Ground Robots Research Articles

Distributed Nonlinear Predictive Control for Unmanned Air-Ground Vehicles

This paper addresses the formation path tracking for a heterogeneous system made up of a steering car and a quadcopter. System modelling is based on Nonlinear Model Predictive Control (NMPC), which is a proper solution when considering a heterogeneous feet as not only it deals with non-linearities of the dynamic model but it is also a way to generate trajectories that can be communicated to other agents. Moreover, an Extended Kalman Filter (EKF) is employed to estimate the non-measurable ground robot state variables. Two separate simulations in Simulink for each agent have been carried out leading to promising results in terms of tracking errors. Indeed, tests show that the proposed solution allows the two vehicles to follow the reference aligned with a deviation of a few centimeters.

Portable Planner For Enhancing Ground Robots Exploration Performance In Unstructured Environments

Portable Planner For Enhancing Ground Robots Exploration Performance In Unstructured Environments

Smart railways: the design and construction of an autonomous inspection and maintenance vehicle

The Railway Inspection and Maintenance Vehicle (RIMV) is a state-of-the-art autonomous ground robot for the railway environment. The robot has specialised hardware tailored for specific functionalities, ensuring optimal performance in its designated tasks. It incorporates a GPS, IMU, and encoder for robust localisation, and it integrates a LiDAR system and a depth camera for collision avoidance. Prioritising safety, the RIMV features an IP camera for real-time environmental monitoring and is equipped with emergency stop mechanisms. An Ubuntu Linux machine manages the robot’s data processing, complemented by a 5G Wi-Fi router for remote monitoring and operation when necessary. ROS2 is the primary platform for robot operations, standing out for its open-source solution and enhanced cybersecurity features. We validated the RIMV in a heritage railway setting with an ultrasonic inspection kit to detect rail-track defects. Beyond this specific application, the RIMV is versatile and designed to serve as a platform for other autonomous inspection and maintenance tasks within the railway sector. Its adaptability highlights its potential to enhance efficiency and safety in railway maintenance, offering invaluable assistance to human operators across varied scenarios.

The Application of SLAM in Life and Scientific Research

This article mainly focuses on the application of SLAM in technology and provides a literature review on the following aspects: 1) The application of SLAM in automatic parking of automobiles. This includes using AVP-SLAM for high-precision automatic parking in outdoor parking lots using convolutional neural networks, and using MOFISLM for high-precision automatic parking when indoor GPS signals are poor. 2) The application of SLAM in robotics. It includes three aspects. The first is using the GMapping algorithm to construct and locate maps with high accuracy, low computational complexity, and high robustness, enabling robots to plan the shortest path in unknown environments. The second is to use ORB-SLAM2, which can handle more complex situations, to navigate medical institution robots to improve hospital efficiency and reduce disease transmission rates. The third is for robots that perform tasks in complex and unknown terrains. The improved version of LAMP1.0, LAMP2.0, which is suitable for complex underground environments, can achieve multi robot collaborative cooperation with high accuracy and robustness. 3) Application of SLAM in the field of unmanned aerial vehicles. This article mainly elaborates on four aspects. The first is to use visual SLAM to achieve collaborative work between ground robots and drones, and to utilize the high camera advantage of drones to quickly build maps for ground robots, improve accuracy, and save time. The second is to utilize the application of VSLAM on unmanned aerial vehicles to contribute to agriculture. The third is ORB-SLAM3 to provide rapid and high-precision landing on deck for unmanned aerial vehicles in maritime missions. The fourth is using SLAM to assist unmanned aerial vehicles in landing in emergency or position situations (such, when GPS signals are lost).

RESEARCH ON 3D MEASUREMENT TECHNOLOGY BASED ON MACHINE VISION

Measurement is an important means for humans to understand and transform the world, and it is the technological foundation for breaking through the forefront of science and solving major problems in economic and social development. The three-dimensional measurement system serves primary national needs, leads national economic development, and ensures national defense security. With the arrival of a new industrial revolution, major industrial countries worldwide have begun to accelerate the strategic deployment of intelligent manufacturing. As an essential component of the construction of smart factories and lighthouse factories, the 3D measurement system will play a vital role in deepening the implementation of the manufacturing power strategy and promoting the high-end, intelligent, and green manufacturing process. In recent years, optical 3D measurement technology represented by surface structured light has developed rapidly and has been widely applied in multiple material processing fields such as forging, casting, and sheet metal. To analyze the manufacturing accuracy of complex parts using surface structured light 3D measurement technology, it is necessary to first scan and reconstruct the overall 3D surface of the part. The reconstructed 3D point cloud data of the part surface should be roughly and precisely matched with the design model. Finally, based on this, data comparison and accuracy analysis should be carried out according to the actual detection requirements of different types of parts. In this process, the accuracy of 3D reconstruction of complex parts and the alignment accuracy between the reconstruction results and the design model directly determine the reliability and accuracy of the final part manufacturing and machining accuracy analysis. This article uses cases to illustrate the application of machine vision in 3D online measurement. The application of three-dimensional measurement technology in online quality inspection and grinding of blades can not only improve the measurement accuracy of online quality inspection of blades but also maintain the relative stability of robot grinding force and improve the grinding effect in robot grinding of aircraft engine blades. Applied to online quality inspection of train wheel hubs, three-dimensional measurement of train wheel adapters and high-speed train wheel size online inspection has been achieved.

Cyber-WISE: A Cyber-Physical Deep Wireless Indoor Positioning System and Digital Twin Approach.

In recent decades, there have been significant research efforts focusing on wireless indoor localization systems, with fingerprinting techniques based on received signal strength leading the way. The majority of the suggested approaches require challenging and laborious Wi-Fi site surveys to construct a radio map, which is then utilized to match radio signatures with particular locations. In this paper, a novel next-generation cyber-physical wireless indoor positioning system is presented that addresses the challenges of fingerprinting techniques associated with data collection. The proposed approach not only facilitates an interactive digital representation that fosters informed decision-making through a digital twin interface but also ensures adaptability to new scenarios, scalability, and suitability for large environments and evolving conditions during the process of constructing the radio map. Additionally, it reduces the labor cost and laborious data collection process while helping to increase the efficiency of fingerprint-based positioning methods through accurate ground-truth data collection. This is also convenient for working in remote environments to improve human safety in locations where human access is limited or hazardous and to address issues related to radio map obsolescence. The feasibility of the cyber-physical system design is successfully verified and evaluated with real-world experiments in which a ground robot is utilized to obtain a radio map autonomously in real-time in a challenging environment through an informed decision process. With the proposed setup, the results demonstrate the success of RSSI-based indoor positioning using deep learning models, including MLP, LSTM Model 1, and LSTM Model 2, achieving an average localization error of ≤2.16 m in individual areas. Specifically, LSTM Model 2 achieves an average localization error as low as 1.55 m and 1.97 m with 83.33% and 81.05% of the errors within 2 m for individual and combined areas, respectively. These outcomes demonstrate that the proposed cyber-physical wireless indoor positioning approach, which is based on the application of dynamic Wi-Fi RSS surveying through human feedback using autonomous mobile robots, effectively leverages the precision of deep learning models, resulting in localization performance comparable to the literature. Furthermore, they highlight its potential for suitability for deployment in real-world scenarios and practical applicability.

Research on a Method of Robot Grinding Force Tracking and Compensation Based on Deep Genetic Algorithm

In the grinding process of complex-shaped cast workpieces, discrepancies between the workpiece’s contours and their corresponding three-dimensional models frequently lead to deviations in the machining trajectory, resulting in instances of under-grinding or over-grinding. Addressing this challenge, this study introduces an advanced robotic grinding force automatic tracking technique, leveraging a combination of deep neural networks and genetic algorithms. Harnessing the capability of force sensing, our method dynamically recalibrates the grinding path, epitomizing truly flexible grinding. Initially, in line with the prerequisites for force and pose tracking, an impedance control strategy was developed, integrating pose deviations with force dynamics. Subsequently, to enhance steady-state force tracking, we employed a genetic algorithm to compensate for force discrepancies caused by positional errors. This was built upon the foundational concepts of the three-dimensional model, impedance control, and environmental parameter estimation, leading to an optimized grinding trajectory. Following tracking tests, it was observed that the grinding’s normal force was consistently controlled within the bracket of 20 ± 2.5 N. To further substantiate our methodology, a specialized experimental platform was established for grinding complex-shaped castings. Optimized strategies were employed under anticipated forces of 5 N, 10 N, and 15 N for the grinding tests. The results indicated that the contact forces during the grinding process remained stable at 5 ± 1 N, 10 ± 1.5 N, and 15 ± 2 N. When juxtaposed with conventional teaching grinding methods, our approach manifested a reduction in grinding forces by 71.4%, 70%, and 75%, respectively. Post-grinding, the workpieces presented a pronounced enhancement in surface texture, exhibiting a marked increase in surface uniformity. Surface roughness metrics, originally recorded at 17.5 μm, 17.1 μm, and 18.7 μm, saw significant reductions to 1.5 μm, 1.6 μm, and 1.4 μm, respectively, indicating reductions by 76%, 73%, and 78%. Such outcomes not only meet the surface finishing standards for complex-shaped castings but also offer an efficacious strategy for robot-assisted flexible grinding.

A signal-to-image fault classification method based on multi-sensor data for robotic grinding monitoring

A signal-to-image fault classification method based on multi-sensor data for robotic grinding monitoring

Modification of the Ant Colony Optimization Algorithm for Solving Multi-Agent Task Allocation Problem in Agricultural Application

This paper considers the problem of task allocation where the goal is to find a coalition of UAVs (agents) to complete on-farm agricultural tasks. In this study, Ant Colony Optimization (ACO) algorithm is employed to find the best coalition of agents. The performance of the basic ACO algorithm for solving task allocation is improved by modifying the efficiency factor. In the proposed algorithm, the efficiency factor is defined as a function that relates not only to the capability of the agents and the distance between the agents, but also to the distance between the agents and the target. To solve the task allocation problem, the capability list of the agents was also adjusted using common UAV capabilities in agricultural application. Simulation results showed that the proposed ACO algorithm with the modified efficiency factor improved the performance of basic ACO algorithm for solving task allocation problem in terms of the average total travel cost for each agent. The optimum number of ants and agents in the proposed algorithm was also analysed for robust performance. Simulation results revealed that the addition of the numbers of agents and ants increases the average efficiency of the algorithm. In this study, we have also added a function to calculate the system capability utilization. By employing such a function, simulation results show that the total resource used by the agents and total communication cost can be optimized. In addition, a simple experiment using five ground robots with a centralized control was also carried out as a proof of concept for the proposed algorithm.

GWO-PID of Two-phase Hybrid Stepping Motor for Robotic Grinding Force

The use of the computer program MATLAB is prominent in many studies that simulate many industrial systems. The current simulation aims to build a suitable simulation model representing the Two-phase Hybrid Stepping Motor (2Ph-HSM). This type of motor is employed in a specific application to produce a force called automatic grinding force. To control the force, motor speed, and location, we need to add control systems, so two methods have been proposed, one of which is traditional, namely proportional, integral, and derivative (PID) control and the other is intelligent, called Gray Wolf Optimization (GWO). The current work also aims to use traditional control algorithms and advanced optimization algorithms that were chosen for their ease of control and possibility of use in many industrial applications. By setting appropriate specifications for the simulation model and after conducting prescribed tests that simulate different applications of the motor’s work within electrical systems, the results demonstrated good motor performance, better response, and high accuracy, in addition to speed. The goal is to design and tune a proportional, integral, and derivative (PID) controller by gray wolf optimization (GWO) using the transfer function (TF) of a 2Ph-HSM. To adjust the parameters of conventional controllers using advanced optimization, a suitable mechanism and technique were selected from advanced optimization techniques, where the gray wolf technique algorithm was chosen as an optimization technique and Integrated Time Absolute Error (ITAE) to adjust the parameters of conventional PID controller.

Improved UAV-to-Ground Multi-Target Tracking Algorithm Based on StrongSORT.

Unmanned aerial vehicles (UAV) are essential for aerial reconnaissance and monitoring. One of the greatest challenges facing UAVs is vision-based multi-target tracking. Multi-target tracking algorithms that depend on visual data are utilized in a variety of fields. In this study, we present a comprehensive framework for real-time tracking of ground robots in forest and grassland environments. This framework utilizes the YOLOv5n detection algorithm and a multi-target tracking algorithm for monitoring ground robot activities in real-time video streams. We optimized both detection and re-identification networks to enhance real-time target detection. The StrongSORT tracking algorithm was selected carefully to alleviate the loss of tracked objects due to factors like camera jitter, intersecting and overlapping targets, and smaller target sizes. The YOLOv5n algorithm was used to train the dataset, and the StrongSORT tracking algorithm incorporated the best-trained model weights. The algorithm's performance has greatly improved, as demonstrated by experimental results. The number of ID switches (IDSW) has decreased by sixfold, IDF1 has increased by 7.93%, and false positives (FP) have decreased by 30.28%. Additionally, the tracking speed has reached 38 frames per second. These findings validate our algorithm's ability to fulfill real-time tracking requisites on UAV platforms, delivering dependable resolutions for dynamic multi-target tracking on land.

A real‐time fuzzy motion planning system for unmanned aerial vehicles in dynamic 3D environments

This paper presents a new fuzzy potential system to plan the motion of Unmanned Aerial Vehicles (UAVs) in dynamic 3D Space. The system consists of two fuzzy subsystems representing the attractive model and the repulsive model of virtual forces in 3D. The attractive model will generate the attractive force required to pull the UAV in a smooth and optimized trajectory to land softly on a moving or stationary target. The repulsive model will generate the required repulsive force to avoid stationary or moving obstacles in 3D Space. The attractive fuzzy inference system takes the relative position and relative velocity between UAV and the target in the x, y, and z directions as inputs. It generates the required attractive force in the x, y, and z directions. The repulsive fuzzy inference system takes the relative position between UAV and obstacle in the xyz directions as input. Fuzzy associative memory (FAM) models the inputs and generates the required repulsive force in the x, y, and z directions. As a result, the UAV is considered to be moving under the influence of fuzzy virtual attractive and repulsive forces simultaneously. Accordingly, it will be able to change both its altitude and projected planner position concurrently and resolves the local minima problem if occurred. On the other hand, many classical models in dynamic environments require several additional inputs, such as the relative position and relative velocity, which increase the requirement on the measurement system to localize the moving objects in the 3D Space. Several experiments were performed and discussed to verify the robustness and effectiveness of the proposed motion planner with real-time implementations. The system performance was validated using three robotics platforms, two quadcopter drones, and one ground robot. The position and orientation of each robot were defined using a motion capture system with 6 opti-track cameras. The motion planning system produces a quadcopter drone's efficient and accurate low-frequency trajectory. The generated trajectory allows the drone to track the ground robot and avoid collision effectively with the second drone in the vicinity.

Dual PID Adaptive Variable Impedance Constant Force Control for Grinding Robot

High-precision and low-overshoot force control are important to guarantee the material removal rate and surface quality of robot grinding. However, traditional force control methods are subjected to positional disturbance, stiffness disturbance, contact process nonlinearity, and force-position coupling, leading to difficulties in robot constant force control. Therefore, how to achieve smooth, stable, and high-precision constant force control is an urgent problem. To address this problem, a dual PID adaptive variable impedance control is established (DPAVIC). Firstly, PD control is used to compensate for the force error, and PID is used to update the damping parameters to compensate for the disturbance. Secondly, a nonlinear tracking differentiator is used to smooth the desired force and reduce the contact force overshoot. Then, the stability, convergence, and effectiveness of the force control algorithm are verified via theoretical analysis, simulations, and experiments. The force tracking error and overshoot of a conventional impedance controller (CIC), adaptive variable impedance control (AVIC), and DPAVIC are analyzed. Finally, the algorithm is used in grinding experiments on a thin-walled workpiece. The force tracking error is controlled within ±0.2 N, and the surface roughness of the workpiece is improved to Ra 0.218 μm.

Research on robotic belt grinding method of blisk for obtaining high surface integrity features with variable inclination angle force control

The blisk was a new type of component for high-performance aero-engines, which could significantly improve the energy efficiency ratio of the engine, however there were also shortcomings such as narrow structure and difficult material removal. Robotic belt grinding was widely used in the processing of key complex surfaces such as blades, fairings and propellers, which is due to its large processing space and high flexibility. Nevertheless, how to improve the surface integrity of the blisk under the premise of ensuring the profile accuracy was a challenging problem. In view of the above problems, this study started with the grinding force, and innovatively proposed a robotic belt grinding method for high surface integrity of blisk based on variable inclination angle force control. Firstly, a belt grinding robot based on macro-micro-end hand structure and electromagnetic force-controlled end was designed based on indirect arm-winding control. Secondly, an adaptive variable impedance compliance based blisk grinding model was established through the relation expression of grinding end and the mathematical formula of inclination contact micro-surface control, which effectively coordinates the coupling relationship between force control and trajectory under inclined attitude. Lastly, the experimental study proved that the normal grinding force of this method was stable and the error was 1.14 %, the surface hardness and residual compressive stress were improved by about 8.57 % and 52.82 % respectively, the surface morphology was uniform and the surface defects are well suppressed. The surface integrity of the blisk was significantly improved.

Robot Ground Media Classification Based on Hilbert–Huang Transform and Attention-Based Spatiotemporal Coupled Network

With the development of technology, mobile robots are increasingly deployed in real-world environments. To enable robots to work safely in a variety of terrain environments, we proposed a ground-type detection method based on the Hilbert–Huang transform (HHT) and attention-based spatiotemporal coupled network. Taking a dataset containing multiple sets of robot signals from a Kaggle competition as an example; we use the proposed method to classify the signals and thus achieve a terrain classification of the robot’s location. Firstly, the signal data were processed using the discrete wavelet transform for noise reduction, and all channels in the dataset were ranked by importance using the permutation importance method. Next, the instantaneous frequencies of the two most important channels were extracted using the HHT and added to the original dataset to expand the feature dimension. Then the features in the expanded dataset were extracted by the convolutional neural network, long short-term memory, and attention module. Afterward, the fully extracted features were passed into the fully connected layer for classification, and an average classification accuracy of 83.14% was obtained. The effectiveness of each part in our method was demonstrated using ablation experiments. Finally, we compared our method with some common methods in the field and found that our method obtained the highest classification accuracy, proving the superiority of the proposed method.

Effect of Grinding Parameters on Industrial Robot Grinding of CFRP and Defect Formation Mechanism

Effect of Grinding Parameters on Industrial Robot Grinding of CFRP and Defect Formation Mechanism

Kinematic Modeling and Optimization of a Clustered Tensegrity Mobile Robot

Abstract Clustered tensegrity mechanisms have elicited extensive attention in recent research due to their easy control system and high stiffness-to-mass ratio. However, modeling and analyzing these mechanisms are still challenging due to the clustering of cables and redundant structural parameters. This article proposes an energy-based kinematic modeling method for a modular clustered tensegrity mobile robot. The design of the clustered tensegrity robot is inspired by the biomechanics of worms, allowing it to achieve two locomotion modes resembling earthworm-like and inchworm-like movements using two motors. Moreover, the clustered and modular structure enables the robot to increase the number of modules as needed without increasing the number of actuators. This feature enhances the robot's terrain adaptability without adding complexity to the control system. The article establishes kinematic models using the energy method and clarifies the motion law of nodes on the sliding cables of the robot, considering multiple structural parameters for both locomotion modes. Based on these models, the article reveals the mapping relationships among various structural parameters (i.e., cable-hole gap, cable-hole friction, stiffness and original length of elastic cables, and ground–robot friction) and locomotion performance (i.e., morphology, displacement, and velocity) of the robot. Furthermore, structural parameter optimization is performed to enhance the kinematic performance of the robot in both locomotion modes simultaneously. To validate the proposed kinematic modeling method, a prototype with two modules is developed, and experiments are conducted to assess the robot's locomotion performance. These experiments demonstrate the effectiveness and rationality of the proposed method.

Distributed Control for Multi-Robot Interactive Swarming Using Voronoi Partioning

The problem of safe navigation of a human-multi-robot system is addressed in this paper. More precisely, we propose a novel distributed algorithm to control a swarm of unmanned ground robots interacting with human operators in presence of obstacles. Contrary to many existing algorithms that consider formation control, the proposed approach results in non-rigid motion for the swarm, which more easily enables interactions with human operators and navigation in cluttered environments. Each vehicle calculates distributively and dynamically its own safety zone in which it generates a reference point to be tracked. The algorithm relies on purely geometric reasoning through the use of Voronoi partitioning and collision cones, which allows to naturally account for inter-robot, human-robot and robot-obstacle interactions. Different interaction modes have been defined from this common basis to address the following practical problems: autonomous waypoint navigation, velocity-guided motion, and follow a localized operator. The effectiveness of the algorithm is illustrated by outdoor and indoor field experiments.

Robotic compliant grinding of curved parts based on a designed active force-controlled end-effector with optimized series elastic component

High-accuracy, fast-response, and low-overshoot force control are important to guarantee the material removal accuracy and surface quality of robotic compliant grinding. In order to achieve the above target, this study develops an active compliant force-controlled end-effector based on a series elastic actuator for the robotic grinding of curved parts. Firstly, a decoupled robotic grinding system composed of an industrial robot and an end-effector is developed, and a novel force-controlled end-effector is designed by adding an elastic component between the servo motor and the load to improve compliance. Secondly, the influences of the elastic component and grinding tool stiffness on the stability of the force-controlled end-effector system are analyzed by establishing a contact model of the compliant end-effector and the transfer function of the entire force control system. Then, the stiffness of the grinding tool and the elastic component are optimized with full consideration of the system cutoff frequency and the end-effector compliance. To improve the force tracking accuracies of the developed compliant end-effector, a proportional-integral (PI) controller with first-order differential force feedforward control is designed. Finally, grinding experiments are conducted for verification. The effects of spring stiffness and grinding tool stiffness on the force control system are tested, which match well with the theoretical analysis. Grinding results show that the maximum force control error of the compliant force-controlled end-effector is decreased by 70% compared to that of the rigid force-controlled end-effector, and the overshoot of the force control is reduced from 30% to almost 0 under the same response speed. The maximum and average absolute grinding depth errors using the designed end-effector are reduced by 57.2% and 58.6%, respectively, compared with those of the traditional rigid end-effector, and the average surface roughness of the finished part is reduced by 19.2%. Which demonstrates the effectiveness and advantages of the proposed compliant force-controlled end-effector.

Pyramidal 3D feature fusion on polar grids for fast and robust traversability analysis on CPU

Self-driving vehicles and autonomous ground robots require a reliable and accurate method to analyze the traversability of the surrounding environment for safe navigation. This paper proposes and evaluates a real-time machine learning-based traversability analysis method that combines geometric features with a pyramid-polar space representation based on SVM classifiers. In particular, we show that by fusing geometric features with information stemming from coarser pyramid levels that account for a broader space portion, as well as integrating important implementation details, allows for a noticeable boost in performance and reliability. The main goal of this work is to demonstrate that traversability analysis is possible with effective results and in real-time even on cheaper hardware than expensive GPUs, e.g. CPU-only PCs. The proposed approach has been compared with state-of-the-art deep learning approaches on publicly available datasets of outdoor driving scenarios, running such algorithms both on GPU and CPU to compare runtimes. Our method can be fully executed on CPU and achieves results close to the best-in-class methods, runs faster, and requires fewer and less expensive hardware resources, consuming less than 30% electrical power with respect to deep learning models on embedded processing units. We release with this paper the open-source implementation of our method.