Robot Navigation Method Research Articles

Survey and Experimental Comparison of RGB-D Indoor Robot Navigation Methods Supported by ROS and Their Expansion via Fusion with Wheel Odometry and IMU Data

Survey and Experimental Comparison of RGB-D Indoor Robot Navigation Methods Supported by ROS and Their Expansion via Fusion with Wheel Odometry and IMU Data

A study of a discrete Bayes and a Kalman filter computational Complexity and performance in the case of 1D robot localization

In the robotic field of study, localization is one of the important methods for autonomous mobile robot navigation. Probabilistic approaches have received significant attention in the robotics community. The discrete Bayes and Kalman filters are the fundamental algorithms in probabilistic approach which have to be clearly understood in order to develop more advanced filtering algorithms. This paper discusses discrete Bayes and Kalman filtering algorithms. The mathematical representation of each filter algorithm, in the 1-dimensional case, presented in detail. The algorithms were implemented using python to simulate the probability of the robot position. The algorithm’s complexity was analysed with respect to the computational cost and size of memory used. From this study, it has been observed that the Kalman filter is computationally more efficient, and less memory is required.

Deep Visual MPC-Policy Learning for Navigation

Humans can routinely follow a trajectory defined by a list of images/landmarks. However, traditional robot navigation methods require accurate mapping of the environment, localization, and planning. Moreover, these methods are sensitive to subtle changes in the environment. In this letter, we propose PoliNet, a deep visual model predictive control-policy learning method that can perform visual navigation while avoiding collisions with unseen objects on the navigation path. PoliNet takes in as input a visual trajectory and 360 $^{\circ }$ images from robot's current view and outputs velocity commands for a planning horizon of $N$ steps that optimally balance between trajectory following and obstacle avoidance. PoliNet is trained using a differentiable neural image predictive model and a traversability estimation model in an model predictive control setup, with minimal human supervision. PoliNet can be applied to visual trajectory in new scenes without retraining. We show experimentally that the robot can follow a visual trajectory even if it does not start from the exact same position and in the presence of previously unseen obstacles. We validated our algorithm with tests both in a realistic simulation environment and in the real world outperforming state-of-the-art baselines under similar conditions in success rate, coverage rate of the trajectory, and with lower computational load. We also show that we can generate visual trajectory in simulation and execute the corresponding path in the real environment.

A Bionic Robot Navigation Algorithm Based on Cognitive Mechanism of Hippocampus

The firing of space cell in hippocampus is considered to be able to form an intrinsic map for the environment which is called cognitive map. Previous bionic navigation algorithms (such as rat simultaneous localization and mapping) and traditional SLAM algorithms lack sufficient physiological basis and cannot reflect the cognitive mechanism of hippocampal formation. Based on the cognitive mechanism of hippocampal space cells, this paper proposes a navigation algorithm for constructing accurate environmental cognitive map. This algorithm is characterized by the construction of a unified spatial cell attractor model for self-motion trajectory path integration. The expressions of grid cells and place cells are driven by stripe cells. The algorithm performs closed-loop detection by collecting depth image, red green blue+depthmap information and corrects the error of spatial cells’ path integral. Eventually, we get a precise cognitive map of the environment and bionic robot navigation is achieved by global navigation and local navigation algorithm based on the map. The cognitive map is a topological metric map that contains the topological relations of the environment feature point coordinates, visual cues, and specific sites. In this paper, the method is verified by the simulation experiment and the physical experiment on the robot platform. The research results laid the foundation for the research of the robot navigation method based on the hippocampus cognitive mechanism. Note to Practitioners —Environmental cognition and navigation ability are the main function of intelligent mobile robots. People and animals have strong adaptability and cognitive ability in unfamiliar environment, and they can independently recognize and navigate in unfamiliar environment. Now, the environmental cognition and navigation ability of intelligent robots are far from the level of human and animal. This paper suggests a bionic robot navigation algorithm based on the cognitive mechanism of rat hippocampus. The bionic robot navigation algorithm makes mobile robots more intelligent by learning and imitating human and animal’s environmental cognition and navigation ability. This navigation algorithm conforms to the physiological characteristics and is pretty accurate and intelligent. The experimental results demonstrate the effectiveness of this algorithm in building environment map and navigation.

A navigation method for mobile robots using interval type-2 fuzzy neural network fitting Q-learning in unknown environments

A navigation method for mobile robots using interval type-2 fuzzy neural network fitting Q-learning in unknown environments

A hand-drawn map-based navigation method for mobile robots using objectness measure

Correct cognition of the environment is the premise of mobile robots to realize autonomous navigation control tasks. The inconsistency caused by time-varying environmental information is a bottleneck for the development and application of cognitive environment technologies. In this article, we propose an environmental cognition method that uses a hand-drawn map. Firstly, we use the single skeleton refinement and fuzzy c-means algorithms to segment the image. Then, we select candidate regions combining the saliency map. At the same time, we use the superpixels straddling method to filter the windows. The final candidate object regions are obtained based on a fusion of saliency segmentation and superpixels clustering. Based on the above objectness estimation results, we use a human–computer interaction method to construct an inaccurate hand-drawn environment map for navigation. The experimental results from PASCAL VOC2007 validate the efficacy of the proposed objectness measure method, where our result of 41.2% on mean average precision is the best of the tested methods. Furthermore, the experimental results of robot navigation in the actual scene also verified the effectiveness of the proposed approach.

A knowledge based fuzzy-probabilistic roadmap method for mobile robot navigation

In this paper a novel knowledge based fuzzy control system with Probabilistic Roadmap (PRM) method is proposed for path planning and target seeking behaviour of mobile robot in presence of obstacles. The proposed method runs in two folds, first fold generates the shortest path between the start position to target position in a priori known cluttered environment, wherein the PRM is used to construct straight-lined path by connecting the intermediate nodes. However, the second fold steps help to convert the sharp corners into the smoothen curves throughout the path. The knowledge based fuzzy control system ensures the smooth turns by adjusting the suitable heading angle, there by correcting the position and orientation of the robots to find local/global targets. The presented methodology has been simulated and tested in various environments. Simulation results justify that, the method is not only capable to find an optimal or near-optimal robot path in complex obstacle present environments while avoiding any dead end situation, but also ensures a good control over robot velocity and smooth turning at the turning junctions. In all the simulation experiments it is found that, the method has shorten the path length by more than 5 percent while smoothening and subsequently navigation time was also reduced appreciably.

Wheelchair robot navigation in different weather conditions using deep learning and evolved neural controller

PurposeWheelchair robot navigation in different weather conditions using single camera is still a challenging task. The purpose of this study is to develop an autonomous wheelchair robot navigation method in different weather conditions, with single camera vision to assist physically disabled people.Design/methodology/approachA road detection method, called dimensionality reduction deep belief neural network (DRDBNN), is proposed for drivable road detection. Due to the dimensionality reduction ability of the DRDBNN, it detects the drivable road area in a short time for controlling the robot in real-time. A feed-forward neural network is used to control the robot for the boundary following navigation using evolved neural controller (ENC). The robot detects road junction area and navigates throughout the road, except in road junction, using calibrated camera and ENC. In road junction, it takes turning decision using Google Maps data, thus reaching the final destination.FindingsThe developed method is tested on a wheelchair robot in real environments. Navigation in real environments indicates that the wheelchair robot moves safely from source to destination by following road boundary. The navigation performance in different weather conditions of the developed method has been demonstrated by the experiments.Originality/valueThe wheelchair robot can navigate in different weather conditions. The detection process is faster than that of the previous DBNN method. The proposed ENC uses only distance information from the detected road area and controls the robot for boundary following navigation. In addition, it uses Google Maps data for taking turning decision and navigation in road junctions.

Experimental Analysis of Acoustic Field Control-Based Robot Navigation

This paper proposes novel robot navigation methods that utilize strong interaction between a designed field and a robot controller. In recent years, several studies have demonstrated the importance of interactions between different subject types (e.g., human-robot interaction, robot-environment interaction) instead of just that between a robot controller and an isolated subject. This study explores therobot-field interactiondesign to realize autonomous robot navigation, and verifies the proposed methods experimentally. We prepare acoustic navigation trails from the start to the goal; one is generated from multiple sounds with identical frequencies, while the other is generated from multiple sounds with different frequencies. For each field controller, both the dynamic acoustic trail and the static acoustic trail, two types ofstaticrobot controllers are designed based only on thepresentsensor data,namely, gradient-following controller and sound-habituation controller. The former is a microphone-array based controller for robots equipped with multiple microphones, while the latter is designed for robots with a single microphone. Throughout the real-world demonstration, we show the validity of our proposed methods.

Reactive Magnetic-Field-Inspired Navigation Method for Robots in Unknown Convex 3-D Environments

With a shift in current robotics application from known, well-defined environments toward unknown environments, the robot's ability to avoid unknown obstacles in real-time while relying on limited information about spatial constraints in its path becomes essential. Taking inspiration from the laws of electromagnetism, we present a novel navigation method, whereby the moving robot induces an artificial electric current onto the obstacle surface generating, in turn, a magnetic field guiding the robot along the obstacle's boundary without affecting its kinetic energy. Our method has several advantages over existing methods, which are as follows. 1) It guides point-like robots toward the goal without suffering from local minima in 3-D environments populated with convex obstacles. 2) It does not need any prior knowledge of obstacle positions and geometries. 3) It only requires environmental sensor information that is spatially and temporally local to generate motion commands iteratively. Our navigation method is tested in simulations and experiments, showing that a point-to-point navigation of point-like robots and the end effector of the Baxter's arm has been successfully achieved in a collision-free manner toward a goal position in a 3-D environment populated with unknown convex obstacles.

A Single RF Emitter-Based Indoor Navigation Method for Autonomous Service Robots.

Location-aware services are one of the key elements of modern intelligent applications. Numerous real-world applications such as factory automation, indoor delivery, and even search and rescue scenarios require autonomous robots to have the ability to navigate in an unknown environment and reach mobile targets with minimal or no prior infrastructure deployment. This research investigates and proposes a novel approach of dynamic target localisation using a single RF emitter, which will be used as the basis of allowing autonomous robots to navigate towards and reach a target. Through the use of multiple directional antennae, Received Signal Strength (RSS) is compared to determine the most probable direction of the targeted emitter, which is combined with the distance estimates to improve the localisation performance. The accuracy of the position estimate is further improved using a particle filter to mitigate the fluctuating nature of real-time RSS data. Based on the direction information, a motion control algorithm is proposed, using Simultaneous Localisation and Mapping (SLAM) and A* path planning to enable navigation through unknown complex environments. A number of navigation scenarios were developed in the context of factory automation applications to demonstrate and evaluate the functionality and performance of the proposed system.

Road area detection method based on DBNN for robot navigation using single camera in outdoor environments

PurposeThe purpose of this study is to develop a cost-effective autonomous wheelchair robot navigation method that assists the aging population.Design/methodology/approachNavigation in outdoor environments is still a challenging task for an autonomous mobile robot because of the highly unstructured and different characteristics of outdoor environments. This study examines a complete vision guided real-time approach for robot navigation in urban roads based on drivable road area detection by using deep learning. During navigation, the camera takes a snapshot of the road, and the captured image is then converted into an illuminant invariant image. Subsequently, a deep belief neural network considers this image as an input. It extracts additional discriminative abstract features by using general purpose learning procedure for detection. During obstacle avoidance, the robot measures the distance from the obstacle position by using estimated parameters of the calibrated camera, and it performs navigation by avoiding obstacles.FindingsThe developed method is implemented on a wheelchair robot, and it is verified by navigating the wheelchair robot on different types of urban curve roads. Navigation in real environments indicates that the wheelchair robot can move safely from one place to another. The navigation performance of the developed method and a comparison with laser range finder (LRF)-based methods were demonstrated through experiments.Originality/valueThis study develops a cost-effective navigation method by using a single camera. Additionally, it utilizes the advantages of deep learning techniques for robust classification of the drivable road area. It performs better in terms of navigation when compared to LRF-based methods in LRF-denied environments.

Visual navigation method for indoor mobile robot based on extended BoW model

This article proposes a new navigation method for mobile robots based on an extended bag of words (BoW) model for general object recognition in indoor environments. The scale-invariant feature transform (SIFT)-detection algorithm with the graphic processing unit (GPU) acceleration technology is used to describe feature vectors in this model. First, in order to add some redundant image information, statistical information of the spatial relationships of all the feature points in an image, i.e. relative distances and angles, is used to extend the feature vectors in the original BoW model. Then, the support vector machine (SVM) classifier is used to classify objects. Also, in order to navigate conveniently in unknown and dynamic indoor environments, a type of human–robot interaction method based on a hand-drawn semantic map is considered. The experimental results show that this new navigation technology for indoor mobile robots is very robust and highly effective.

Autonomous navigation method for substation inspection robot based on travelling deviation

A new method of edge detection is proposed in substation environment, which can realize the autonomous navigation of the substation inspection robot. First of all, the road image and information are obtained by using an image acquisition device. Secondly, the noise in the region of interest which is selected in the road image, is removed with the digital image processing algorithm, the road edge is extracted by Canny operator, and the road boundaries are extracted by Hough transform. Finally, the distance between the robot and the left and the right boundaries is calculated, and the travelling distance is obtained. The robot's walking route is controlled according to the travel deviation and the preset threshold. Experimental results show that the proposed method can detect the road area in real time, and the algorithm has high accuracy and stable performance.

A novel fuzzy three-dimensional grid navigation method for mobile robots

The objective of the autonomous navigation aims to achieve the self-motion control for a robot with the environmental feedbacks and becomes popular recently. Problems of complex modeling, large amo...

An indoor mobile robot navigation technique using odometry and electronic compass

A novel method of indoor mobile robot navigation is presented. The proposed approach fuses the data of odometry and electronic compass for navigation. It includes two calibration methods and a fusion algorithm. First of all, calibration method of systematic odometry error is used to reduce the error of navigation and provide the reliable estimate of pose of mobile robot for adaptive extended Kalman filter fusion algorithm later. Secondly, calibration method of electronic compass using an adaptive neural fuzzy inference system provides direction angle of mobile robot as observation for adaptive extended Kalman filter algorithm later. Finally, a fusion algorithm using adaptive extended Kalman filter algorithm fuses data of odometry and electronic compass that provides the position and orientation of mobile robot. In addition, the value of the parameter k of adaptive extended Kalman filter algorithm which is related to the process noise covariance is decided by fuzzy algorithm. In order to illustrate the feasibility of the proposed approach, two types of experiments are done: the first-type experiment is that the mobile robot runs along default path only with odometry, and the mobile robot with odometry and electronic compass in the second-type experiment utilizes the proposed approach for navigation. The results of experiments show that the error of localization and navigation in the first-type experiment is larger than one in the second-type experiment. They prove the good performance of the proposed approach.

Object Following Design for a Mobile Robot using Neural Network

Deciding the best method for robot navigation is the most important tasks in mobile robot design, defined as the robot's ability to reach the target or/and move around its environment safely using the installed sensors and/or predefined map. To achieve this objective, wall or object detection can be considered. It is common to derive kinematics and dynamics to design the controls system of the robot, however by giving intelligence system to the robot, the control system will provide better performance for robot navigation. One of the most applied artificial intelligence is neural networks, a good approach for sensors of mobile robot system that is difficult to be modeled with an accurate mathematical equations. Mostly discussed basic navigation of a mobile robot is wall following. Wall following robot has been used for many application not only in industrial as a transport robot but also in domestic or hospital. Two behaviors are designed in this paper, wall following and object following. Object following behavior is developed from wall following by utilizing data from 4 installed distance sensors. The leader robot as the target for the follower robot, therefore the follower robot will keep on trying reaching for the leader in a safe distance. The novelty of this research is in the sense of the simplicity of proposed method. The feasibility of our proposed design is proven by simulation where all the results shows the effectiveness of the proposed method.

音場制御に基づくロボットナビゲーション

This paper proposes a new kind of navigation method for mobile robots. Instead of designing a complicated control structure for every robot, we dare to make a potential field, which manipulates the robot movement. We adopt sound in order to create the potential field. On this method, a robot selects an action from proceeding and turning based on the strength of the field. We design a control method of the sound field and a sound hearing robot, and we examine the effectiveness of the proposed method in the real world. After conducting experiments, we found that a mobile robot succeeded in a goal-navigation task by habituating appropriately the robot to the sound.

Review of Vision-Based Robot Navigation Method

Vision-based robot navigation is a research theme that continues to be developed up to now by the researchers in the field of robotics. There are innumerable methods or algorithms are developed, and this paper described the reviews of the methods. The methods are distinguished whether the robot is equipped with the navigation map (map-based), the map is built incrementally as robot observes the environment (map-building), or the robot navigates using no map (mapless). In this paper will described navigation methods of map-based, map-building, and mapless category.

Development of Autonomous Mobile Robot Based on Accurate Map in the Tsukuba Challenge 2014

<div class=""abs_img""> <img src=""[disp_template_path]/JRM/abst-image/00270004/04.jpg"" width=""300"" /> Navigation method for mobile robots</div> We describe a navigation method for autonomous mobile robots and detail knowledge obtained through Tsukuba Challenge 2014 trial runs. The challenge requires robots to navigate autonomously 1.4 km in an urban area and to search for five persons in three areas. Accurate maps are important tools in localization on complex courses in autonomous outdoor navigation. We constructed an occupancy grid map using laser scanners, gyro-assisted odometry and a differential global positioning system (DGPS). In this study, we use maps as a graphical interface. Namely, by using maps, we give environmental information, untravelable low objects such as curb stones, and areas in nonsearches for “target” persons. For the purpose of increasing the map reusability, we developed a waypoint editor, which can modify waypoints on maps to fit a course to a situation. We also developed a velocity control method that the robot uses to follow pedestrians and other robot by keeping safety distance on the course. As a result, our robot took part five of seven official trial runs to get to the goal. This indicates that the autonomous navigation method was stable in the Tsukuba Challenge 2014 urban environment. </span>