Autonomous Mobile Robot Navigation Research Articles

Hybrid Global Positioning System-Adaptive Neuro-Fuzzy Inference System based autonomous mobile robot navigation

The collision-free navigation of a mobile robot in clutter environments is challenging. Global Positioning System (GPS) and adaptive neuro-fuzzy inference system (ANFIS) are well-known techniques widely used for navigation and control, respectively. This paper proposes a hybrid GPS-ANFIS based method for collision-free navigation of autonomous mobile robots. The GPS-based controller keeps the navigation direction of the robot toward the static or dynamic target. It uses the coordinates received from the two GPS modules on the edges of the longitudinal axis of the robot all together with the coordinates of the target to divert it from the current path making a certain angle towards the target. The performance of the proposed method in navigating a mobile robot in clutter environments and its effectiveness in comparison with the other collision-free navigation methods has been evaluated through simulations. The evaluation criteria are on the basis of the obstacle avoidance behavior and the length of the discovered collision-free path by the robot. The results have shown that our hybrid GPS-ANFIS method navigates the robot toward the goal via a shorter path while avoiding the obstacles.

Development of an Autonomous Robotics Platform for Road Marks Painting Using Laser Simulator and Sensor Fusion Technique

SUMMARYThe design and experimental works of an autonomous robotic platform for road marks painting are presented in this paper as the first autonomous system of its kind. The whole system involves two main sub-systems, namely: an autonomous mobile robot navigation system which is used for recognizing the roads and estimating the position of road marks, and automatic road marks painting system that is attached to the mobile robot platform to control the spray of the paint on the road’s surface. The experimental results show the capability of the proposed system to perform the task of autonomous road marks painting with accuracy of ±10 cm.

Autonomous omnidirectional mobile robot navigation based on hierarchical fuzzy systems

PurposeThis paper aims to propose a one-layer Mamdani hierarchical fuzzy system (HFS) to navigate autonomously an omnidirectional mobile robot to a target with a desired angle in unstructured environment. To avoid collision with unknown obstacles, Mamdani limpid hierarchical fuzzy systems (LHFS) are developed based on infrared sensors information and providing the appropriate linear speed controls.Design/methodology/approachThe one-layer Mamdani HFS scheme consists of three fuzzy logic units corresponding to each degree of freedom of the holonomic mobile robot. This structure makes it possible to navigate with an optimized number of rules. Mamdani LHFS for obstacle avoidance consists of a number of fuzzy logic units of low dimension connected in a hierarchical structure. Hence, Mamdani LHFS has the advantage of optimizing the number of fuzzy rules compared to a standard fuzzy controller. Based on sensors information inputs of the Mamdani LHFS, appropriate linear speed controls are generated to avoid collision with static obstacles.FindingsSimulation results are performed with MATLAB software in interaction with the environment test tool “Robotino Sim.” Experiments have been done on an omnidirectional mobile robot “Robotino.” Simulation results show that the proposed approaches lead to satisfied performances in navigation between static obstacles to reach the target with a desired angle and have the advantage that the total number of fuzzy rules is greatly reduced. Experimental results prove the efficiency and the validity of the proposed approaches for the navigation problem and obstacle avoidance collisions.Originality/valueBy comparing simulation results of the proposed Mamdani HFS to another navigational controller, it was found that it provides better results in terms of path length in the same environment. Moreover, it has the advantage that the number of fuzzy rules is greatly reduced compared to a standard Mamdani fuzzy controller. The use of Mamdani LHFS in obstacle avoidance greatly reduces the number of involved fuzzy rules and overcomes the complexity of high dimensionality of the infrared sensors data information.

USING AN LOW-COST STEREO CAMERA FOR AUTONOMOUS NAVIGATION OF MOBILE ROBOT

Abstract. The paper considers the possibility of using low-cost stereo cameras for autonomous robot navigation. An low-cost stereo camera with a focal length of 5 mm and a photo base of 6 cm was chosen for the research. Experimental studies have shown that the accuracy of determining the coordinates of object points from a pair of images obtained by such a stereo camera is sufficient for organizing autonomous navigation of the robot. In order to improve the reliability and accuracy of determining the trajectory of the robot, this paper proposes to use two stereo cameras. One is directed forward by the robot's movement, and the other is directed at the nadir. Thus, the trajectory is determined twice, independently of each other. Moreover, each case has its own algorithm for finding the homologue points. In the first case, a sparse point cloud is constructed for each stereo pair based on the selection of interesting points and their identification based on the comparison of descriptors. In addition, blunder detection of points identification are realized based on the analysis of the values of the relative orientation equations using the fundamental matrix. In the second case, when the stereo camera is pointed at the nadir, the usual method of correlation is used in the nodes of the grid specified at one image. Experimental studies have shown sufficient efficiency of autonomous navigation of mobile robot based on the use of two stereo cameras.

Autonomous system to control a mobile robot

This paper presents an ongoing effort to control a mobile robot in unstructured environment. Obstacle avoidance is an important task in the field of robotics, since the goal of autonomous robot is to reach the destination without collision. Several algorithms have been proposed for obstacle avoidance, having drawbacks and benefits. In this paper, the fuzzy controller is used to tackle the problem of mobile robot autonomous navigation in unstructured environment. The objective is to make the robot move along a collision free trajectory until it reaches its target. The proposed approach uses the fuzzified, adaptive inference engine and defuzzification engine. Also number of linguistic labels is optimized for the input of the mobile robot in order to reduce computational time for real-time applications. The proposed fuzzy controller is evaluated subjectively and objectively with other approaches and also the processing time is taken in consideration.

Navigation of a mobile robot in a dynamic environment using a point cloud map

In this paper, we consider autonomous navigation of a wheeled mobile robot in a dynamic environment using a 3D point cloud map. We consider four kinds of 2D maps: static global map, dynamic global map, global cost map, and local cost map; to plan a feasible path of the robot to adapt to a dynamic environment. We consider a mobile robot for plant patrolling in a 3D environment with plane slopes but not rough terrain for which a 2D environment map suffices. We propose 2D static global map for robot navigation by projecting prior measured 3D point cloud map data on a horizontal plane with considering the climbing ability of the robot. We also build a 2D dynamic global map by projecting a real-time 3D point cloud on the 2D static global map by SLAM. Accumulated errors of SLAM can be canceled using some landmarks placed in the environment. A global planner calculates an optimal global path that minimizes the distance from an initial robot pose (position and orientation) to a goal pose (position and orientation) by A* algorithm based on the global cost map which is built from the dynamic global map. However, this process should take much time. To avoid moving obstacles, the TEB (Timed Elastic Band) local planner is used to calculate an optimal local path based on a local cost map which is given by a real-time local 3D point cloud. To demonstrate the effectiveness of the proposed system, experiments were carried out. In the experiment, we use an AR card as a landmark for simplification of implementation. We prove that the robot can navigate in a dynamic environment and accumulated errors can be canceled by the AR cards placed in the environment as landmarks.

Towards simultaneous localization and mapping tolerant to sensors and software faults: Application to omnidirectional mobile robot

In the last few years, simultaneous localization and mapping became an important topic of research in the robotics community. This article proposes an approach for autonomous navigation of mobile robots in faulty situations. The main objective is to extend the fault tolerance strategy to simultaneous localization and mapping in presence of sensor faults or software faults in the data fusion process. Fault detection and isolation technique is performed based on duplication–comparison method and structured residuals. The proposed fault tolerance approach is based on the extended Kalman filter for simultaneous localization and mapping when an absolute localization sensor is available. The validation of the proposed approach and the extended Kalman filter for simultaneous localization and mapping algorithm is performed from experiments employing an omnidrive mobile robot, equipped with embedded sensors, namely: wheel encoders, gyroscope, two laser rangefinders and external sensor for the absolute position (indoor global positioning system). The obtained results demonstrate the effectiveness of the proposed approach where it was found that its fault tolerance performance is based essentially on the selected residuals and the values of the fault detection thresholds to be used for the fault detection and isolation.

Automatic Storage and Retrieval System using the Optimal Path Algorithm

The demand for application of mobile robots in performing boring and extensive tasks are increasing rapidly due to unavailability of human workforce. Navigation by humans within the warehouse is one among such repetitive and exhaustive task. Autonomous navigation of mobile robots for picking and dropping the shelves within the warehouse will save time and money for the warehousing business. Proposing an optimization model for automated storage and retrieval systems by the goals of its planning is investigated to minimize travel time in multi-robot systems. This paper deals with designing a system for storing and retrieving a group of materials within an environment arranged in rows and columns. Its intersections represent storage locations. The title of any subject is indicated by the row number and the column in it. A method was proposed to store and retrieve a set of requests (materials) using a number of robots as well as one receiving and delivery port. Several simulation results are tested to show this improvement in length of path and time of arrival.

A smart mobile robot commands predictor using recursive neural network

Autonomous navigation of mobile robot via classic neural network (NN) models are no more valid in terms of efficiency and accuracy due to the development of new advanced techniques. However, the necessity of finding an implementable Recursive Neural Network (RNN) model to predict the motor control of the robot with both speed and accuracy constraints still remains stagnant because of the nonlinearity and complexity of the trajectories.To provide new solutions for smart navigation problems, this paper proposes a new implementable recursive neural network controller (RNNC) predictor that calculates the Pulse Width Modulation (PMW) signals of the motors. Such proposed Multi-input Multi-output (MIMO) Controller succeeded to solve the problem of speed and accuracy of autonomous navigation.The Smart RNNC model design is illustrated with its architecture in details. Due to the complexity and the non-efficiency of the training process in real-world, a 3D Simulator was developed to create all possible scenarios. The machine learning and navigation predictions processes for designing the new RNNC model are presented together in details. In addition, the motor commands generation speed and accuracy as well as their efficiency are theoretically and practically proven. Moreover, numerical studies, 3D scenarios of trajectory tracking and obstacle avoidance prove the effectiveness and robustness of the proposed technique.

Autonomous smart robot for path predicting and finding in maze based on fuzzy and neuro‐Fuzzy approaches

AbstractThe navigation of autonomous mobile robots has in recent times gained interest from many researchers in different areas such as the industrial, agricultural, and military sectors. This paper aims at carefully investigating two advanced types of approaches for guiding a non‐holonomic mobile robot to navigate in an environment area cluttered with static obstacles. Firstly, a Fuzzy logic controller (FLC) was designed, using trapezoidal shape Membership functions (MF's). Secondly, an Adaptive neuro fuzzy inference system (ANFIS) controller was used to optimize the results obtained from trapezoidal fuzzy controller. To validate the feasibility and effectiveness of the proposed models, V‐REP and MATLAB software are used. A comparative evaluation is, then, done on the basis of speed. The simulations results showed that the mobile robot could navigate successfully into maze environment with both proposed approaches but ANFIS controller provided better results in comparison to fuzzy controller.

A survey of image semantics-based visual simultaneous localization and mapping: Application-oriented solutions to autonomous navigation of mobile robots

As one of the typical application-oriented solutions to robot autonomous navigation, visual simultaneous localization and mapping is essentially restricted to simplex environmental understanding based on geometric features of images. By contrast, the semantic simultaneous localization and mapping that is characterized by high-level environmental perception has apparently opened the door to apply image semantics to efficiently estimate poses, detect loop closures, build 3D maps, and so on. This article presents a detailed review of recent advances in semantic simultaneous localization and mapping, which mainly covers the treatments in terms of perception, robustness, and accuracy. Specifically, the concept of “semantic extractor” and the framework of “modern visual simultaneous localization and mapping” are initially presented. As the challenges associated with perception, robustness, and accuracy are being stated, we further discuss some open problems from a macroscopic view and attempt to find answers. We argue that multiscaled map representation, object simultaneous localization and mapping system, and deep neural network-based simultaneous localization and mapping pipeline design could be effective solutions to image semantics-fused visual simultaneous localization and mapping.

Autonomous navigation and obstacle avoidance of an omnidirectional mobile robot using swarm optimization and sensors deployment

The present work deals with the design of intelligent path planning algorithms for a mobile robot in static and dynamic environments based on swarm intelligence optimization. Two modifications are suggested to improve the searching process of the standard bat algorithm with the result of two novel algorithms. The first algorithm is a Modified Frequency Bat algorithm, and the second is a hybridization between the Particle Swarm Optimization with the Modified Frequency Bat algorithm, namely, the Hybrid Particle Swarm Optimization-Modified Frequency Bat algorithm. Both Modified Frequency Bat and Hybrid Particle Swarm Optimization-Modified Frequency Bat algorithms have been integrated with a proposed technique for obstacle detection and avoidance and are applied to different static and dynamic environments using free-space modeling. Moreover, a new procedure is proposed to convert the infeasible solutions suggested via path the proposed swarm-inspired optimization-based path planning algorithm into feasible ones. The simulations are run in MATLAB environment to test the validation of the suggested algorithms. They have shown that the proposed path planning algorithms result in superior performance by finding the shortest and smoothest collision-free path under various static and dynamic scenarios.

A Novel FastSLAM Framework Based on 2D Lidar for Autonomous Mobile Robot

The autonomous navigation and environment exploration of mobile robots are carried out on the premise of the ability of environment sensing. Simultaneous localisation and mapping (SLAM) is the key algorithm in perceiving and mapping an environment in real time. FastSLAM has played an increasingly significant role in the SLAM problem. In order to enhance the performance of FastSLAM, a novel framework called IFastSLAM is proposed, based on particle swarm optimisation (PSO). In this framework, an adaptive resampling strategy is proposed that uses the genetic algorithm to increase the diversity of particles, and the principles of fractional differential theory and chaotic optimisation are combined into the algorithm to improve the conventional PSO approach. We observe that the fractional differential approach speeds up the iteration of the algorithm and chaotic optimisation prevents premature convergence. A new idea of a virtual particle is put forward as the global optimisation target for the improved PSO scheme. This approach is more accurate in terms of determining the optimisation target based on the geometric position of the particle, compared to an approach based on the maximum weight value of the particle. The proposed IFastSLAM method is compared with conventional FastSLAM, PSO-FastSLAM, and an adaptive generic FastSLAM algorithm (AGA-FastSLAM). The superiority of IFastSLAM is verified by simulations, experiments with a real-world dataset, and field experiments.

Congratulations! Journal of Robotics and Mechatronics Best Paper Award 2019

We are pleased to announce that the 12th Journal of Robotics and Mechatronics Best Paper Award (JRM Best Paper Award 2019) has been decided by the JRM editorial committee. The following paper won the JRM Best Paper Award 2019, severely selected from among all 94 papers published in Vol.30 (2018). The Best Paper Award ceremony was held in Gakushi-Kaikan, Tokyo, Japan, on January 7, 2020, attended by the author and JRM editorial committee members who took part in the selection process. The award winner will also be announced on the JRM website and was given a certificate and a nearly US$1,000 honorarium. JRM Best Paper Award 2019 Title: End-to-End Autonomous Mobile Robot Navigation with Model-Based System Support Authors: Alexander Carballo, Shunya Seiya, Jacob Lambert, Hatem Darweesh, Patiphon Narksri, Luis Yoichi Morales, Naoki Akai, Eijiro Takeuchi, and Kazuya Takeda J. Robot. Mechatron., Vol.30 No.4, pp. 563-583, August 2018

Mobile Robot Navigation in Cluttered Environment Using Spider Monkey Optimization Algorithm

Swarm intelligence is one of the most emerging methods used for autonomous mobile robot navigation. Researchers have developed many algorithms in mobile robot navigation by simulating the swarming behavior of various creatures like ants, firefly, honey bees, and cuckoo, and the findings are very motivating. The paper presents application and implementation of spider monkey optimization (SMO) along with Three Path method (TPM) for mobile robot navigation in cluttered environment. A collision-free path is selected by using TPM. When all the three paths are blocked by obstacles, SMO is used for obstacles avoidance. The finding of global and local leaders from the groups is the key concept of the proposed method. The proposed method efficiently improves the global search in less number of iterations, and hence, it can be easily implemented for real-time obstacle avoidance. The computational path and time are less as compared to other navigational methods. Some simulation results are presented at the end of the paper to show the effectiveness of the proposed navigational method.

Mobile robot controller using novel hybrid system

Hybrid neuro-fuzzy controller is one of the techniques that is used as a tool to control a mobile robot in unstructured environment. In this paper a novel neuro-fuzzy technique is proposed in order to tackle the problem of mobile robot autonomous navigation in unstructured environment. Obstacle avoidance is an important task in the field of robotics, since the goal of autonomous robot is to reach the destination without collision. The objective is to make the robot move along a collision free trajectory until it reaches its target. The proposed approach uses the artificial neural network instead of the fuzzified engine then the output from it is processed using adaptive inference engine and defuzzification engine. In this approach, the real processing time is reduce that is increase the mobile robot response. The proposed neuro-fuzzy controller is evaluated subjectively and objectively with other approaches and also the processing time is taken in consideration.

Managing Localization Uncertainty to Handle Semantic Lane Information from Geo-Referenced Maps in Evidential Occupancy Grids

Occupancy grid is a popular environment model that is widely applied for autonomous navigation of mobile robots. This model encodes obstacle information into the grid cells as a reference of the space state. However, when navigating on roads, the planning module of an autonomous vehicle needs to have semantic understanding of the scene, especially concerning the accessibility of the driving space. This paper presents a grid-based evidential approach for modeling semantic road space by taking advantage of a prior map that contains lane-level information. Road rules are encoded in the grid for semantic understanding. Our approach focuses on dealing with the localization uncertainty, which is a key issue, while parsing information from the prior map. Readings from an exteroceptive sensor are as well integrated in the grid to provide real-time obstacle information. All the information is managed in an evidential framework based on Dempster–Shafer theory. Real road results are reported with qualitative evaluation and quantitative analysis of the constructed grids to show the performance and the behavior of the method for real-time application.

Autonomous navigation of mobile robot using shallow and deep neural network

Neural network provides an efficient solution for the manoeuvrability problems of autonomous mobile robots. Freire et al. (2009) studied the autonomous navigation of SCITOS-G5 (mobile robot) by training four types of neural networks to perform a classification task. The multi-layer perceptron (MLP) network gave the best performance in comparison to others (mixture of experts, Elman and logistic perceptron). In this paper, a different model of MLP network has been trained using the same training set whose performance is found to be better than that obtained by Freire, in terms of faster computations and a higher success rate. Also, since deep learning started gaining popularity in terms of its association with the neural network therefore, a recurrent neural network model is developed whose performance is compared to a simple MLP network. The results show that it gives superior performance, in comparison to the developed MLP network, using fewer training samples.

Autonomous navigation of mobile robot using shallow and deep neural network

Autonomous navigation of mobile robot using shallow and deep neural network

HPPRM: Hybrid Potential Based Probabilistic Roadmap Algorithm for Improved Dynamic Path Planning of Mobile Robots

Path planning and navigation is a very important problem in robotics, especially for mobile robots operating in complex environments. Sampling based planners such as the probabilistic roadmaps (PRM) have been widely used for different robot applications. However, due to the random sampling of nodes in PRM, it suffers from narrow passage problem that generates unconnected graph. The problem is addressed by increasing the number of nodes but at higher computation cost affecting real-time performance. To address this issue, in this paper, we propose an improved sampling-based path planning method for mobile robot navigation. The proposed method uses a layered hybrid Probabilistic Roadmap (PRM) and the Artificial Potential Field (APF) method for global planning. We used a decomposition method for node distribution that uses map segmentation to produce regions of high and low potential, and propose a method of reducing the dispersion of sample set during the roadmap construction. Our method produces better goal planning queries with a smaller graph and is computationally efficient than the traditional PRM. The proposed planner called the Hybrid Potential based Probabilistic Roadmap (HPPRM) is an improved sampling method with respect to success rate and calculation cost. Furthermore, we present a method for reactive local motion planning in the presence of static and dynamic obstacles in the environment. The advantage of the proposed method is that it can avoid local minima and successfully generate plans in complex maps such as narrow passages and bug trap scenarios that are otherwise difficult for the traditional sample-based methods. We show the validity of our method with experiments in simulation and real environments for both local and global planning. The results indicate that the proposed HPPRM is effective for autonomous mobile robot navigation in complex environments. The success rate of the proposed method is higher than 95% both for local and global planning.