Ground Platforms Research Articles

An Independent Suspension and Trafficability Analysis for an Unmanned Ground Platform

The objective of this paper was to investigate and design a novel vertical- and horizontal-arm independent suspension system aimed at enhancing the autonomous obstacle-crossing capabilities of unmanned ground platforms in complex, unstructured environments such as mountainous regions, hills, and mining areas. By thoroughly considering factors such as the suspension structure design, changes in the centroid position, distribution of driving forces, and dynamic stability analysis, we proposed an innovative suspension structure. An unmanned ground platform model equipped with this suspension system was developed using ADAMS and MATLAB/Simulink. Subsequently, a joint simulation was conducted to validate the performance of the suspension system. The results indicated that the unmanned ground platform could successfully traverse vertical steps up to 370 mm high and trenches measuring up to 600 mm wide. Furthermore, when confronted with intricate obstacles including vertical barriers, trenches, and side slopes, the platform demonstrated exceptional traversing capabilities. In conclusion, the proposed suspension system significantly enhances both the obstacle-surmounting ability and the terrain adaptability of unmanned ground platforms while providing crucial technical support for their deployment in complex unstructured environments.

The Wheel–Rail Contact Force for a Heavy-Load Train Can Be Measured Using a Collaborative Calibration Algorithm

The wheel–rail contact force is a crucial indicator for ensuring the secure operation of a heavy-load train. However, obtaining the real-time wheel–rail contact force of a heavy-load train is a challenging task as, due to safety considerations, it is not possible to install instrumented wheelsets on heavy-load trains. This work presents a novel approach to quantify the wheel–rail contact force of a heavy-load train, utilizing a cooperative calibration methodology. First, a ground measurement platform for the wheel–rail contact force of a heavy-load train is constructed on a selected rail section. The railway inspection car’s wheel–rail contact force measurement system is fine-tuned using a multilayer perceptron calibration approach, and the ground platform then uses the results to fine-tune the railway inspection car’s examined wheelset. Second, based on actual measured data on the wheel–rail contact force of a heavy-load train, and using the golden jackal optimization algorithm, the multilayer perceptron correction approach is employed to create a data relationship mapping model. This model correlates the corrected data on the wheel–rail contact force obtained from the railway inspection car with the wheel–rail contact force of a heavy-haul train with an axle load of 25 tons, and the precision of the mapping is guaranteed. Finally, by combining the wheel–rail contact force correction method for the railway inspection car and the contact force mapping model between the railway inspection car and the heavy-load train, collaborative calibration of the wheel–rail contact force of the heavy-load train is realized. The experimental results under two working conditions show that this method can realize high-precision, real-time measurement of the wheel–rail contact force of a heavy-load train. For the working condition of a straight-line section, the calibration error was within 1.593 kN, and the MAPE was 0.105%; for the working condition of a curved-line section, the calibration error was 2.344 kN, and the RMSE was 184.72 N.

Collaborative planning and control of heterogeneous multi-ground unmanned platforms

With the rapid development of intelligent vehicles, mobile robots, warehousing and logistics, exploration and testing and other industries, multi-platform collaborative work research has become the future research focus of ground platforms. This paper mainly studies the multi-ground platform collaborative system as follows: Combined with the multi-vehicle collaborative scenario, a three-layer system Artificial Intelligence control framework is proposed, which is composed of a task assignment layer, trajectory planning layer and multi-vehicle control layer. Firstly, the multi-car task assignment algorithm based on the Dubins curve is studied. Secondly, the vehicle motion planning algorithm based on the D*Lite algorithm is designed, and the driving direction and the optional grid range are improved. Then, the obstacle scene of multi-vehicle formation is analyzed, two obstacle avoidance schemes of formation are proposed and the process analysis is carried out. Finally, the application in engineering is conducted to verify the effectiveness of obstacle avoidance strategy, trajectory planning strategy and the overall system framework.

The Novel Method in Validating the Spectral Wavelength Optimization to Determine Archaeological Proxies by the Integration of Aerial and Ground Platforms

This research proposed a novel method for evaluating the ideal spectral wavelength by integrating the aerial remote sensing image and geophysical techniques to improve the detection of buried archaeological proxies via the spectral wavelength. Eight different wavelength ranges were compared to eight distinct spectral indices to conduct a more thorough vegetation analysis. The spectral information from eight various Vegetation Indices and two types of resistivity data was then analyzed using a Linear Regression model. Then, the novel "Constant Experimental Evaluation" method (CEE) was developed to improve the preliminary result. Subsequently, the results outlined newly optimal spectral wavelengths by enhancing correlation coefficient R2 values, before (R2=0.595) to (R2=0.86) after CEE application, with the spectral wavelengths values of (NIRnew=0.783µm) and (Rednew=0.627µm) along with the 50% of image enhancement. It suggests that the technique may be significant to any archaeological site that presents spectrally differently from its immediate environment.

Forest point cloud registration: a review.

Point cloud registration is a necessary prerequisite for conducting precise, large-scale forest surveys and management. This paper focuses on providing a systematic overview and summary of the work on forest point cloud registration over the past 20 years. The developmental process of forest point cloud registration methods, spanning from the early reliance on manual markers to the subsequent evolution towards automatic registration based on feature matching, and then to the advanced technology based on deep learning were reviewed. Furthermore, the paper offered detailed discussions on the registration between different point cloud platforms: ground platforms, between ground platforms and aerial platforms, and between aerial platforms. Additionally, the paper delved into mainstream datasets and evaluation metrics in the domain of forest point cloud registration. Finally, the paper summarized the current state of research in this area, highlighted challenges, and provided future research outlooks. This review aims to provide researchers with a comprehensive understanding of forest point cloud registration, and to promote the advancement of point cloud technology, hopefully inspiring further applications in the field.

Research on seat active noise control of driver's cab ground platform based on far-point secondary sound sources

Driver's cab noise has an impact on the long-term driving environment and physical health of drivers. The locomotive driver's cab has significant low-frequency noise due to structure-borne sound, which is suitable for effective suppression by the active noise control system. However, on the one hand, the seat headrest system hinders the driver's movement space, on the one hand, the active noise control for space zones in the driver's cab has limited noise reduction effect due to the large control area. Therefore, a ground research test platform of driver's cab for active noise control was designed, and its structure and control method were introduced in this study. Based on the near-point seat active noise reduction control system, the coherence of the reference acoustic signal of the chair to the acoustic signal at the driver's left ear is very close with the one on the floor, and both of their active noise reduction in the full frequency band from 50 Hz to 5000 Hz are very close (about 4.5 dB (A)). In order to alleviate the interference of the headrest system installed with secondary sound sources on the driver's operating space, a far-point active noise reduction control system was proposed. The results showed that when two reference microphone signals from the seat back and floor position are used at the same time, the active noise reduction next to the driver's left ear in the full frequency band of 50 Hz to 5000 Hz is 4.0 dB(A), which is still significant. This provides a useful reference for the engineering application of active noise control systems in rail driver's cabs.

One Class One Click: Quasi scene-level weakly supervised point cloud semantic segmentation with active learning

Reliance on vast annotations to achieve leading performance severely restricts the practicality of large-scale point cloud semantic segmentation. For the purpose of reducing data annotation costs, effective labeling schemes are developed and contribute to attaining competitive results under weak supervision strategy. Revisiting current weak label forms, we introduce One Class One Click (OCOC), a low cost yet informative quasi scene-level label, which encapsulates both point-level and scene-level annotations. An active weakly supervised framework is proposed to leverage scarce labels by involving weak supervision from both global and local perspectives. Contextual constraints are imposed by an auxiliary scene classification task, respectively based on global feature embedding and point-wise prediction aggregation, which restricts the model prediction merely to OCOC labels within a sub-cloud. Furthermore, we design a context-aware pseudo labeling strategy, which effectively supplement point-level supervisory signals subject to OCOC labels. Finally, an active learning scheme with a uncertainty measure — temporal output discrepancy is integrated to examine informative samples and provides guidance on sub-clouds query, which is conducive to quickly attaining desirable OCOC annotations and reduces the labeling cost to an extremely low extent. Extensive experimental analysis using three LiDAR benchmarks respectively collected from airborne, mobile and ground platforms demonstrates that our proposed method achieves very promising results though subject to scarce labels. It considerably outperforms genuine scene-level weakly supervised methods by up to 25% in terms of average F1 score and achieves competitive results against full supervision schemes. On terrestrial LiDAR dataset — Semantics3D, using approximately 2‱ of labels, our method achieves an average F1 score of 85.2%, which increases by 11.58% compared to the baseline model. Codes are publicly available at https://github.com/PuzoW/One-Class-One-Click.

Effects of wind speed and tropospheric height on solar power generation: Energy exploration above ground level

Terrestrial and extraterrestrial factors hinder the exploitation of solar power using a ground platform. This paper is concerned with the generation of solar power above ground level. This paper employs modeling and simulations coupled with experimentation to establish a functional relationship between the percentage of solar power gain, tropospheric height, and wind speed. The finite difference method based on the Cranks–Nicolson scheme was used to realize the model solution. The wind flow equation established a linear relationship between tropospheric height and wind speed, between tropospheric height and the percentage of solar power gain. It is evident that an infinitesimal percentage of solar power gain (≈2.5%) corresponded to 1000 m above ground level; the tropospheric height of 8100 m recorded 23% of solar power gain. Furthermore, wind speeds of 0 to 33 ms −1/distance (1000 m) correspond to ground level and tropospheric height of about 8100 m respectively. However, there is a prospect of achieving more percentage of solar power gain by applying high-altitude platforms. The results obtained apply to other study areas having elevations close to 1100 m, it serves as a guide in the estimation of the percentage of solar power gain by the virtue of tropospheric height and wind speed.

A Systematic Review of Effective Hardware and Software Factors Affecting High-Throughput Plant Phenotyping

Plant phenotyping studies the complex characteristics of plants, with the aim of evaluating and assessing their condition and finding better exemplars. Recently, a new branch emerged in the phenotyping field, namely, high-throughput phenotyping (HTP). Specifically, HTP exploits modern data sampling techniques to gather a high amount of data that can be used to improve the effectiveness of phenotyping. Hence, HTP combines the knowledge derived from the phenotyping domain with computer science, engineering, and data analysis techniques. In this scenario, machine learning (ML) and deep learning (DL) algorithms have been successfully integrated with noninvasive imaging techniques, playing a key role in automation, standardization, and quantitative data analysis. This study aims to systematically review two main areas of interest for HTP: hardware and software. For each of these areas, two influential factors were identified: for hardware, platforms and sensing equipment were analyzed; for software, the focus was on algorithms and new trends. The study was conducted following the PRISMA protocol, which allowed the refinement of the research on a wide selection of papers by extracting a meaningful dataset of 32 articles of interest. The analysis highlighted the diffusion of ground platforms, which were used in about 47% of reviewed methods, and RGB sensors, mainly due to their competitive costs, high compatibility, and versatility. Furthermore, DL-based algorithms accounted for the larger share (about 69%) of reviewed approaches, mainly due to their effectiveness and the focus posed by the scientific community over the last few years. Future research will focus on improving DL models to better handle hardware-generated data. The final aim is to create integrated, user-friendly, and scalable tools that can be directly deployed and used on the field to improve the overall crop yield.

Demand and Current Situation of 3/8 mm Dual Band Transparent, Bulletproof and Stealth Integrated Radome Technology

Starting from the threats faced by land-based ground platforms and the battlefield environment, this paper discusses the necessity of the development of 3/8 mm dual band transparent, bulletproof and stealth integrated radome technology. By analyzing the domestic and international development status of relevant technologies, the main problems existing in the research of bulletproof radome are summarized. Finally, the difficulties in the development of this technology are analyzed.

Distributed Estimation of a Layered Architecture for Collaborative Air–Ground Target Geolocation in Outdoor Environments

To solve the problem of collaborative air–ground target search and localization in large outdoor environments, we adopt a distributed layered architecture and propose a corresponding distributed estimation algorithm, which can produce accurate estimates of interested target position. The air–ground system consists of a single unmanned aerial vehicle (UAV) and several ground platforms. First, for the distributed layered architecture, this article develops unbalanced simple convex combination algorithm using one-shot measurements from the single UAV and all ground platforms to generate global estimates of the stationary target state. The novelty of the proposed algorithm is that it considers the differences in sensor capabilities between the aerial and ground platforms. Then, performance analysis is described to show that the proposed algorithm is obviously superior to the traditional existing convex combination algorithms. Finally, the efficacy of this algorithm is further demonstrated by the simulation experiments and actual geolocation tests.

Satellite‐air‐ground integrated multi‐source earth observation and machine learning processing brain for tailings reservoir monitoring and rapid emergency response

AbstractTailings reservoirs are an inevitable part of the production process of metal mines and are typical of post‐mining and post‐industrial lands. Tailings reservoirs are often located in mountainous areas so earth observation and remote sensing is a necessary monitoring means. However, existing observation are generally based on satellite, air or ground platforms, Combined satellite‐air‐ground observation is rare, and the coordination ability of processing methods to cope with it is insufficient. Therefore, the response to sudden major environmental and disaster events is slow and lagging. In this study, inspired by the human brain, a satellite‐air‐ground integrated multi‐source earth observation and machine learning processing system was built up for tailings reservoir stereoscopic monitoring and rapid emergency response (SAGTR). Firstly, the brain‐inspired human visual multimodal data acquisition by satellite‐air‐ground integration platform has been established to break through the traditional single‐source and single‐mode data approach and involves satellite remote sensing images, UAV hyperspectral images, and ground parameters. Moreover, it is unique among current tailings reservoir monitoring systems. In general, our proposed SAGTR framework has promise for improving the comprehensive monitoring and emergency response to tailings reservoir failures.

Vision-Based Autonomous Following of a Moving Platform and Landing for an Unmanned Aerial Vehicle

Interest in Unmanned Aerial Vehicles (UAVs) has increased due to their versatility and variety of applications, however their battery life limits their applications. Heterogeneous multi-robot systems can offer a solution to this limitation, by allowing an Unmanned Ground Vehicle (UGV) to serve as a recharging station for the aerial one. Moreover, cooperation between aerial and terrestrial robots allows them to overcome other individual limitations, such as communication link coverage or accessibility, and to solve highly complex tasks, e.g., environment exploration, infrastructure inspection or search and rescue. This work proposes a vision-based approach that enables an aerial robot to autonomously detect, follow, and land on a mobile ground platform. For this purpose, ArUcO fiducial markers are used to estimate the relative pose between the UAV and UGV by processing RGB images provided by a monocular camera on board the UAV. The pose estimation is fed to a trajectory planner and four decoupled controllers to generate speed set-points relative to the UAV. Using a cascade loop strategy, these set-points are then sent to the UAV autopilot for inner loop control. The proposed solution has been tested both in simulation, with a digital twin of a solar farm using ROS, Gazebo and Ardupilot Software-in-the-Loop (SiL); and in the real world at IST Lisbon's outdoor facilities, with a UAV built on the basis of a DJ550 Hexacopter and a modified Jackal ground robot from DJI and Clearpath Robotics, respectively. Pose estimation, trajectory planning and speed set-point are computed on board the UAV, using a Single Board Computer (SBC) running Ubuntu and ROS, without the need for external infrastructure.

CLEANDEM, a Cyber physicaL Equipment for unmAnned Nuclear DEcommissioning Measurements

Human intervention is still required nowadays for most operations conducted during the Dismantling & Decommissioning (D&D) steps, which cover a wide range of radiological conditions: from the harsh initial conditions, nearly identical to when operating, to the final decommissioning steps where radioactivity has been removed. The goal of the three years EU-funded CLEANDEM project, led by CEA List, is to deliver a unique platform which will support the end-users’ operations, from the initial radiological assessment to the final characterization of the facility, while enabling their continuous monitoring during the D&D operations. Ten leading actors from four European countries’ nuclear industry and research, have joined their expertise and efforts in the CLEANDEM consortium to develop a mobile unmanned ground platform (UGV), equipped with upgraded highly-mature detection technologies for 3D-localized radiological measurements. These will complete the facilities’ available data into a 3D and fully detailed Digital Twin of the surveyed area, thus improving the planning and traceability of the D&D operations.

Coverage Path Planning Optimization of Heterogeneous UAVs Group for Precision Agriculture

Precision farming is one of the ways of transition to the intensive methods of agricultural production. The case of application of unmanned aerial vehicles (UAVs) for solving problems of agriculture and animal husbandry is among the actively studied issues. The UAV is capable of solving the tasks of monitoring, fertilizing, herbicides, etc. However, the effective use of UAV requires to solve the tasks of flight planning, taking into account the heterogeneity of the available attachments and the problem solved in the process of the overflight. This research investigates the problem of flight planning of a group of heterogeneous UAVs applied to solving the issues of coverage, which may arise both in the course of monitoring and in the process of the implementation of agrotechnical measures. The method of coverage path planning of heterogenic UAVs group based on a genetic algorithm is proposed; this method provides planning of flight by a group of UAVs using a moving ground platform on which UAVs are recharged and refueled (multi heterogenic UAVs coverage path planning with moving ground platform (mhCPPmp)). This method allows calculating a fly by to solve the task of covering fields of different shapes and permits selecting the optimal subset of UAVs from the available set of devices; it also provides a 10% reduction in the cost of a flyby compared to an algorithm that does not use heterogeneous UAVs or a moving platform.

Rotorcraft aerial vehicle’s contact-based landing and vision-based localization research

AbstractA novel concept—the contact-based landing on a mobile platform—is proposed in this paper. An adaptive backstepping controller is designed to deal with the unknown disturbances in the interactive process, and the contact-based landing mission is implemented under the hybrid force/motion control framework. A rotorcraft aerial vehicle system and a ground mobile platform are designed to conduct flight experiments, evaluating the feasibility of the proposed landing scheme and control strategy. To the best of our knowledge, this is the first time a rotorcraft unmanned aerial vehicle has been implemented to conduct a contact-based landing. To improve system autonomy in future applications, vision-based recognition and localization methods are studied, contributing to the detection of a partially occluded cooperative object or at a close range. The proposed recognition algorithms are tested on a ground platform and evaluated in several simulated scenarios, indicating the algorithm’s effectiveness.

Deep Reinforcement Learning with Corrective Feedback for Autonomous UAV Landing on a Mobile Platform

Autonomous Unmanned Aerial Vehicle (UAV) landing remains a challenge in uncertain environments, e.g., landing on a mobile ground platform such as an Unmanned Ground Vehicle (UGV) without knowing its motion dynamics. A traditional PID (Proportional, Integral, Derivative) controller is a choice for the UAV landing task, but it suffers the problem of manual parameter tuning, which becomes intractable if the initial landing condition changes or the mobile platform keeps moving. In this paper, we design a novel learning-based controller that integrates a standard PID module with a deep reinforcement learning module, which can automatically optimize the PID parameters for velocity control. In addition, corrective feedback based on heuristics of parameter tuning can speed up the learning process compared with traditional DRL algorithms that are typically time-consuming. In addition, the learned policy makes the UAV landing smooth and fast by allowing the UAV to adjust its speed adaptively according to the dynamics of the environment. We demonstrate the effectiveness of the proposed algorithm in a variety of quadrotor UAV landing tasks with both static and dynamic environmental settings.

A Review of Current and Historical Research Contributions to the Development of Ground Autonomous Vehicles for Agriculture

In this study, a comprehensive overview of the available autonomous ground platforms developed by universities and research groups that were specifically designed to handle agricultural tasks was performed. As cost reduction and safety improvements are two of the most critical aspects for farmers, the development of autonomous vehicles can be of major interest, especially for those applications that are lacking in terms of mechanization improvements. This review aimed to provide a literature evaluation of present and historical research contributions toward designing and prototyping agricultural ground unmanned vehicles. The review was motivated by the intent to disseminate to the scientific community the main features of the autonomous tractor named BOPS-1960, which was conceived in the 1960s at the Alma Mater Studiorum University of Bologna (UNIBO). Jointly, the main characteristics of the modern DEDALO unmanned ground vehicle (UGV) for orchard and vineyard operations that was designed recently were evaluated. The basic principles, technology and sensors used in the two UNIBO prototypes are described in detail, together with an analysis of UGVs for agriculture conceived in recent years by research centers all around the world.

PRACTICAL APPROACH FOR THE SAFETY IN I - GIRDER CASTING AND STRESSING IN CASTING YARD

Infrastructure development is the very important for any Country. Highway’s infrastructure comprises two part say Roads and Bridges, supplementary to each other. In modern projects the part of structures is increased about 40% to 50% which have very big influence to complete the project within targeted span of period. As per site condition and aesthetic requirement, there are several types of bridges. Bridges comprises different type of superstructure. I-girder is one of the simplest and popular forms of super structure adopted for bridges. The casting of I Girders is may be easy the job because you are casting them on the ground platform. This is the first part and second part are launching/erection of I-Girders after stressing. This paper is mainly written to share the knowledge and how to reduce the consequences, mainly to boost the site staff moral for the construction process. The erection activity is highly critical and to be done in very safe manner. Each step of erection must be followed by the all concerns. Now a days the clients are also very strict and specific with extra vigilant in girder erection process. This document is just a guideline and to spread awareness to all concerns. The burning issue of incidences in civil constructions and the requisite precautionary measures to avoid the same and consequential loss of properties and life.

Range-aided ego-centric collaborative pose estimation for multiple robots

Robots’ simultaneous relative pose estimation has become an essential step in most robotic-oriented problems, such as map merging, collision avoidance, path planning, and multi-Simultaneous Localization and Mapping (SLAM). This article addresses the problem of 3D and ego-centric relative pose estimation for a team of robots equipped with Ultra WideBand (UWB) nodes. More specifically, the article introduces a novel optimization framework to obtain pose information based on the embodiment of UWB ranges, without relying on any fixed external infrastructure configuration of UWB anchors on the surrounding environment. In the proposed method, we demonstrate the validity through the utilization of a Micro Aerial Vehicle (MAV) and a ground vehicle that are equipped with multiple UWB transceivers, and each platform simultaneously acts as a based anchor for the other platform for extracting an ego-centric position estimation of the UWB nodes. Additionally, for the pose estimation, the obtained information is fused with the onboard Inertial Measurement Unit (IMU) measurements on each of the considered robotic platforms. Finally, the efficacy of the proposed theoretical framework is evaluated in multiple experiments, where the aerial and ground platforms are simultaneously and separately navigating, and the ego-centric collaborative pose-estimation is compared with a VICON ground truth positioning system.