ROS Platform Research Articles

Trajectory planning and automatic docking of LNG five-axis loading arm

PurposeIn response to the challenges posed by the conventional manual flange docking method in the LNG (Liquefied Natural Gas) loading process, such as low positioning accuracy, constraints on production efficiency and safety hazards, this study analyzed the LNG five-axis loading arm’s main functions and structural characteristics.Design/methodology/approachAn automated solution for the joints of the LNG loading arm was designed. The forward kinematic model of the LNG loading arm was established using the Denavit–Hartenberg (D-H) parameter method, and its workspace was analyzed. The Newton–Raphson iteration method was employed to solve the inverse kinematics of the LNG loading arm, facilitating trajectory planning. The relationship between the target position and the joint variables was established to verify the stability of the arm’s motion. Flange center identification was achieved using the Hough transform function. Based on the ROS platform, combined with Gazebo and Rviz, an experimental simulation of automatic docking of the LNG loading arm was conducted.FindingsThe docking errors in the XYZ directions were all less than 0.8 mm, meeting the required docking accuracy. Moreover, the motion performance of the loading arm during docking was smooth and free of abrupt changes, validating its capability to accomplish the automatic docking task.Originality/valueThe proposed trajectory planning and automatic docking scheme can be used for the rapid filling of LNG filling arms and LNG tankers to improve the efficiency of LNG transportation. In guiding the docking, the proposed automatic docking scheme is an accurate and efficient way to improve safety.

Research and Implementation of Robotic Arm Positioning and Grasping Based on Visual Guidance

Abstract This paper proposes a robotic arm vision guidance system based on the ROS platform, which combines the Hikrobot Robotics 2D vision sensor with the Xinsong GCR5 robotic arm to successfully realise vision-guided robotic arm positioning and grasping. Camera calibration, hand-eye calibration, and deep learning techniques are used to establish an accurate transformation relationship between the base coordinate system of the robotic arm and the camera coordinate system to achieve efficient target goal recognition and localisation. Adopting the MoveIt framework and RRT-connect algorithm, the robotic arm can flexibly plan the movement path and successfully complete the target grasping, which provides the theoretical basis and practical experience for robotic arm intelligent grasping.

Improving path planning for mobile robots in complex orchard environments: the continuous bidirectional Quick-RRT* algorithm.

Efficient obstacle-avoidance path planning is critical for orchards with numerous irregular obstacles. This paper presents a continuous bidirectional Quick-RRT* (CBQ-RRT*) algorithm based on the bidirectional RRT (Bi-RRT) and Quick-RRT* algorithms and proposes an expansion cost function that evaluates path smoothness and length to overcome the limitations of the Quick-RRT* algorithm for non-holonomic mobile robot applications. To improve the zigzag between dual trees caused by the dual-tree expansion of the Bi-RRT algorithm, CBQ-RRT* proposes the CreateConnectNode optimization method, which effectively solves the path smoothness problem at the junction of dual trees. Simulations conducted on the ROS platform showed that the CBQ-RRT* outperformed the unidirectional Quick-RRT* in terms of efficiency for various orchard layouts and terrain conditions. Compared to Bi-RRT*, CBQ-RRT* reduced the average path length and maximum heading angle by 8.5% and 21.7%, respectively. In addition, field tests confirmed the superior performance of the CBQ-RRT*, as evidenced by an average maximum path lateral error of 0.334m, a significant improvement over Bi-RRT* and Quick-RRT*. These improvements demonstrate the effectiveness of the CBQ-RRT* in complex orchard environments.

Development of Local Path Planning Using Selective Model Predictive Control, Potential Fields, and Particle Swarm Optimization

This paper focuses on the real-time obstacle avoidance and safe navigation of autonomous ground vehicles (AGVs). It introduces the Selective MPC-PF-PSO algorithm, which includes model predictive control (MPC), Artificial Potential Fields (APFs), and particle swarm optimization (PSO). This approach involves defining multiple sets of coefficients for adaptability to the surrounding environment. The simulation results demonstrate that the algorithm is appropriate for generating obstacle avoidance paths. The algorithm was implemented on the ROS platform using NVIDIA’s Jetson Xavier, and driving experiments were conducted with a steer-type AGV. Through measurements of computation time and real obstacle avoidance experiments, it was shown to be practical in the real world.

Path Planning of a Mobile Robot for a Dynamic Indoor Environment Based on an SAC-LSTM Algorithm.

This paper proposes an improved Soft Actor-Critic Long Short-Term Memory (SAC-LSTM) algorithm for fast path planning of mobile robots in dynamic environments. To achieve continuous motion and better decision making by incorporating historical and current states, a long short-term memory network (LSTM) with memory was integrated into the SAC algorithm. To mitigate the memory depreciation issue caused by resetting the LSTM's hidden states to zero during training, a burn-in training method was adopted to boost the performance. Moreover, a prioritized experience replay mechanism was implemented to enhance sampling efficiency and speed up convergence. Based on the SAC-LSTM framework, a motion model for the Turtlebot3 mobile robot was established by designing the state space, action space, reward function, and overall planning process. Three simulation experiments were conducted in obstacle-free, static obstacle, and dynamic obstacle environments using the ROS platform and Gazebo9 software. The results were compared with the SAC algorithm. In all scenarios, the SAC-LSTM algorithm demonstrated a faster convergence rate and a higher path planning success rate, registering a significant 10.5 percentage point improvement in the success rate of reaching the target point in the dynamic obstacle environment. Additionally, the time taken for path planning was shorter, and the planned paths were more concise.

Mapping and Autonomous Obstacle Avoidance of Mobile Robot Based on ROS Platform

Mapping and Autonomous Obstacle Avoidance of Mobile Robot Based on ROS Platform

Development of mobile smart material-handling system

The global surge for achieving economics in the field of manufacturing has led to the evolution of the industrial manufacturing system to industry 4.0. Autonomous mobile robots are integral to the smart manufacturing and logistics system. In this work, a smart material handling system is designed and developed, which can work autonomously and can be integrated with another subsystem of the manufacturing system. An algorithm is developed on the ROS platform for performing loading, transportation, and unloading operations while navigating the path autonomously. Simulation is done using Gazebo and RViz application software. A CAD of a scissor lift for loading/unloading operations is designed using Autodesk Fusion360 and fabricated through FDM 3D printing. For validation, a working model of the smart material handling system is developed by mounting the scissors lift on a commercially available mobile robot Turtlebot3 Waffle Pi and interfacing the scissors lift actuators with the mobile robot controller. The simulation and experimental results for various layouts of the warehouse validate the developed system.

Application of A Grasping Autonomous Transport Robotic Car with Machine Vision in the Express Industry in China

In recent years, COVID-19 has badly affected people’s lives, and most industries have been hit hard, the express industry is a typical example, if the staff needs to be quarantined for epidemic control, the work efficiency of the express transfer center would reduce. In this project, to solve problems in the express industry, an autonomous transport car with a robotic arm was designed by using the technology of machine vision, path planning, SLAM, etc. The robot was simulated in the ROS platform m replaced by the turtlebot3 robot. As the result, the robot will go to the position set by Python code in the gazebo, when the robot identified the target, it will keep going straight forward to the target while keeping the target in the center of the camera. If the distance between the camera and the target is 0.15 meters, the car will stop and the robotic arm would grasp the target automatically. After the grasp, the robot will go to the destination and put the target in the basket. The result of the simulation shows that this robot can be applied to the express transfer center.

A Mobile Robot with a Manipulator to Alleviate the Shortage of Health Workers in Hospitals in COVID 19

COVID-19 has brought an unprecedented burden to hospitals. Hospitals are facing many problems, such as understaffing and infected employees. But this has also promoted the development of hospital robots to a certain extent. This paper aimed to develop a robot that can move around the hospital and pick and send stuff to patients. The robot is mainly divided into 2 two parts: the moving part and the grasping part. The moving part includes map construction, localization, and navigation with gmapping, A*, and DWA algorithms that would stimulate on the ROS platform. For the grasping part, the forward and inverse kinematics of the robot arm and PD control would be analyzed using MATLAB with the Robotics System Toolbox, Simulink, and Simscape Multibody to simulate and control the robot arm. Using this approach, the robot can reach the target position and avoid dynamic obstacles. In addition, the robot arm can pick up and drop the ball with the designed trajectory.

Research on path planning of mobile robot based on improved genetic algorithm

The basic genetic algorithm usually has the following problems when solving robot path planning problems. First, the chromosome (path) of the first generation is randomly generated, so its fitness is often too high, resulting in too slow convergence speed and even unable to obtain the global optimal solution. Second, in the crossover operator, the selection of crossover points is often random, which cannot ensure that the fitness of cross generated offspring is better than that of their parents. Finally, in the mutation stage, because the traditional mutation strategy is to replace the selected mutation node in the individual chromosome with a random node, the offspring path generated by the mutation operator is likely to be discontinuous, so it cannot reflect the effectiveness of the mutation operator. Based on the mentioned contents, some improved strategies are proposed for the discussed three shortcomings of the basic genetic algorithm. First, a new generation mechanism of the first generation is constructed by simulating the path finding rules of ants in ant colony optimization, which greatly improves the quality of the first generation. Second, during crossover operator, the chromosomes of the two parents are disconnected at the same node, and the optimal chromosome fragments in each segment are combined based on greed, so as to gather all the excellent gene fragments of the parents in an individual as much as possible, improve the quality of the offspring after crossover operator, and speed up the convergence speed. Finally, a new mutation strategy is proposed to eliminate redundant sections and the number of corners, so that the individuals always can be mutated in a good direction. A large number of simulation results show that the improved genetic algorithm is effective in solving the robot path planning problem, and the overall performance is better than the basic genetic algorithm and some other improved genetic algorithms. Finally, by modeling and simulating the real enterprise factory environment based on the ROS platform, the experimental results also verify the effectiveness and feasibility of the improved genetic algorithm.

Indoor Top Mobile Service Robot Based on Improved RRT Algorithm

An indoor top mobile service robot based on the improved RRT algorithm is proposed. The robot is mainly composed of a lifting truss platform and a manipulator, which avoids the mapping and positioning of complex ground and obstacle avoidance planning. At the same time, the kinematics analysis of the manipulator is carried out. In view of the function of obstacle avoidance planning when the manipulator completes the task, the traditional RRT algorithm is improved to overcome the shortcomings of the low efficiency of path planning in the traditional RRT algorithm, and the planned path quality is uncertain and not smooth enough. The simulation environment is built based on ROS platform to verify the feasibility of the algorithm. To a certain extent, it improves the autonomy of robots to complete tasks.

An Effective Camera-to-Lidar Spatiotemporal Calibration Based on a Simple Calibration Target.

In this contribution, we present a simple and intuitive approach for estimating the exterior (geometrical) calibration of a Lidar instrument with respect to a camera as well as their synchronization shifting (temporal calibration) during data acquisition. For the geometrical calibration, the 3D rigid transformation of the camera system was estimated with respect to the Lidar frame on the basis of the establishment of 2D to 3D point correspondences. The 2D points were automatically extracted on images by exploiting an AprilTag fiducial marker, while the detection of the corresponding Lidar points was carried out by estimating the center of a custom-made retroreflective target. Both AprilTag and Lidar reflective targets were attached to a planar board (calibration object) following an easy-to-implement set-up, which yielded high accuracy in the determination of the center of the calibration target. After the geometrical calibration procedure, the temporal calibration was carried out by matching the position of the AprilTag to the corresponding Lidar target (after being projected onto the image frame), during the recording of a steadily moving calibration target. Our calibration framework was given as an open-source software implemented in the ROS platform. We have applied our method to the calibration of a four-camera mobile mapping system (MMS) with respect to an integrated Velodyne Lidar sensor and evaluated it against a state-of-the-art chessboard-based method. Although our method was a single-camera-to-Lidar calibration approach, the consecutive calibration of all four cameras with respect to the Lidar sensor yielded highly accurate results, which were exploited in a multi-camera texturing scheme of city point clouds.

Lidar-based Robot Detection and Positioning using Machine Learning Methods

This paper presents a machine learning-based kin detection method for multi-robotic and swarm systems. Detecting surrounding objects and distinguishing robots from these objects (kin detection) are essential in most of the multi-robotic applications. While infrared, ultrasonic, vision systems had been mainly used for applying the robot detection and relative positioning task in the literature, studies that use the Lidar-based approach is limited. The proposed method uses the Lidar sensor to discover the work area and determine the distance and the angle of all kin members relative to the observer robot. The main steps of the proposed method can be summarized as follows: 1) the Lidar distance points are read and stored as a vector with some pre-processing, 2) the acquired distance points representing different objects in the environment are separated from each other using a segmentation method, 3) in order to classify the segmented objects, the segment classification process starts with extracting five features for each object, then these features are fed to various machine learning classification algorithms to distinguish the kin robots, 4) the segments classified as a kin robot in the previous step are handled and the relative position is found for each of them. A new mobile robot prototype has been modeled and equipped with a Lidar sensor using ROS platform. Lidar has been used to collect data and four different classification methods have been tested to verify the efficiency of the method using Gazebo simulation platform.

Robot Three-Finger Grasping Strategy Based on DeeplabV3+

Researchers all over the world are aiming to make robots with accurate and stable human-like grasp capabilities, which will expand the application field of robots, and development of a reasonable grasping strategy is the premise of this function. In this paper, the improved deeplabV3+ semantic segmentation algorithm is used to predict a triangle grasp strategy. The improved model was trained on the relabeled Cornell grasp datasets and tested on self-collected datasets. Compared with the existing rectangular grasp strategy, the proposed algorithm and triangle grasp strategy have achieved outstanding performance in stability, accuracy, and speed. Finally, based on the ROS platform, this paper deploys the trained model and verifies the real effect of the trained grasping strategy prediction model, and achieves excellent grasping effect.

Application of Simultaneous Location and Map Construction Algorithms Based on Lidar in the Intelligent Robot Food Runner

With the rapid development of artificial intelligence, there are more and more “shadows” of artificial intelligence in restaurants. In the market, the intelligent robot food runner is relatively expensive and not widely used. In this paper, an intelligent robot food runner with lower price but better performance is proposed, which is suitable for restaurants. Among them, this paper mainly analyzes how to use laser radar SLAM to build restaurant map, locate and navigate, and how to build obstacle avoidance and path planning. Through ROS platform, the whole process of intelligent robot food runner is simulated and verified, which can meet the needs of restaurants.

Object Position Estimation based on Dual Sight Perspective Configuration

Development of the coordination system requires the dataset because the dataset could provide information around the system that the coordination system can use to make decisions. Therefore, the capability to process and display data-related positions of objects around the robots is necessary. This paper provides a method to predict an object’s position. This method is based on the Indoor Positioning System (IPS) idea and object position estimation with the multi-camera system (i.e., stereo vision). This method needs two input data to estimate the ball position: the input image and the robot’s relative position. The approach adopts simple and easy calculation technics: trigonometry, angle rotations, and linear function. This method was tested on a ROS and Gazebo simulation platform. The experimental result shows that this configuration could estimate the object’s position with Mean Squared Error was 0.383 meters. Besides, R squared distance calibration value is 0.9932, which implies that this system worked very well at estimating an object’s position.

Autonomous mobile robot development based on duckietown platform for recognizing and following the traffic sign

This paper presents development of an autonomous mobile robot which can recognize the traffic sign and move according to that recognized sign. The mobile robot was developed based on Duckietown platform, which is a research which focuses on self-driving vehicles. The mobile robot was equipped with a fish eye camera as its vision device and raspberry pi.3 controller module as the main controller for doing image processing in order to recognize the signs and controlling the movement of the robot. The program runs on ROS platform. The system has been tested by moving mobile robot through all area and the results showed average recognition rate of 80%. The system also has been tested in variation of light intensity and the result showed average recognition rate of 80%. Another test also was done by adding disturbance object which has similar or same color as sign color and the result showed average recognition rate of 43.3%.

Robot Operating System (ROS) in Quadcopter Flying Robot Using Telemetry System

In this study implementing odometry using RVIZ on a quadcopter flying robot that uses the Pixhawk Cube firmware version 3.6.8 as the sub-controller. Then the Lenovo G400 laptop as the main-controller as well as the Ground Control Station using the ubuntu 16.04 Linux operating system. The ROS platform uses the Kinetic and MAVROS versions as a quadcopter platform package using MAVlink communication with the telemetry module. The odometry system was tested using Rviz as navigation for Quadcopter movements in carrying out movements that follow movement patterns in certain shapes and perform basic robot movements. Data were collected using a standard measuring instrument inclinometer as a measurement of the slope of the robot and visualization RVIZ as a visual display of the odometric robot. The results of the research obtained are that the flying robot can maneuver according to the shape on the RVIZ according to the movements carried out directly at the airport, as well as the effect of the roll angle on the quadcopter (negative left roll, positive right) and the pitch angle on the quadcopter (negative forward pitch, the pitch returns positive).

English

English

Autonomous Vehicle Control in CARLA Challenge

The introduction of Autonomous Vehicles (AVs) in a realistic urban environment is an ambitious objective. AV validation on real scenarios involving actual objects such as cars or pedestrians in a wide range of traffic cases would escalate the cost and could generate hazardous situations. Consequently, autonomous driving simulators are quickly evolving to cover the gap to achieve a fully autonomous driving architecture validation. Most used 3D simulators in self-driving cars field are V-REP (Rohmer, E., 2013) and Gazebo (Koenig, N. and Howard, A., 2004), due to an easy integration with ROS (Quigley, 2009) platform to increase the interoperability with other systems. Those simulators provide accurate motion information (more appropriate for easier scenes like robotic arms) but not a realistic appearance and not allowing real-time systems, not being able to recreate complex traffic scenes. CARLA (Dosovitskiy, A., 2017) open-source AV simulator is designed to be able to train and validate control and perception algorithms in complex traffic scenarios with hyper-realistic environments. CARLA simulator allows to easily modify on-board sensors such as cameras or LiDAR, weather conditions and also the traffic scene to perform specific traffic cases. In Summer 2019, CARLA launched its driving challenge to allow everyone to test their own control techniques under the same traffic scenarios, scoring its performance regarding traffic rules. In this paper, the Robesafe researching group approach will be explained, detailing vehicle motion control and object detection adapted from Smart Elderly Car (Gómez-Huélamo, C., 2019) that lead the group to reach the 4th place in Track 3 challenge, where HD Map, Waypoints and environmental sensors data (LiDAR, RGB cameras and GPS) were provided.