Unmanned Ground Vehicle Research Articles

Deep reinforcement learning and ant colony optimization supporting multi‐UGV path planning and task assignment in 3D environments

AbstractWith the development of artificial intelligence, the application of unmanned ground vehicles (UGV) in outdoor hazardous scenarios has received more attention. However, the terrains in these environments are often complex and undulating, which also pose higher challenges to the multi‐UGV path planning and task assignment (MUPPTA) optimization. To efficiently improve the multi‐UGV collaboration in 3D environments, a MUPPTA method is proposed based on double deep Q learning network (DDQN) and ant colony optimization (ACO) to jointly optimize the path planning and task assignment decisions of multiple UGVs. The authors first comprehensively consider the characteristics of the 3D environments, and model the MUPPTA problem as a combinatorial optimization problem. To tackle it, the original problem is decomposed into the multi‐UGV path planning sub‐problem and task assignment sub‐problem, and solve them separately. First, the path planning sub‐problem in the 3D environments is transformed into a Markov decision process (MDP) model, and a multi‐UGV path planning algorithm based on DDQN (MUPP‐DDQN) is proposed to obtain the optimal paths and actual path costs between tasks through extensive offline learning and training. Based on this, a multi‐UGV task assignment algorithm is further proposed based on ACO (MUTA‐ACO) to solve the task assignment sub‐problem and achieve the optimal task assignment solution. Simulation results show that the proposed method is more cost‐effective and time‐saving compared to other comparison algorithms.

Unmanned ground vehicle (UGV) based automated construction progress measurement of road using LSTM

PurposeCurrent solutions for monitoring the progress of pavement construction (such as collecting, processing and analysing data) are inefficient, labour-intensive, time-consuming, tedious and error-prone. In this study, an automated solution proposes sensors prototype mounted unmanned ground vehicle (UGV) for data collection, an LSTM classifier for road layer detection, the integrated algorithm for as-built progress calculation and web-based as-built reporting.Design/methodology/approachThe crux of the proposed solution, the road layer detection model, is proposed to develop from the layer change detection model and rule-based reasoning. In the beginning, data were gathered using a UGV with a laser ToF (time-of-flight) distance sensor, accelerometer, gyroscope and GPS sensor in a controlled environment. The long short-term memory (LSTM) algorithm was utilised on acquired data to develop a classifier model for layer change detection, such as layer not changed, layer up and layer down.FindingsIn controlled environment experiments, the classification of road layer changes achieved 94.35% test accuracy with 14.05% loss. Subsequently, the proposed approach, including the layer detection model, as-built measurement algorithm and reporting, was successfully implemented with a real case study to test the robustness of the model and measure the as-built progress.Research limitations/implicationsThe implementation of the proposed framework can allow continuous, real-time monitoring of road construction projects, eliminating the need for manual, time-consuming methods. This study will potentially help the construction industry in the real time decision-making process of construction progress monitoring and controlling action.Originality/valueThis first novel approach marks the first utilization of sensors mounted UGV for monitoring road construction progress, filling a crucial research gap in incremental and segment-wise construction monitoring and offering a solution that addresses challenges faced by Unmanned Aerial Vehicles (UAVs) and 3D reconstruction. Utilizing UGVs offers advantages like cost-effectiveness, safety and operational flexibility in no-fly zones.

Location Selection Methods for Urban Terminal Co-Distribution Centers with Air–Land Collaboration

Urban terminal logistics and distribution enterprises face the problems of duplicated network layouts, high costs, and inefficient urban environments. Recently, collaborative distribution using unmanned aerial vehicles (UAVs) and ground vehicles has been considered as a means of reducing costs and enhancing efficiency, thus overcoming the issues created by the high-density layout of enterprises’ relatively independent networks. This essentially involves constructing an air–ground collaborative common distribution network. To optimize the economic cost and distribution time of network operations, we established a site selection planning model for air–ground cooperative urban co-distribution centers and designed a solution method based on gray wolf optimization with K-means clustering. Taking the Wangsheren area of Jinan City, China, as an example, 15 UAV co-distribution centers and 13 vehicle co-distribution centers were identified. Although the average distribution cost of the network rose by 35–50% compared to traditional terminal distribution, the time saving was 80–85%, greatly improving the high-value-added service capacity. The end-distribution efficiency and customer satisfaction were also enhanced, which fully verifies the feasibility, validity, and applicability of the proposed model. Our approach can be applied to landing sites and the planning and optimization of large-scale commercial operations using logistics UAVs in urban areas.

Modeling swarm mission with COTS characterization: a series of return on experience

AbstractSystem design in defense systems is a competitive field, in which economical viability relies on a sequence of architectural decisions, aiming at quality, resource and time (Q,R,T) compromises. We observe that low‐cost unmanned ground vehicles (UGV) and drones appear as new threats on current battlefield. To face these new threats, Direction Générale de l'Armement (DGA) have organized challenges around robotization of battlefield, to design future employment doctrines and help technologies to reach maturity in a reasonable time. This article exposes a NATO Architecture Framework (NAF) 3.1‐based workflow that includes return of experience form the field over yearly iterations of such challenges. The capabilities depicted are requirements to match, constituent systems are based on Components‐Off‐The‐Shelf (COTS) answering to both edition of the challenge. This article details how manually re‐injecting feedback from field back to the system model failed to ensure the next iterations of the challenge. Our works propose conclusions on formulation of the “engineering leakage problem” and how resolution of this problem is NP‐Hard and should be addressed using optimization.

An Autonomous Unmanned Ground Vehicle: A Technology Driven Approach for Spraying Agrochemicals in Agricultural Crops

The application of chemicals through spraying is an essential component of agricultural management systems. However, the use of these chemical products results in the accumulation of residues in the soil, leading to a decline in soil fertility and plant diversity. Additionally, farmers who manually spray pesticides onto their crop fields are at risk of developing health issues such as tumors, hypersensitivity, allergies, and skin diseases. As the global population continues to grow and climate change impacts farmland ecosystems, the occurrence of pest epidemics in crops is becoming more frequent. Consequently, there is a greater demand for enhanced tools and methods to improve crop production. Unmanned ground vehicles (UGVs) have the potential to revolutionize agricultural spraying by offering efficient and effective applications of crop protection agrochemicals. This article provides an overview and consolidation of the present research and advancements in UGV application technologies and different sensors that are specifically designed for spray applications of agrichemicals. It examines the features of both hardware and software architecture for implementing control strategies, obstacle detection, and avoidance systems with real-time integrated systems, and the ability to perform variable-rate agrochemical applications.

An Enhanced-LiDAR/UWB/INS Integrated Positioning Methodology for Unmanned Ground Vehicle in Sparse Environments

An Enhanced-LiDAR/UWB/INS Integrated Positioning Methodology for Unmanned Ground Vehicle in Sparse Environments

Unmanned Ground Vehicle Path Planning Based on Improved DRL Algorithm

Path planning and obstacle avoidance are fundamental problems in unmanned ground vehicle path planning. Aiming at the limitations of Deep Reinforcement Learning (DRL) algorithms in unmanned ground vehicle path planning, such as low sampling rate, insufficient exploration, and unstable training, this paper proposes an improved algorithm called Dual Priority Experience and Ornstein–Uhlenbeck Soft Actor-Critic (DPEOU-SAC) based on Ornstein–Uhlenbeck (OU noise) and double-factor prioritized sampling experience replay (DPE) with the introduction of expert experience, which is used to help the agent achieve faster and better path planning and obstacle avoidance. Firstly, OU noise enhances the agent’s action selection quality through temporal correlation, thereby improving the agent’s detection performance in complex unknown environments. Meanwhile, the experience replay is based on double-factor preferential sampling, which has better sample continuity and sample utilization. Then, the introduced expert experience can help the agent to find the optimal path with faster training speed and avoid falling into a local optimum, thus achieving stable training. Finally, the proposed DPEOU-SAC algorithm is tested against other deep reinforcement learning algorithms in four different simulation environments. The experimental results show that the convergence speed of DPEOU-SAC is 88.99% higher than the traditional SAC algorithm, and the shortest path length of DPEOU-SAC is 27.24, which is shorter than that of SAC.

Robust Autonomous Mobile Manipulation for Substation Inspection

Abstract The need for autonomous infrastructure inspections performed by mobile robots is becoming increasingly prevalent, to mitigate human error and inspect critical infrastructure with increased frequency, while reducing costs. Electric distribution substations contain a variety of high-power equipment that may occasionally fail, and we focus on inspecting pothead compartments as a representative test case. Frequent measurements of acoustic and transient earth voltage data can indicate degradation before failures occur. Handheld partial discharge (PD) sensors can gather these types of data. Measurements using PD sensors can be automated using a mobile manipulation platform with a custom end-effector. Accurate mapping, localization, and navigation are required to perform autonomous inspection tasks in indoor environments with unmanned ground vehicles. Computer vision and precise manipulator control are necessary for successful handheld sensor interactions. In this paper, we present and analyze a custom-integrated mobile manipulation system capable of performing these functions, which achieves a tradeoff between the small size needed to navigate through low-clearance areas, and the reach capabilities needed to collect the required measurements from pothead compartments.

Conceptual Design of an Unmanned Electrical Amphibious Vehicle for Ocean and Land Surveillance

Unmanned vehicles (UVs) have become increasingly important in various scenarios of civil and military operations. The present work aims at the conceptual design of a modular Amphibious Unmanned Ground Vehicle (A-UGV) that can be easily adapted for different types of land and/or water missions with low monetary cost (EUR < 5 k, without sensors). Basing the design on the needs highlighted in the 2021 review of the Strategic Directive of the Portuguese Navy, the necessary specifications and requirements are established for two mission scenarios. Then, a market research analysis focused on vehicles currently available and their technological advances is conducted to identify existing UV solutions and respective characteristics/capabilities of interest to the current work. To study and define the geometry of the hull and the configuration of the A-UGV itself, preliminary computational structural and fluid analyses are carried out to ensure it complies with the specifications initially established. As a result, one obtains a fully electric vehicle with approximate dimensions of 1050 × 670 × 450 mm (length–width–height), enabled with 6 × 6 traction capable of reaching 20 km/h on land, which possesses amphibious capabilities of independent propulsion in water up to 8 kts and an estimated autonomy of over 60 min.

Enhancing unmanned ground vehicle performance in SAR operations: integrated gesture-control and deep learning framework for optimised victim detection.

In this study, we address the critical need for enhanced situational awareness and victim detection capabilities in Search and Rescue (SAR) operations amidst disasters. Traditional unmanned ground vehicles (UGVs) often struggle in such chaotic environments due to their limited manoeuvrability and the challenge of distinguishing victims from debris. Recognising these gaps, our research introduces a novel technological framework that integrates advanced gesture-recognition with cutting-edge deep learning for camera-based victim identification, specifically designed to empower UGVs in disaster scenarios. At the core of our methodology is the development and implementation of the Meerkat Optimization Algorithm-Stacked Convolutional Neural Network-Bi-Long Short Term Memory-Gated Recurrent Unit (MOA-SConv-Bi-LSTM-GRU) model, which sets a new benchmark for hand gesture detection with its remarkable performance metrics: accuracy, precision, recall, and F1-score all approximately 0.9866. This model enables intuitive, real-time control of UGVs through hand gestures, allowing for precise navigation in confined and obstacle-ridden spaces, which is vital for effective SAR operations. Furthermore, we leverage the capabilities of the latest YOLOv8 deep learning model, trained on specialised datasets to accurately detect human victims under a wide range of challenging conditions, such as varying occlusions, lighting, and perspectives. Our comprehensive testing in simulated emergency scenarios validates the effectiveness of our integrated approach. The system demonstrated exceptional proficiency in navigating through obstructions and rapidly locating victims, even in environments with visual impairments like smoke, clutter, and poor lighting. Our study not only highlights the critical gaps in current SAR response capabilities but also offers a pioneering solution through a synergistic blend of gesture-based control, deep learning, and purpose-built robotics. The key findings underscore the potential of our integrated technological framework to significantly enhance UGV performance in disaster scenarios, thereby optimising life-saving outcomes when time is of the essence. This research paves the way for future advancements in SAR technology, with the promise of more efficient and reliable rescue operations in the face of disaster.

Autonomous Exploration Method of Unmanned Ground Vehicles Based on an Incremental B-Spline Probability Roadmap.

Autonomous exploration in unknown environments is a fundamental problem for the practical application of unmanned ground vehicles (UGVs). However, existing exploration methods face difficulties when directly applied to UGVs due to limited sensory coverage, conservative exploration strategies, inappropriate decision frequencies, and the non-holonomic constraints of wheeled vehicles. In this paper, we present IB-PRM, a hierarchical planning method that combines Incremental B-splines with a probabilistic roadmap, which can support rapid exploration by a UGV in complex unknown environments. We define a new frontier structure that includes both information-gain guidance and a B-spline curve segment with different arrival orientations to satisfy the non-holonomic constraint characteristics of UGVs. We construct and maintain local and global graphs to generate and store filtered frontiers. By jointly solving the Traveling Salesman Problem (TSP) using these frontiers, we obtain the optimal global path traversing feasible frontiers. Finally, we optimize the global path based on the Time Elastic Band (TEB) algorithm to obtain a smooth, continuous, and feasible local trajectory. We conducted comparative experiments with existing advanced exploration methods in simulation environments of different scenarios, and the experimental results demonstrate that our method can effectively improve the efficiency of UGV exploration.

Study on the Influence of an UGV Suspension System on Camera Motion of the Teleoperation System

In the following article, the results of a study on the impact of the suspension system used in Unmanned Ground Vehicles (UGVs) on the kinematic excitation of cameras in teleoperation systems are presented. As indicated by preliminary reconnaissance studies, these excitations significantly affect the operator’s ability to perceive the environment and recognize images while driving. Currently, there is a lack of publications and guidelines in the literature regarding the design of UGV suspensions and their evaluation in terms of improving operator perception in teleoperation systems. The studies were conducted in a simulated environment using multibody systems, where various suspension structure variants were developed. The tests were carried out on the ISO 5008 rough test track. The evaluation of the tested suspension structures was carried out using a proprietary method, enabling parametric analysis and the selection of favorable solutions for improving image recognition by the UGV operator. Future research can focus on adjustment of the UGV suspension characteristics which could have significant influence on situational awareness and the operator’s ability to act effectively, especially during dynamic missions.

The LTAR Cropland Common Experiment at the Texas Gulf.

Texas Gulf is one of the 18 regional sites that is part of the USDA-ARS Long-Term Agroecosystem Research (LTAR) Network and focuses on cropland and integrated grazing land research in Central Texas, addressing challenges posed by soil characteristics, climate variability, and urbanization. This paper provides brief site descriptions of the two Cropland Common Experiments being conducted in the Texas Gulf LTAR region, emphasizing conservation tillage practices and precision agriculture techniques. The plot-scale study is located in Temple, TX, at the USDA-ARS Grassland, Soil and Water Research Laboratory and examines conventional tillage, strip tillage, and no tillage practices. The field-scale study, located in Riesel, TX, at the USDA-ARS Riesel Watersheds, assesses the impact of no tillage, cover crops, fertility management, adaptive management, and precision conservation on crop yield, profitability, and environmental footprint. Key measurements include soil and plant analyses, greenhouse gas fluxes, runoff water quantity and quality, and field operations recorded with precision agriculture equipment. Despite challenges posed by urban encroachment, future research aims to incorporate new technologies, such as unmanned ground vehicles, to enhance sustainability and productivity of the agricultural landscape. These experiments provide valuable insights for stakeholders, contributing to the development of sustainable agricultural practices tailored to the unique challenges within the Texas Gulf LTAR region.

Method for the Trajectory Tracking Control of Unmanned Ground Vehicles Based on Chaotic Particle Swarm Optimization and Model Predictive Control

Method for the Trajectory Tracking Control of Unmanned Ground Vehicles Based on Chaotic Particle Swarm Optimization and Model Predictive Control

Patent Trend Analysis of Unmanned Ground Vehicles(UGV) using Topic Modeling

This study provides a thorough examination of Unmanned Ground Vehicles(UGVs), focusing on crucial technologies and trends across major global markets. It includes an in-depth patent analysis revealing the dominant positions of the United States and the European Union in this field. Additionally, it underscores substantial advancements made by China, Japan, and Korea since 2010. Using Latent Dirichlet Allocation(LDA)-based patent text mining, the study identified key technology areas in UGV development, such as advanced control systems, navigation technologies, power supply mechanisms, and sensing and communication tools. Through linear regression analysis, the study predicted the future paths of these technology areas, offering important insights into the evolving world of UGV technology. The findings can provide strategic guidance for stakeholders in the defense, commercial, and academic sectors, pointing out the future directions in UGV advancements.

Place Recognition through Multiple LiDAR Scans Based on the Hidden Markov Model.

Autonomous driving systems for unmanned ground vehicles (UGV) operating in enclosed environments strongly rely on LiDAR localization with a prior map. Precise initial pose estimation is critical during system startup or when tracking is lost, ensuring safe UGV operation. Existing LiDAR-based place recognition methods often suffer from reduced accuracy due to only matching descriptors from individual LiDAR keyframes. This paper proposes a multi-frame descriptor-matching approach based on the hidden Markov model (HMM) to address this issue. This method enhances the place recognition accuracy and robustness by leveraging information from multiple frames. Experimental results from the KITTI dataset demonstrate that the proposed method significantly enhances the place recognition performance compared with the scan context-based single-frame descriptor-matching approach, with an average performance improvement of 5.8% and with a maximum improvement of 15.3%.

Attitude stability control for 6WID unmanned ground vehicle during steering: A collaborative controller considering minimizing tire slip energy loss

The instability of vehicle attitude and wheel slippage during turning on complex roads are key factors affecting the operational efficiency and accuracy of a variable wheelbase six-wheel independent drive unmanned ground vehicle (6WID UGV), posing a serious threat to driving safety. This article proposes a hierarchical coordinated controller to improve the attitude stability of a 6WID UGV equipped with interconnected active hydro pneumatic suspension (IAHPS) and reduce tire slip energy loss. Firstly, an integral sliding mode controller with adaptive high-order coupling factor (AHOCF-ISMC) is designed to determine the active anti roll torque required for stable roll attitude. An adaptive high-order coupling factor is introduced in the controller framework to couple physical components with different properties, avoiding overshoot and oscillation caused by integral saturation of the controller. Secondly, based on satisfying the stability of the roll attitude, the lateral stability and longitudinal traction characteristics of the vehicle are constrained and controlled. An optimization function was established to minimize tire slip energy loss within the feasible range of wheel torque determined by lateral and longitudinal control objectives. Thirdly, the particle swarm optimization algorithm was improved (IPSO) by designing adaptive weighting factors and learning factors, and is used to optimize the wheel torque distribution scheme under composite constraint conditions. Finally, the effectiveness of the coordinated controller was tested and validated in different scenarios. The results show that the designed controller has good control performance and robustness without the need to establish an accurate mathematical model, and performs well in terms of economic benefits and application prospects.

ОБОСНОВАНИЕ РАЦИОНАЛЬНОЙ КОНСТРУКЦИИ КРИВОШИПНОГО МЕХАНИЗМА КОЛЕСНО-ШАГАЮЩЕГО ДВИЖИТЕЛЯ

The article substantiates the rational design of the crank mechanism of a wheel-step mover. Kinematics analysis of a prototype of the wheel-step mover revealed the presence of oscillations in the vertical coordinate of the central axis during movement. To eliminate this drawback, differential geometry methods were used, thanks to which a method for calculating the non-circular profile of support shoes was created. Studies of the dynamics of the crank mechanism of the wheel-step mover showed that even in a steady state of motion, periodically acting inertial forces arise. To reduce their effect, non-circular gears should be used in the mover power drive. The dimensions of the crank mechanism links have been calculated, at which the cross-country ability of the running system, its kinematics and dynamics characteristics are improved, energy costs when laying a track are reduced, as well as the negative impact of the machine on the fertile soil layer. The polar coordinates of the involute points have been calculated. They are needed to construct the tooth profiles of non-circular gears. As the power drive of the crank mechanism, non-circular gears have symmetrical geometric parameters along two axes and provide a constant movement speed. Thus, the wheel-step running system can be used in agriculture, the timber industry, mining, and when working in emergency situations. The mover design being developed is intended for unmanned ground vehicles. This type of unmanned vehicles is at the initial stage of its development, inferior in frequency to air and marine unmanned vehicles. A targeted concentration of production and financial resources is necessary to ensure that domestic industry has a leading position in the production and sale of unmanned ground vehicles.

Development of an unmanned ground vehicle for seed planting

As global population growth intensifies the demand for sustainable food production, the application of robotics to agriculture emerges as a promising solution. This research focuses on the design, development, and deployment of an unmanned ground vehicle for seed planting, also known as a robotic seed planter. The robotic seed planter automates seed planting processes, offering advantages such as increased accuracy, reduced labour requirements, and optimal resource usage. Parametric Technology Corporation (PTC) Creo was used for the structural design, Proteus 8.14 for the circuitry design, and Arduino IDE 2.0 with Visual Studio Code for the programming. The design incorporates seed metering and drilling mechanisms guided by intelligent systems. Results show exceptional accuracy in seed placement (94%), operational efficiency, and adaptability to diverse conditions, with energy consumption relatively low. The planter is equipped with a web application for remote monitoring and control. The application is hosted on one of the microcontrollers and WebSockets protocol is utilized for inter-microcontroller communication. It offers an auto mode for automated planting and Manual mode for easier manoeuvrability. The findings of this study demonstrate the robotic seed planter’s transformative impact on precision agriculture, providing a glimpse into the future of efficient and sustainable farming operations.

Adaptive differential steering strategy for distributed driving unmanned ground vehicle with variable configurations based on modified localized modelling sliding mode control

When performing complex tasks such as position transfer and material transportation, the distributed driving unmanned platform with variable configurations needs to address the challenge of multi-wheel cooperative torque distribution control to achieve high-performance differential steering and enhance vehicle dynamics. The configuration change will impact the dynamic performance of the unmanned platform, posing a challenge to the performance of the existing control strategy based on mathematical model development. In order to address the aforementioned issues, this paper analyzes the impact of changes in vehicle configuration on steering gain and proposes a hierarchical adaptive differential steering strategy based on variable vehicle configurations. Firstly, the response characteristics of the yaw angle relative to the active yaw moment under the influence of changes in wheelbase and tread are analyzed. Based on this analysis, two structural modes, maneuverable and balanced, are selected. Secondly, a localized-modelling sliding mode control method with an extended state observer is proposed to estimate the desired yaw moment in the upper controller, considering the motor's execution delay. Then, the lower controller optimizes the torque of each wheel in real-time using the whale optimization algorithm. It aims to optimize tire energy dissipation and tire load rate while ensuring driving stability and achieving differential steering. Finally, through co-simulation and experiments on a scaled prototype, the reliability of the dynamics theory and the superiority of the control algorithm are validated. This optimization has led to significant improvements in the tire dissipation energy index and tire load rate index.