Real Mobile Robot Research Articles

An improved fuzzy inference strategy using reinforcement learning for trajectory-tracking of a mobile robot under a varying slip ratio

AbstractIn this study, a fuzzy reinforcement learning control (FRLC) is proposed to achieve trajectory tracking of a differential drive mobile robot (DDMR). The proposed FRLC approach designs fuzzy membership functions to fuzzify the relative position and heading between the current position and a prescribed trajectory. Instead of fuzzy inference rules, the relationship between the fuzzy inputs and actuator voltage outputs is built using a reinforcement learning (RL) agent. Herein, the deep deterministic policy gradient (DDPG) methodology consisted of actor and critic neural networks is employed in the RL agent. Simulations are conducted with considering varying slip ratio disturbances, different initial positions, and two different trajectories in the testing environment. In the meantime, a comparison with the classical DDPG model is presented. The results show that the proposed FRLC is capable of successfully tracking different trajectories under varying slip ratio disturbances as well as having performance superiority to the classical DDPG model. Moreover, experimental results validate that the proposed FRLC is also applicable to real mobile robots.

A Leader-follower formation control of mobile robots by position-based visual servo method using fisheye camera

This paper presents a leader-follower formation control of multiple mobile robots by position-based method using a fisheye camera. A fisheye camera has a wide field of view and recognizes a wide range of objects. In this paper, the fisheye camera is first modeled on spherical coordinates and then a position estimation technique is proposed by using an AR marker based on the spherical model. This paper furthermore presents a method for estimating the velocity of a leader robot based on a disturbance observer using the obtained position information. The proposed techniques are combined with a formation control based on the virtual structure. In this paper, the formation controller and velocity estimator can be designed independently, and the stability analysis of the total system is performed by using Lyapunov theorem. The effectiveness of the proposed method is demonstrated by simulation and experiments using two real mobile robots.

A path planning algorithm fusion of obstacle avoidance and memory functions

AbstractIn this study, to address the issues of sluggish convergence and poor learning efficiency at the initial stages of training, the authors improve and optimise the Deep Deterministic Policy Gradient (DDPG) algorithm. First, inspired by the Artificial Potential Field method, the selection strategy of DDPG has been improved to accelerate the convergence speed during the early stages of training and reduce the time it takes for the mobile robot to reach the target point. Then, optimising the neural network structure of the DDPG algorithm based on the Long Short‐Term Memory accelerates the algorithm's convergence speed in complex dynamic scenes. Static and dynamic scene simulation experiments of mobile robots are carried out in ROS. Test findings demonstrate that the Artificial Potential Field method‐Long Short Term Memory Deep Deterministic Policy Gradient (APF‐LSTM DDPG) algorithm converges significantly faster in complex dynamic scenes. The success rate is improved by 7.3% and 3.6% in contrast to the DDPG and LSTM‐DDPG algorithms. Finally, the usefulness of the method provided in this study is similarly demonstrated in real situations using real mobile robot platforms, laying the foundation for the path planning of mobile robots in complex changing conditions.

A Fast Online Planning Under Partial Observability Using Information Entropy Rewards

Motion planning in an unknown environment is a common challenge because of the existing uncertainties. Representatively, the partially observable Markov decision process (POMDP) is a general mathematical framework for planning in uncertain environments. Recent POMDP solvers generally adopt the sparse reward scheme to solve the planning under uncertainty problem. Subsequently, the robot's exploration may be hindered without immediate rewards, resulting in excessively long planning time. In this article, a POMDP method information entropy determinized sparse partially observation tree (IE-DESPOT) is proposed to explore a high-quality solution and efficient planning in unknown environments. First, a novel sample method integrating state distribution and Gaussian distribution is proposed to optimize the quality of the sampled states. Then, an information entropy based on sampled states is established for real-time reward calculation, resulting in the improvement of robot exploration efficiency. Moreover, the near-optimality and convergence of the proposed algorithm are analyzed. As a result, compared with general-purpose POMDP solvers, the proposed algorithm exhibits fast convergence to a near-optimal policy in many examples of interest. Furthermore, the IE-DESPOT's performance is verified in real mobile robot experiments.

Kinematics Model Estimation of 4W Skid-Steering Mobile Robots Using Visual Terrain Classification

Accurate real-time kinematics model is very important for the control of a skid-steering mobile robot. In this study, the kinematics model of the skid-steering mobile robots was first designed based on instantaneous rotation centers (ICRs). Then, the extended Kalman filter (EKF) technique was applied to obtain the parameters of ICRs under the same specific terrain online. To adapt to different terrain environments, the fractal dimension-based SFTA (segmentation-based fractal texture analysis) method was used to extract features of different terrains, and the k-nearest neighbor (KNN) method was used to classify the terrains. In the case of real-time terrain recognition, the filter parameters of the EKF for estimating the ICRs are adjusted adaptively. Experiments on a real skid-steering mobile robot show that this method can quickly estimate the kinematics model of the robot in the case of terrain changes, and can meet the needs of practical applications. The average error of odometer estimation based on visual terrain classification is 0.06 m, while the average error of odometer estimation without terrain classification is 0.14 m.

Real-Time Multi-Agent Mobile Robot based on A Client-Server Model

A client-server network is one of the most important topics in a computer network. In this work, a real-time computer control system is designed based on the Client-Server Model for a Multi-Agent Mobile Robot System (CSM-MAMRS) and is applied to a building that consists of (N) floors and uses one mobile robot on each floor that has specific actions in different types of environments. The new proposed CSM-MAMRS consists of four layers. The first stage manages the network communication for each agent. The second stage solves the major problems of path planning by using a proposed hybrid algorithm that combines the Rapidly Exploring Random Tree Star (RRT*) and the Particle Swarm Optimization (PSO) algorithms in order to provide the shortest and smoothest path with collision avoidance between the starting and the target points in a static and dynamic robot environments are used.. In the third stage, a velocity planner controller is based on an inverse kinematic mobile robot model. In the fourth stage, the Hypertext Transfer Protocol HTTP is used to send velocity values to real mobile robots via the Wireless Network Control Administration. The simulation results and experimental works successfully achieved to significant improvement in real-time when using three missions of three mobile robots on different static map floors in the building. The maximum tracking pose errors for three robots in the static enviormnets are 0.39 cm, 0.02 cm, 0.32 cm respectively, but the maximum tracking pose error in the dynamic environments are 2.94 cm and 2.8 cm only for two mobile robots along the maximum distance of 250 cm. Index Terms— Real-time computer control, Mobile robot, Multi-agent system, Path planning algorithms.

A Hybrid Motion Planning Algorithm for Multi-Mobile Robot Formation Planning

This paper addresses the problem of relative position-based formation planning for a leader–follower multi-robot setup, where the robots adjust the formation parameters, such as size and three-dimensional orientation, to avoid collisions and progress toward their goal. Specifically, we develop a virtual sub-target-based obstacle avoidance method, which involves a transitional virtual sub-target that guides the robots to avoid obstacles according to obstacle information, target, and boundary. Moreover, we develop a changing formation strategy to determine the necessity to avoid collisions and a priority-based model to determine which robots move, thus dynamically adjusting the relative distance between the followers and the leader. The backstepping-based sliding motion controller guarantees that the trajectory and velocity tracking errors converge to zero. The proposed robot navigation method can be employed in various environments and types of obstacles, allowing for a formation change. Furthermore, it is efficient and scalable under various numbers of robots. The approach is experimentally verified using three real mobile robots and up to five mobile robots in simulated scenarios.

IRDC-Net: Lightweight Semantic Segmentation Network Based on Monocular Camera for Mobile Robot Navigation.

Computer vision plays a significant role in mobile robot navigation due to the wealth of information extracted from digital images. Mobile robots localize and move to the intended destination based on the captured images. Due to the complexity of the environment, obstacle avoidance still requires a complex sensor system with a high computational efficiency requirement. This study offers a real-time solution to the problem of extracting corridor scenes from a single image using a lightweight semantic segmentation model integrating with the quantization technique to reduce the numerous training parameters and computational costs. The proposed model consists of an FCN as the decoder and MobilenetV2 as the decoder (with multi-scale fusion). This combination allows us to significantly minimize computation time while achieving high precision. Moreover, in this study, we also propose to use the Balance Cross-Entropy loss function to handle diverse datasets, especially those with class imbalances and to integrate a number of techniques, for example, the Adam optimizer and Gaussian filters, to enhance segmentation performance. The results demonstrate that our model can outperform baselines across different datasets. Moreover, when being applied to practical experiments with a real mobile robot, the proposed model's performance is still consistent, supporting the optimal path planning, allowing the mobile robot to efficiently and effectively avoid the obstacles.

SLAMICP Library: Accelerating Obstacle Detection in Mobile Robot Navigation via Outlier Monitoring following ICP Localization.

The Iterative Closest Point (ICP) is a matching technique used to determine the transformation matrix that best minimizes the distance between two point clouds. Although mostly used for 2D and 3D surface reconstruction, this technique is also widely used for mobile robot self-localization by means of matching partial information provided by an onboard LIDAR scanner with a known map of the facility. Once the estimated position of the robot is obtained, the scans gathered by the LIDAR can be analyzed to locate possible obstacles obstructing the planned trajectory of the mobile robot. This work proposes to speed up the obstacle detection process by directly monitoring outliers (discrepant points between the LIDAR scans and the full map) spotted after ICP matching instead of spending time performing an isolated task to re-analyze the LIDAR scans to detect those discrepancies. In this work, a computationally optimized ICP implementation has been adapted to return the list of outliers along with other matching metrics, computed in an optimal way by taking advantage of the parameters already calculated in order to perform the ICP matching. The evaluation of this adapted ICP implementation in a real mobile robot application has shown that the time required to perform self-localization and obstacle detection has been reduced by 36.7% when obstacle detection is performed simultaneously with the ICP matching instead of implementing a redundant procedure for obstacle detection. The adapted ICP implementation is provided in the SLAMICP library.

A Comparative Study of Various Intelligent Algorithms Based Nonlinear PID Neural Trajectory Tracking Controller for the Differential Wheeled Mobile Robot Model

This paper presents a comparative study of two learning algorithms for the nonlinear PID neural trajectory tracking controller for mobile robot in order to follow a pre-defined path. As simple and fast tuning technique, genetic and particle swarm optimization algorithms are used to tune the nonlinear PID neural controller's parameters to find the best velocities control actions of the right wheel and left wheel for the real mobile robot. Polywog wavelet activation function is used in the structure of the nonlinear PID neural controller. Simulation results (Matlab) and experimental work (LabVIEW) show that the proposed nonlinear PID controller with PSOlearning algorithm is more effective and robust than genetic learning algorithm; this is demonstrated by the minimized tracking error and obtained smoothness of the velocity control signal, especially when external disturbances are applied.

Path Following and Avoiding Obstacle for Mobile Robot Under Dynamic Environments Using Reinforcement Learning

Obstacle avoidance for mobile robot to reach the desired target from a start location is one of the most interesting research topics. However, until now, few works discuss about working of mobile robot in the dynamic and continuously changing environment. So, this issue is still the research challenge for mobile robots. Traditional algorithm for obstacle avoidance in the dynamic, complex environment had many drawbacks. As known that Q-learning, the type of reinforcement learning, has been successfully applied in computer games. However, it is still rarely used in real world applications. This research presents an effectively method for real time dynamic obstacle avoidance based on Q-learning in the real world by using three-wheeled mobile robot. The position of obstacles including many static and dynamic obstacles and the mobile robot are recognized by fixed camera installed above the working space. The input for the robot is the 2D data from the camera. The output is an action for the robot (velocities, linear and angular parameters). Firstly, the simulation is performed for Q-learning algorithm then based on trained data, The Q-table value is implemented to the real mobile robot to perform the task in the real scene. The results are compared with intelligent control method for both static and dynamic obstacles cases. Through implement experiments, the results show that, after training in dynamic environments and testing in a new environment, the mobile robot is able to reach the target position successfully and have better performance comparing with fuzzy controller.

Real-Time SLAM Mobile Robot and Navigation Based on Cloud-Based Implementation

This study investigates the feasibility of a mobile robot navigating and discovering its location in unknown environments, followed by the creation of maps of these navigated environments for future use. First, a real mobile robot named TurtleBot3 Burger was used to achieve the simultaneous localization and mapping (SLAM) technique for a complex environment with 12 obstacles of different sizes based on the Rviz library, which is built on the robot operating system (ROS) booted in Linux. It is possible to control the robot and perform this process remotely by using an Amazon Elastic Compute Cloud (Amazon EC2) instance service. Then, the map to the Amazon Simple Storage Service (Amazon S3) cloud was uploaded. This provides a database to display maps and use them at any time for navigation without the need to redraw the map. This map can be accessed by using an authentication process (username and password) supervised by the cloud server administrator. After that, using the serverless image handler (SIH), with the aid of this solution, you can change the size of images, change the color of the background, format them, or add watermarks. Experiment results demonstrated the ability to build a map of an unknown location in a complex environment and use it for navigation tasks on a real mobile robot via remote control. It also showed the success of the process of storing the map for future use and the process of modifying the map using SIH.

English

This paper presents the research and construction of a motion tracing control system for omnidirectional mobile robots based on reinforcement learning techniques in automatic control. The process of controlling a mobile robot in a flat environment with definite and unknown obstacles, taking into account the nonlinear factor of interference. Research and application of programming tools are operating systems for mobile robots (Robot Operating System - ROS). From updated information on maps, operating environment, robot control position, and obstacle identification (SLAM) to calculate the movement trajectory of a three-wheeled omnidirectional mobile robot. The positioning system calculates the orbital tracking for the robot based on the Q-learning algorithm. The results of simulation research in the Gazebo environment and running tests on real Turtlebot mobile robots have shown the practical effectiveness of the research problem of tracking motion tracking and intelligent navigation for mobile robots.

Specification, stochastic modeling and analysis of interactive service robotic applications

Assistive robotic systems are quickly becoming a core technology for the service sector as they are understood capable of supporting people in need of assistance in a wide variety of tasks. This step poses a number of ethical and technological questions. The research community is wondering how service robotics can be a step forward in human care and aid, and how robotics applications can be realized in order to put the human role at the forefront. Therefore, there is a growing demand for frameworks supporting robotic application designers in a “human-aware” development process. This paper presents a model-driven framework for analyzing and developing human–robot interactive scenarios in non-industrial settings with significant sources of uncertainty. The framework’s core is a formal model of the agents at play – the humans and the robot – and the robot’s mission, which is then put through verification to estimate the probability of completing the mission. The model captures non-trivial features related to human behavior, specifically the unpredictability of human choices and physiological aspects tied to their state of health. To foster the framework’s accessibility, we present a verification tool-agnostic Domain-Specific Language that allows designers lacking expertise in formal modeling to configure the interactive scenarios in a user-friendly manner. We compare the formal analysis outputs with results obtained by deploying benchmark scenarios in the physical environment with a real mobile robot to assess whether the formal model adheres to reality and whether the verification results are accurate. The entire development pipeline is then tested on several scenarios from the healthcare setting to assess its flexibility and effectiveness in the application design process.

Robot Vitals and Robot Health: Towards Systematically Quantifying Runtime Performance Degradation in Robots Under Adverse Conditions

This letter addresses the problem of automatically detecting and quantifying performance degradation in remote mobile robots, in real-time, during task execution. A robot may encounter a variety of uncertainties and adversities during task execution, which can impair its ability to carry out tasks effectively and cause its performance to degrade. Such situations can be mitigated or averted by timely detection and intervention, e.g., by a remote human supervisor taking over control in teleoperation mode. Inspired by patient triaging systems in hospitals, we introduce the framework of “robot vitals” for estimating overall “robot health”. A robot's vitals are a set of lower-level metrics that estimate a variety of indicators of performance degradation faced by a robot at any given point in time. Robot health is a higher-level metric that combines robot vitals into a single scalar value estimate of performance degradation. Experiments, both in simulation and on a real mobile robot, demonstrate that the proposed robot vitals and robot health can be used effectively for online estimation of robot performance degradation during run-time.

Improved Nonlinear Finite-Memory Estimation Approach for Mobile Robot Localization

In this article, we present a new mobile robot localization algorithm. The Kalman filter (KF) and particle filter (PF), which are widely used in localization problems, may show poor performance or the divergence phenomenon due to the existence of disturbances or missing measurements. This article proposes an improved nonlinear finite-memory estimation (INFME) algorithm to overcome the performance degradation problem caused by linearization errors in existing finite-memory (FM) estimation methods. To ensure robustness against noise and disturbances, the INFME algorithm was designed with an FM structure based on the minimization of an objective function, which induces reduction of adverse effects of disturbances including the linearization error. It showed superior accurate, robust, real-time performance in real mobile robot localization experiments. The accuracy and robustness of the new algorithm were verified using harsh experimental scenarios including a kidnapped robot problem and a situation in which multiple missing measurements occurred.

Forced motion control of a mobile robot

Objectives. The increase of the efficiency of a separate transport mobile robot in a warehouse due to optimal regulation of the speed of its movement. It is required to control the position, speed, acceleration and direction of movement of the mobile robot at each moment of time along a known route. A method for forced control of the movement of a transport mobile robot was proposed. A control block for various motion maneuvers was developed in Simulink environment, which calculates the distance to the nearest turning point or stop and then by constructed cyclogram the corresponding speed at each moment of time is determined. The proposed control unit can be used in practice for the tasks of optimal movement of transport robots in predetermined area.Methods. The method of the theory of optimal control according to the criterion of maximum speed, the wave algorithm for finding the shortest path, the method of finite automata for relay control of the acceleration of movement are used.Results. Based on the proposed method of forced control of the movement of a transport mobile robot in the Simulink environment, a maneuver control system was developed that provides the minimum travel time for each segment of the path. Maneuvers mean the rectilinear movement of the robot, as well as its turn on the spot, in two modes: with and without reaching maximum speed. The technique is based on the assumption that the movement of the transport robot is uniformly accelerated. A side result of the developed control system is that when it is scaled to a group of robots, it becomes possible to predict the time and place of their potential collisions, in order to subsequently take into account a group of robots for effective control.Conclusion. The developed control system can be used to control a real transport mobile robot equipped with a servo drive in solving the problems of transporting goods around the warehouse.

How to pick a mobile robot simulator: A quantitative comparison of CoppeliaSim, Gazebo, MORSE and Webots with a focus on accuracy of motion

The number of available tools for dynamic simulation of robots has been growing rapidly in recent years. However, to the best of our knowledge, there are very few reported quantitative comparisons of the most widely-used robot simulation tools. This article attempts to partly fill this gap by providing quantitative and objective comparisons of four widely-used simulation packages for mobile robots. The comparisons reported here were conducted by obtaining data from a real Husky A200 mobile robot driving on mixed terrains as ground truth and by simulating a 3D mobile robot model in a developed identical simulation world of these terrains for each simulator. We then compared the simulation outputs with real, measured results by weighted metrics. Based on our experiments and selected metrics, we conclude that CoppeliaSim is currently the best performing simulator, although Gazebo is not far behind and is a good alternative.

Learning Pneumatic Non-Prehensile Manipulation With a Mobile Blower

We investigate pneumatic non-prehensile manipulation (i.e., blowing) as a means of efficiently moving scattered objects into a target receptacle. Due to the chaotic nature of aerodynamic forces, a blowing controller must (i) continually adapt to unexpected changes from its actions, (ii) maintain fine-grained control, since the slightest misstep can result in large unintended consequences (e.g., scatter objects already in a pile), and (iii) infer long-range plans (e.g., move the robot to strategic blowing locations). We tackle these challenges in the context of deep reinforcement learning, introducing a multi-frequency version of the spatial action maps framework. This allows for efficient learning of vision-based policies that effectively combine high-level planning and low-level closed-loop control for dynamic mobile manipulation. Experiments show that our system learns efficient behaviors for the task, demonstrating in particular that blowing achieves better downstream performance than pushing, and that our policies improve performance over baselines. Moreover, we show that our system naturally encourages emergent specialization between the different subpolicies spanning low-level fine-grained control and high-level planning. On a real mobile robot equipped with a miniature air blower, we show that our simulation-trained policies transfer well to a real environment and can generalize to novel objects.

The Navigation of Mobile Robot in the Indoor Dynamic Unknown Environment Based on Decision Tree Algorithm.

This study proposes an optimized algorithm for the navigation of the mobile robot in the indoor and dynamic unknown environment based on the decision tree algorithm. Firstly, the error of the yaw value outputted from IMU sensor fusion module is analyzed in the indoor environment; then, the adaptive FAST SLAM is proposed to optimize the yaw value from the odometer; in the next, a decision tree algorithm is applied which predicts the correct moving direction of the mobile robot through the outputted yaw value from the IMU sensor fusion module and adaptive FAST SLAM of the odometer data in the indoor and dynamic environment; the following is the navigation algorithm proposed for the mobile robot in the dynamic and unknown environment; finally, a real mobile robot is designed to verify the proposed algorithm.The final result shows the proposed algorithms are valid and effective.