment numbers. An alternative way is to use simulators, which from the software side, resemble video games. With the recent expansion of the video game engine industry, currently developed software becomes easier to produce and maintain. This paper tries to answer the question of whether it is possible to develop a highly accurate simulator of a rescue and IED manipulator using a commercially available game engine solution. Firstly, the paper describes different types of simulators for robots currently available. Next, it provides an in-depth description of a plug-in simulator concept. Afterward, an example of a hydrostatic manipulator arm and its virtual representation is described alongside validation and evaluation methodologies. Additionally, the paper provides a set of metrics for an example rescue scenario. Finally, the paper describes research conducted in order to validate the representation accuracy of the developed simulator. Full article