This research work involves the implementation of a person follower robot in ROS_Gazebo platform As part of this research work, we designed a mobile robot (for simulation)that can follow human ...beings. It assists people carrying heavyweights to their desired locations by following them. The entire simulation work is carried out with the help of ROS2 (Robot Operating System Version2). We used Gazebo and RVIZ as simulation tools to verify the outputs. MakeHuman and Blender software's assisted in creating an animated person and verify the rendering in the gazebo. The mobile robot created makes use of a Depth camera (Kinect) to detect a person and Lidars to calculate the distance between the robot and person. YOLOv3 algorithm has been used for image recognition. With this mobile robot, we simulated with multiple persons in gazebo software to make sure the robot is following only one particular person. The Kinect sensor uses object detection algorithms to identify and follow a particular person.
Path planning for long-term tasks is currently an important research area for robotic applications in uncertain environments, such as farms. Here, a robot automatically follows an optimal path ...generated by the robot planner, and the robot planner must consider the uncertainties in the environment to adapt and improve its motion plan during run-time. In some cases, the robot must change its motion direction multiple times in a long-term task. Therefore, the robot has to decide which place to visit next to adapt to unexpected events, such as avoiding obstacles not recognized by the robot or some robot features and environmental conditions. The robot will need to either plan a short path and then back to the global path or, if better for its overall performance, create a new global path to the target and automatically follow the new path. This study proposes a path planning method to generate the unmanned ground vehicle path to visit all predefined locations on a farm. The proposed method is an extended version of our previously developed method, called the Boundary Node Method and Path Enhancement Method. Then, this method is combined with the online path optimization scheme for re-planning and scheduling the new path at run-time to improve the robot's path and adapt to unexpected events. Different simulation environments are examined to demonstrate the performance of the proposed method. The results show that the robot can re-plan an optimal path toward the goal points to avoid unexpected threats and uncertain obstacles.
In recent years, the Robot Operating System (ROS) is developing rapidly and has been widely used in robotics research because of its flexible, open source, and easy-to-expand advantages. In ...scientific research, the corresponding hardware platform is indispensable for the experiment. In the field of mobile robots, PR2, Turtlebot2, and Fetch are commonly used as research platforms. Although these platforms are fully functional and widely used, they are expensive and bulky. What's more, these robots are not easily redesigned and expanded according to requirements. To overcome these limitations, we propose Plantbot, an easy-building, low-cost robot platform that can be redesigned and expanded according to requirements. It can be applied to not only fast algorithm verification, but also simple factory inspection and ROS teaching. This article describes this robot platform from several aspects such as hardware design, kinematics, and control methods. At last two experiments, SLAM and Navigation, on the robot platform are performed. The source code of this platform is available: https://github.com/marooncn/plantbot.
Artificial intelligence (AI) has been an issue in robotics, since AI is based on iterative algorithms. In general, simulations of physical models are used to show the outcome of learning algorithms ...or show proof of concepts. Since models are generated based on parameter estimations of training data, it is crucial to iterate a significant amount of times in order to model an accurate classification function. Thus, it would take a substantial amount of time for a robot to generate such a function. In this research, an implementation of reinforced learning will be applied on a unmanned ground vehicle (UGV) learning simulated model that will be translated into a physical UGV using Robot Operating System (ROS) to test performance of the given model.
In this paper, it is reported on the current status of our efforts since last year, including the outline of the platform for synchronous collection of data output from four cameras for capturing the ...surrounding environment of the vehicle and the driving behavior of the driver, and one IMU sensor installed in the vehicle, as well as the results of data collection and analysis assuming a pedestrian running out as a verification experiment on campus. Based on the needs of medical professionals who have extensive experience in making medical decisions regarding the driving of senior, the objective of the development was to simplify measurement and analysis through sensor fusion. The developed platform uses four Raspberry Pis and a communication system called ROS (Robot Operating System) 2 to link them together. In addition, the platform includes a user interface system to enhance the convenience of operation using the M5Stack Core2. The experimental results show that our platform is inexpensive, highly customizable and synchronized.
Remote Assistance for Autonomous Vehicles Selvaraj, Gopinath; Pillai, Jishnu Jaikumar
2022 IEEE 19th India Council International Conference (INDICON),
2022-Nov.-24
Conference Proceeding
Present day Autonomous Vehicle (AV) has intelligence built in to perceive its surroundings, make decisions about driving maneuvers, and navigate in a safe manner. Typically, decision-making engines ...of AVs are built to decide only limited number of driving scenarios. Still AV's decision-making capabilities are still below in comparison with human intelligence. AVs may encounter novel conditions, such as lane changes in congested traffic, intersection handling, and uncertainty created by human-driven vehicles and pedestrians. AVs may require human intervention in the form of remote assistance (tele-assistance/ teleguiding) in order to make suitable driving decisions to handle such circumstances. In this study, an attempt has been made to demonstrate the remote assistance feature for AVs using Gazebo simulation environment. In this demonstrator setup, a Turtlebot3 burger model is considered as an AV equipped with a camera, lidar, GPS & IMU sensors for perception sensing. ROS framework-based communication was established between the AV and the control center to mimic the tele-guidance infrastructure. Numerical experimentations are presented for various driving scenarios with and without obstacles to show the importance of remote assistance demonstrator for AVs.
ROS Based Simulation Environment for Testing Power Line Inspection Robots Megalingam, Rajesh Kannan; Kota, Avinash Hegde; Vijaya Krishna Tejaswi, P ...
2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT),
2021-Dec.-10
Conference Proceeding
In recent years, the network of High Power voltage lines has grown so large that transmission lines can now be seen in very sparsely populated areas as well. Electricity has become an inevitable ...component of human day-to-day life. The power lines act as pipelines in supplying such a valuable resource. Disruption in the power supply can have a huge impact on people's lives at times. To ensure an uninterrupted power supply, transmission lines have to be checked and repaired at regular intervals. Several aspects make this tedious. The cost involved in inspection manually, risk of life are dominant among other factors.. Also during manual inspection we have to interrupt the power supply, which causes huge loss. So using robots for transmission line inspection is the best option. There are several transmission line inspection robots but, to test such robots in real-time there is a requirement of lot of cost and time. This research work proposes a virtual environment that can replicate real-time testing physically and also cut down cost and risk factors a great extent. There are several types of robot or autonomous systems that are being used to check transmission lines. This research provides a one-stop solution to test all such robots with minimal or no additional cost.
ROS-SF Wang, Yu-Ping; Dong, Yuejiang; Tan, Gang
Proceedings of the 23rd ACM/IFIP International Middleware Conference,
11/2022
Conference Proceeding
Open access
In recent years, ROS becomes the dominant middleware for robotic systems. The performance of its message-passing paradigm is crucial to the robot's reaction time. However, previous works only focus ...on efficiency, but ignore the requirement for transparency. We present ROS-SF framework, which can transparently eliminate serialization and de-serialization under the ROS APIs. The key contributions are a new serialization format called SFM and a life-cycle management method for serialization-free messages. Evaluation results show that our ROS-SF framework can improve the message-passing performance of ROS by up to 76.3\%. Application case study and applicability study show that our ROS-SF framework can be transparently applied to many existing ROS-based systems and packages. Even in the failure cases, our ROS-SF framework can provide modification guidance.
PDF
