Unmanned Ground Vehicle Research Articles

Adaptive heading control strategy for unmanned ground vehicle with variable wheelbase based on robust-active disturbance rejection control

In order to fully exploit the variable wheelbase characteristics of the unmanned ground vehicle (UGV) with variable configuration, this paper proposes an adaptive heading tracking control strategy based on wheelbase changes. This strategy involves adjusting the wheelbase according to different working conditions to optimize various driving performance aspects. Firstly, the impact of changing wheelbase on the response characteristics of sideslip angle and heading angle relative to the front-wheel steering angle is analyzed by using a lateral vehicle dynamic model. The configurations where the 2nd axle moves forward by 0.5 m, remains unchanged, and moves backward by 0.5 m are defined as the ‘stable configuration’, ‘balanced configuration’, and ‘maneuverable configuration’, respectively. Considering time lag effects of hydraulic systems and external random noise interference, a robust-active disturbance rejection control (r-ADRC) method is developed by incorporating a robust term into active disturbance rejection control (ADRC) in order to achieve desired front-wheel steering angle. Additionally, a torque distribution method based on the tire load rate and the real-time vertical load of each wheel is applied to ensure uniform tire wear and enhance longitudinal driving stability. Finally, simulations under various typical working conditions as well as scaled prototype experiments are conducted, and both the theory behind the changing wheelbases and the effectiveness of proposed control strategy are verified. According to different vehicle configurations and mission requirements, the maneuverability and stability of the ground unmanned vehicle are ensured respectively.

Vision-Based Deep Reinforcement Learning of UAV-UGV Collaborative Landing Policy Using Automatic Curriculum

Collaborative autonomous landing of a quadrotor Unmanned Aerial Vehicle (UAV) on a moving Unmanned Ground Vehicle (UGV) presents challenges due to the need for accurate real-time tracking of the UGV and the adjustment for the landing policy. To address this challenge, we propose a progressive learning framework for generating an optimal landing policy based on vision without the need of communication between the UAV and the UGV. First, we propose the Landing Vision System (LVS) to offer rapid localization and pose estimation of the UGV. Then, we design an Automatic Curriculum Learning (ACL) approach to learn the landing tasks under different conditions of UGV motions and wind interference. Specifically, we introduce a neural network-based difficulty discriminator to schedule the landing tasks according to their levels of difficulty. Our method achieves a higher landing success rate and accuracy compared with the state-of-the-art TD3 reinforcement learning algorithm.

Applying a 2 kW Polymer Membrane Fuel-Cell Stack to Building Hybrid Power Sources for Unmanned Ground Vehicles

The novel constructions of hybrid energy sources using polymer electrolyte fuel cells (PEMFCs), and supercapacitors are developed. Studies on the energy demand and peak electrical power of unmanned ground vehicles (UGVs) weighing up to 100 kg were conducted under various conditions. It was found that the average electrical power required does not exceed ~2 kW under all conditions studied. However, under the dynamic electrical load of the electric drive of mobile robots, the short peak power exceeded 2 kW, and the highest current load was in the range of 80–90 A. The electrical performance of a family of PEMFC stacks built in open-cathode mode was determined. A hydrogen-usage control strategy for power generation, cleaning processes, and humidification was analysed. The integration of a PEMFC stack with a bank of supercapacitors makes it possible to mitigate the voltage dips. These occur periodically at short time intervals as a result of short-circuit operation. In the second construction, the recovery of electrical energy dissipated by a short-circuit unit (SCU) was also demonstrated in the integrated PEMFC stack and supercapacitor bank system. The concept of an energy-efficient, mobile, and environmentally friendly hydrogen charging unit has been proposed. It comprises (i) a hydrogen anion exchange membrane electrolyser, (ii) a photovoltaic installation, (iii) a battery storage, (iv) a hydrogen buffer storage in a buffer tank, (v) a hydrogen compression unit, and (vi) composite tanks.

Data Driven Control and slip estimation for Agricultural Tracked Vehicles

This paper focusses on the path following problem for autonomous Unmanned Ground Vehicles developed for precision agriculture. Such vehicles typically face rough terrain and narrow navigating spaces, so reliability of odometry is largely reduced. In this context, slip estimation/accommodation becomes crucial for localization and navigation of vehicles. In this work, a control architecture is presented coupling MIMO Data-Driven Control and Sliding Mode Control, with the inclusion of a fault estimation mechanism aimed at mitigating the actuators’ loss of effectiveness associated to slipping. The supporting theoretical development makes use of previous results available in the Model Free Adaptive Control framework, which have been extended in order to deal with the path following problem for the vehicle. On the basis of extensive simulations, the proposed control policy is shown able to strengthen the recovery capability and robustness inherently owned by the original adaptive mechanism and control laws.

Coverage Path Planning With Budget Constraints for Multiple Unmanned Ground Vehicles

Coverage Path Planning With Budget Constraints for Multiple Unmanned Ground Vehicles

Robotics in Forest Inventories: SPOT’s First Steps

In the context of the potential future use of unmanned ground vehicles for forest inventories, we present the first experiences with SPOT, a legged robot equipped with a LiDAR instrument and several cameras that have been used with a teleoperation approach for single-tree detection and measurements. This first test was carried out using the default LiDAR system (the so-called enhanced autonomy payload-EAP, installed on the board of SPOT to guide autonomous movements) to understand advantages and limitations of this platform to support forest inventory activities. The test was carried out in the Vallombrosa forest (Italy) by assessing different data acquisition methods. The first results showed that EAP LiDAR generated noisy point clouds where only large trees (DBH ≥ 20 cm) could be identified. The results showed that the accuracy in tree identification and DBH measurements were strongly influenced by the path used for data acquisition, with average errors in tree positioning no less than 1.9 m. Despite this, the best methods allowed the correct identification of 97% of large trees.

A Low-Cost Relative Positioning Method for UAV/UGV Coordinated Heterogeneous System Based on Visual-Lidar Fusion

Unmanned Ground Vehicles (UGVs) and Unmanned Aerial Vehicles (UAVs) are commonly used for various purposes, and their cooperative systems have been developed to enhance their capabilities. However, tracking and interacting with dynamic UAVs poses several challenges, including limitations of traditional radar and visual systems, and the need for the real-time monitoring of UAV positions. To address these challenges, a low-cost method that uses LiDAR (Light Detection and Ranging) and RGB-D cameras to detect and track UAVs in real time has been proposed. This method relies on a learning model and a linear Kalman filter, and has demonstrated satisfactory estimation accuracy using only CPU (Central Processing Unit)- in GPS (Global Positioning System)-denied environments without any prior information.

Automated Method for SLAM Evaluation in GNSS-Denied Areas

The automated inspection and mapping of engineering structures are mainly based on photogrammetry and laser scanning. Mobile robotic platforms like unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), but also handheld platforms, allow efficient automated mapping. Engineering structures like bridges shadow global navigation satellite system (GNSS), which complicates precise localization. Simultaneous localization and mapping (SLAM) algorithms offer a sufficient solution, since they do not require GNSS. However, testing and comparing SLAM algorithms in GNSS-denied areas is difficult due to missing ground truth data. This work presents an approach to measuring the performance of SLAM in indoor and outdoor GNSS-denied areas using a terrestrial scanner Leica RTC360 and a tachymeter to acquire point cloud and trajectory information. The proposed method is independent of time synchronization between robot and tachymeter and also works on sparse SLAM point clouds. For the evaluation of the proposed method, three LiDAR-based SLAM algorithms called KISS-ICP, SC-LIO-SAM, and MA-LIO are tested using a UGV equipped with two light detection and ranging (LiDAR) sensors and an inertial measurement unit (IMU). KISS-ICP is based solely on a single LiDAR scanner and SC-LIO-SAM also uses an IMU. MA-LIO, which allows multiple (different) LiDAR sensors, is tested on a horizontal and vertical one and an IMU. Time synchronization between the tachymeter and SLAM data during post-processing allows calculating the root mean square (RMS) absolute trajectory error, mean relative trajectory error, and the mean point cloud to reference point cloud distance. It shows that the proposed method is an efficient approach to measure the performance of SLAM in GNSS-denied areas. Additionally, the method shows the superior performance of MA-LIO in four of six test tracks with 5 to 7 cm RMS trajectory error, followed by SC-LIO-SAM and KISS-ICP in last place. SC-LIO-SAM reaches the lowest point cloud to reference point cloud distance in four of six test tracks, with 4 to 12 cm.

Vehicle State Monitoring and Fault Detection System for Unmanned Ground Vehicles (UGV) using Markov Models

This research presents a novel fault detection and diagnostics system for unmanned ground vehicles (UGVs) by combining Markov models representing the vehicle's navigation, kinematic behavior, and vehicle dynamics systems. Existing studies do not specifically address the challenges related to UGVs and their complex subsystems or the incorporation of weather and environmental condition data. The proposed system leverages environmental and weather condition data to monitor the UGV's state and detect anomalies in its behavior. By predicting the probability of faults such as collisions, sensor damage, and other malfunctions, the system aims to enhance the safety, reliability, and performance of UGVs. The research will demonstrate the effectiveness of the proposed methodology through case studies and performance evaluation, highlighting its potential application in various real-world scenarios. This work contributes to the ongoing research in prognostics and health management, particularly for autonomous systems, by providing a new approach to fault detection and diagnostics in UGVs.

Improving the Efficiency of Modern Warehouses Using Smart Battery Placement

In the ever-evolving landscape of warehousing, the integration of unmanned ground vehicles (UGVs) has profoundly revolutionized operational efficiency. Despite this advancement, a key determinant of UGV productivity remains its energy management and battery placement strategies. While many studies explored optimizing the pathways within warehouses and determining ideal power station locales, there remains a gap in addressing the dynamic needs of energy-efficient UGVs operating in tandem. The current literature largely focuses on static designs, often overlooking the challenges of multi-UGV scenarios. This paper introduces a novel algorithm based on affinity propagation (AP) for smart battery and charging station placement in modern warehouses. The idea of the proposed algorithm is to divide the initial area into multiple sub-areas based on their traffic, and then identify the optimal battery location within each sub-area. A salient feature of this algorithm is its adeptness at determining the most strategic battery station placements, emphasizing uninterrupted operations and minimized downtimes. Through extensive evaluations in a synthesized realistic setting, our results underscore the algorithm’s proficiency in devising enhanced solutions within feasible time constraints, paving the way for more energy-efficient and cohesive UGV-driven warehouse systems.

Reinforcement learning for high-quality reality mapping of indoor construction using unmanned ground vehicles

Recent advances in reality capture technology focused on automating reality capture and devising robust computational models to convert the collected data into usable formats. However, these modern approaches are still challenged by the insufficient capacity of the resulting information to relay accurate and complete representations of the construction state due to the data's poor visual quality. In addition, the complexity of robotic path planning –especially for indoor construction– hinders automatic visual data collection due to cluttered, narrow, and dynamic construction spaces. This work targets both challenges by presenting a reinforcement learning model that optimizes indoor data collection policy for acquiring high-quality visual data using camera-equipped unmanned ground rovers. Results from three learned navigation policies show the capability of the method to provide high visual quality for the collected data. The learned policies reduced the data collection duration by 38.23% on average compared to the currently used automatic data collection strategies. The policies also provided a 31.04% average reduction in data collection distance compared to lawn-mower patterns.

Integrated Robotics Networks with Co-Optimization of Drone Placement and AirGround Communications

Terrestrial robots, i.e., unmanned ground vehicles (UGVs), and aerial robots, i.e., unmanned aerial vehicles (UAVs), operate in separate spaces. To exploit their complementary features (e.g., fields of views, communication links, computing capabilities), a promising paradigm termed integrated robotics network therefore emerges, which provides communications for cooperative UAVs-UGVs applications. However, how to efficiently deploy UAVs and schedule the UAVs-UGVs connections according to different UGV tasks become challenging. In this paper, we consider the sum-rate maximization problem, where UGVs plan their trajectories autonomously and are dynamically associated with UAVs according to their planned trajectories. Although this problem is a NP-hard mixed integer program, a fast polynomial time algorithm using alternating gradient descent and penalty-based binary relaxation, is devised. Simulation results demonstrate the effectiveness of the proposed algorithm.

Stability and energy-saving coordinated control strategy of six-wheel independent drive unmanned ground vehicle

During the operation of six-wheel independent drive unmanned ground vehicle (6WID UGV) in the field, the inconsistent tire contact characteristics and frequent steering maneuvers have led to increasingly prominent issues of tire excessive wear and lateral instability. Therefore, a coordinated hierarchical controller for 6WID UGV is proposed to ensure the stability of the steering process while reducing tire wear and motor energy consumption. First, a sliding mode controller (SMC) with an extended-state observer (ESO) is proposed for lateral stability control referencing the active disturbance rejection control (ADRC) technique, achieving fast response and robustness to uncertainty. Second, the lower controller constructs a Lagrangian function with tire slip energy loss and energy consumption as optimization objectives and allocates torque based on the Pareto optimal solution within the feasible domain given by the upper controller. Finally, the designed controller is tested under typical operating conditions. The results indicate that the designed coordinated controller has significant control performance and economic benefits in improving lateral stability and reducing energy loss. Compared with the torque distribution strategy based on tire vertical load, the tire slip energy is reduced by 44.8 % and 17.7 % in the process of traction/steering and braking/steering, respectively. In addition, the motor energy consumption and the friction braking energy loss are reduced by 12.1 % and 70.8 % respectively.

MIN3D Dataset: MultI-seNsor 3D Mapping with an Unmanned Ground Vehicle

The research potential in the field of mobile mapping technologies is often hindered by several constraints. These include the need for costly hardware to collect data, limited access to target sites with specific environmental conditions or the collection of ground truth data for a quantitative evaluation of the developed solutions. To address these challenges, the research community has often prepared open datasets suitable for developments and testing. However, the availability of datasets that encompass truly demanding mixed indoor–outdoor and subterranean conditions, acquired with diverse but synchronized sensors, is currently limited. To alleviate this issue, we propose the MIN3D dataset (MultI-seNsor 3D mapping with an unmanned ground vehicle for mining applications) which includes data gathered using a wheeled mobile robot in two distinct locations: (i) textureless dark corridors and outside parts of a university campus and (ii) tunnels of an underground WW2 site in Walim (Poland). MIN3D comprises around 150 GB of raw data, including images captured by multiple co-calibrated monocular, stereo and thermal cameras, two LiDAR sensors and three inertial measurement units. Reliable ground truth (GT) point clouds were collected using a survey-grade terrestrial laser scanner. By openly sharing this dataset, we aim to support the efforts of the scientific community in developing robust methods for navigation and mapping in challenging underground conditions. In the paper, we describe the collected data and provide an initial accuracy assessment of some visual- and LiDAR-based simultaneous localization and mapping (SLAM) algorithms for selected sequences. Encountered problems, open research questions and areas that could benefit from utilizing our dataset are discussed. Data are available at https://3dom.fbk.eu/benchmarks.

Research on Terrain Mobility of UGV with Hydrostatic Wheel Drive and Slip Control Systems

The article explored the potential for enhancing the off-road mobility of unmanned ground vehicles (UGV) equipped with a hydrostatic drive system. The analysis showed that effectively overcoming rough or soft terrain demands a slip limitation. In the UGVs with hydrostatic drives, flow dividers are used for this purpose. Unfortunately, they have certain drawbacks, such as reduced efficiency due to pressure losses. In order to minimize this phenomenon, an external braking system was used as a new slip control system. Therefore, simulation studies were carried out to assess the new slip control system while overcoming terrain obstacles due to the reduction of energy consumption and improving the mobility of the UGV.

Longitudinal Velocity Regulation of UGVs: A Composite Control Approach for Acceleration and Deceleration

In this paper, a composite longitudinal controller for velocity regulation of unmanned ground vehicles (UGVs) is proposed. First, both the empirical model and mixed logical dynamic model are developed in terms of the experimental data processing method. Second, a composite longitudinal control strategy incorporating steady-state controller and active disturbance rejection state feedback controller is designed for velocity regulation control during acceleration and deceleration. Finally, the stability analysis of velocity error is given with the global sector condition, and the comparative experimental tests show the effectiveness and robustness of the proposed composite longitudinal regulation control strategy.

Integrated Localization and Planning for Cruise Control of UGV Platoons in Infrastructure-Free Environments

This paper investigates the cruise control problem of unmanned ground vehicle (UGV) platoons from the implementation perspective. Unlike most existing works related to platoon cruise control which rely on positioning infrastructures such as lane markings, roadside units, and global navigation satellite systems (GNSS), this paper explores a new problem: platoon cruise control in environments without positioning infrastructures. The introduction of this constraint disables most existing cruise control approaches. To address this problem, an integrated localization and planning framework is proposed, which is composed of three modular algorithms. Firstly, to localize multiple vehicles in a common coordinate system, a collaborative localization algorithm is developed through matching local perceptions of different vehicles. Secondly, to maintain the desired platoon configuration, the historical trajectory of the preceding vehicle is reconstructed, based on which the target state is planned for the following vehicle. Finally, a virtual controller based algorithm is designed to generate feasible trajectories for the following vehicle in real time. The proposed framework has two salient features. Firstly, it does not depend on positioning infrastructures and does not introduce additional positioning sensors, such as GNSS/INS modules, ultra-wideband (UWB) devices, magnetic meters and so on, as long as each vehicle is equipped with a perception sensor (Lidar, radar or camera), which however is essential equipment for nowaday autonomous systems. Secondly, the proposed framework does not depend on direct observations between vehicles to achieve relative localization, making it applicable in non-line-of-sight (non-LOS) situations. Real-world experiments have been conducted to validate the effectiveness, robustness and practicality of the proposed framework.

A Unmanned Aerial Vehicle (UAV)/Unmanned Ground Vehicle (UGV) Dynamic Autonomous Docking Scheme in GPS-Denied Environments

This study designs a navigation and landing scheme for an unmanned aerial vehicle (UAV) to autonomously land on an arbitrarily moving unmanned ground vehicle (UGV) in GPS-denied environments based on vision, ultra-wideband (UWB) and system information. In the approaching phase, an effective multi-innovation forgetting gradient (MIFG) algorithm is proposed to estimate the position of the UAV relative to the target using historical data (estimated distance and relative displacement measurements). Using these estimates, a saturated proportional navigation controller is developed, by which the UAV can approach the target, making the UGV enter the field of view (FOV) of the camera deployed in the UAV. Then, a sensor fusion estimation algorithm based on an extended Kalman filter (EKF) is proposed to achieve accurate landing. Finally, a numerical example and a real experiment are used to support the theoretical results.

Feature selection of gray-level Cooccurrence matrix using genetic algorithm with Extreme learning machine classification for early detection of Pole roads

Land transportation accidents are a severe problem in Indonesia. Factors that cause land transportation accidents include driver negligence, not road-worthy vehicles, and damaged road conditions. In 2018, according to data from the Indonesian Central Statistics Agency, the number of accidents in Indonesia due to damaged roads was around 36,89%. One of the types of road damage is potholes. Potholes have the potential to trigger road accidents, especially for motorcyclists. By looking at current technological developments, the Unmanned Ground Vehicle (UGV) is a transportation technology that does not have a crew that can help detect obstacles on the highway, such as potholes. The potholed road itself has a different texture from normal roads. The pothole texture value can be represented using Gray-Level Cooccurrence Matrix (GLCM) as a feature extraction algorithm. GLCM has several features and combinations, namely the distance and angle features of GLCM. Too many features are difficult to implement in artificial intelligence because it requires a long computation time. The system needs to produce a fast computation time in detecting the pothole so that it can be implemented in real-time. A Genetic Algorithm is applied to perform feature selection. Furthermore, the classification method is used Extreme Learning Machine (ELM). The GLCM features used are 128 features which will be tested three times with the selection results obtained as a combination of 57 features, 20 features, and 12 features. Based on the best variety of features in the video test, the accuracy is a combination of features 57 of 88,65% and a computation time of 0,115 s. The best overall conclusion is the combination of feature selection 20 and 12 because it has an accuracy of 87,36% and 86,48%, which is not much different from feature selection 57. However, it has a much faster computation time of 0,069 s and 0,062 s.

Research on relevant contents of carrier design based on unmanned aerial vehicle

With the increasing popularity of online shopping, e-commerce has become a time-saving and labour-saving way to shop for people. Consequently, the express industry has emerged as an indispensable part of the supply chain. However, due to the shortage of human resources, express delivery services often face the challenge of overstocked delivery stations, leading to decreased efficiency in the traditional delivery mode. To address this problem, the development of a drone delivery mode that can cooperate with unmanned vehicles has been proposed. In the context of express delivery, key technologies that need to be resolved are elaborated, including UAV material structure, sensors, visual positioning and navigation technology, and path planning. By addressing these issues, this study aims to provide insights into the research and development of unmanned distribution and logistics industries. Furthermore, this study highlights existing problems and proposes solutions for the combined distribution of unmanned aerial and unmanned ground vehicles. The combination of these two modes of delivery presents both opportunities and challenges, which this study aims to identify and address. Ultimately, the findings and recommendations presented in this study contribute to the efficient and effective operation of the express delivery industry in the era of e-commerce.