Localization Of Autonomous Mobile Robot Research Articles

Towards Optimal Dynamic Localization for Autonomous Mobile Robot via Integrating Sensors Fusion

Towards Optimal Dynamic Localization for Autonomous Mobile Robot via Integrating Sensors Fusion

Neural architecture search for the estimation of relative positioning of the autonomous mobile robot

Abstract In the present work, an artificial neural network (ANN) will be developed to estimate the relative rotation and translation of the autonomous mobile robot (AMR). The ANN will work as an iterative closed point, which is commonly used with the singular value decomposition algorithm. This development will provide better resolution for a relative positioning technique that is essential for the AMR localization. The ANN requires a specific architecture, although in the current work a neural architecture search will be adapted to select the best ANN for estimating the relative motion. At the end, these ANNs will be compared with conventional algorithms to check the good performance of adopting an intelligent method for relative positioning estimation.

Localization for Autonomous Mobile Robot in Geographical Map

Localization for Autonomous Mobile Robot in Geographical Map

Monocular Vision Aided Depth Map from RGB Images to Estimate of Localization and Support to Navigation of Mobile Robots

Localization is one of the most challenging requirements needed for a mobile robots. Successful localization represents success in meeting the other principal requirements, such as perception and navigation. This article proposes a new approach for the localization of autonomous mobile robots using a Kinect sensor and the concept of Transfer Learning linked to Convolutional Neural Networks (CNNs). The images acquired from the sensor are applied in a mosaic form, which consists of the three color channels provided along with the depth information of the environment. Topological maps were used for indoor environment localization. The proposed computer vision system employed the Bayesian Classifier, k-Nearest Neighbor, Random Forest, Multi-layer Perceptron, and Support Vector Machine as the classifiers. The main focus of this work is the use of a unique configuration of RGB-D images transformed into a mosaic image, combined with the descriptive power of CNNs, in order to estimate the location of a mobile robot in an indoor environments. The results show that the proposed approach proved to be a convincing method for the tasks of localization and supporting the navigation of mobile robots; the results achieved 100% in Accuracy and in the F1-Score. The values obtained for the processing times were also suitable for a computer vision system, with 31.885ms, 0.040s, and 0.044s for the extraction, training, and classification stages, respectively. All these results were from the RGB-D mosaic images. The data demonstrated the relevance of the proposed work, providing a successful localization and, consequently, a successful navigation for mobile robots.

3D LiDAR-based Localization of Autonomous Mobile Robot based on 3D Point Cloud Generated by Structure from Motion using Aerial photos

3D LiDAR-based Localization of Autonomous Mobile Robot based on 3D Point Cloud Generated by Structure from Motion using Aerial photos

Localization of Autonomous Mobile Robot by Integration of Multiple Sensor Information based on Sensor Information Reliability Map

Localization of Autonomous Mobile Robot by Integration of Multiple Sensor Information based on Sensor Information Reliability Map

GIS-based Localization for Autonomous Mobile Robots

GIS-based Localization for Autonomous Mobile Robots

Landmark Finding Algorithms for Indoor Autonomous Mobile Robot Localization

This contribution is oriented to ways of computer vision algorithms for mobile robot localization in internal and external agricultural environment. The main aim of this work was to design, create, verify and evaluate speed and functionality of computer vision localization algorithm. An input colour camera data and depth data were captured by MS® Kinect sensor that was mounted on 6-wheel-drive mobile robot chassis. The design of the localization algorithm was focused to the most significant blobs and points (landmarks) on the colour picture. Actual coordinates of autonomous mobile robot were calculated out from measured distances (depth sensor) and calculated angles (RGB camera) with respect to landmark points. Time measurement script was used to compare the speed of landmark finding algorithm for localization in case of one and more landmarks on picture. The main source code was written in MS Visual studio C# programming language with Microsoft.Kinect.1.7.dll on Windows based PC. Algorithms described in this article were created for a future development of an autonomous agronomical mobile robot localization and control.

Landmark Finding Algorithms for Indoor Autonomous Mobile Robot Localization

This contribution is oriented to ways of computer vision algorithms for mobile robot localization in internal and external agricultural environment. The main aim of this work was to design, create, verify and evaluate speed and functionality of computer vision localization algorithm. An input colour camera data and depth data were captured by MS® Kinect sensor that was mounted on 6-wheel-drive mobile robot chassis. The design of the localization algorithm was focused to the most significant blobs and points (landmarks) on the colour picture. Actual coordinates of autonomous mobile robot were calculated out from measured distances (depth sensor) and calculated angles (RGB camera) with respect to landmark points. Time measurement script was used to compare the speed of landmark finding algorithm for localization in case of one and more landmarks on picture. The main source code was written in MS Visual studio C# programming language with Microsoft.Kinect.1.7.dll on Windows based PC. Algorithms described in this article were created for a future development of an autonomous agronomical mobile robot localization and control.

Autonomous Mobile Robot Localization and Navigation Using a Hierarchical Map Representation Primarily Guided by Vision

While impressive progress has recently been made with autonomous vehicles, both indoors and on streets, autonomous localization and navigation in less constrained and more dynamic environments, such as outdoor pedestrian and bicycle-friendly sites, remains a challenging problem. We describe a new approach that utilizes several visual perception modules-place recognition, landmark recognition, and road lane detection-supplemented by proximity cues from a planar laser range finder for obstacle avoidance. At the core of our system is a new hybrid topological/grid-occupancy map that integrates the outputs from all perceptual modules, despite different latencies and time scales. Our approach allows for real-time performance through a combination of fast but shallow processing modules that update the map's state while slower but more discriminating modules are still computing. We validated our system using a ground vehicle that autonomously traversed three outdoor routes several times, each 400 m or longer, on a university campus. The routes featured different road types, environmental hazards, moving pedestrians, and service vehicles. In total, the robot logged over 10 km of successful recorded experiments, driving within a median of 1.37 m laterally of the center of the road, and localizing within 0.97 m median longitudinally of its true location along the route.

Autonomous mobile robot localization based on RSSI measurements using an RFID sensor and neural network BPANN

Radio Frequency Identification (RFID) technology is broadly deployed for improving trade and transactions. An RFID tag can identify the region (position) where it resides; thus, a popular trend among researchers is to deploy RFID technology for mobile robot localization. Because the intensities of signals at adjacent regions are similar to each other, it is a challenge to employ an RFID system as a sensor. In this proposed system, tags are scattered throughout a mobile robot’s environment in a constrained random pattern and are treated as landmarks. An RFID receiver is mounted on a mobile robot that can navigate such an environment. The robot senses all landmarks in the vicinity to acquire the IDs and received signal strength indicator (RSSI) measurements of the scattered tags. The robot can locate itself depending on the classification result provided by a feed-forward back-propagation artificial neural network (BPANN) supplied with a set of all RSSI measurements read by this robot at a specific location. To be acceptable, this set should only have one high RSSI measurement. The robot senses the location information from a high-valued RSSI tag and adds it to a list of tag IDs along with the corresponding location information. The robot can use this information to travel between any two identified locations. The experimental results demonstrate the efficiency of this proposed system.

Localization algorithm using a virtual label for a mobile robot in indoor and outdoor environments

Localization for autonomous mobile robot is one of the most important factors. If current position of robot is unknown, it should be impossible to solve a problem such as how to decide and where to go. There are various localization methods developed by previous researches; localization using RFID tag, ultrasonic and image processing and recognizing landmark. However, these methods have problems and faults. In indoor, RFID, vision and ultrasonic sensors are only detected a restricted space and easily effected by height, interval and direction of installed sensors. In outdoor, it is difficult to detect current position because of disconnected signal and error of GPS which has used in the most of research. This paper proposes new localization algorithm which is assigned virtual label along with map building through information acquired by using a 2D laser range finder, an encoder and a GPS in indoor/outdoor environments. The proposed algorithm for virtual label is verified by applying a mobile robot both indoor and outdoor.

Localization of an Autonomous Mobile Robot Based on Ultrasonic Sensory Information

Based on ultrasonic sensory information, an approach is proposed for localization of autonomous mobile robot (AMRs). In the proposed method, it will be proven that the combination of three ultrasonic transmitters and two receivers can determine both the position and the orientation of an AMR with respect to a reference frame uniquely. In this manner, since only ultrasonic sensors are used, the proposed method will be highly cost-effective and easy to implement. To show the validity and feasibility of the proposed method, the hardware configuration and a series of experiments will be given for illustration.

Dead Reckoning Navigation for Autonomous Mobile Robots

A dead reckoning navigation system for autonomous mobile robot localization is presented. The navigation system was implemented by novel sensor fusion using a Kalman filter. A differential encoder and the gyroscope error models are developed for the filter. An indirect Kalman filter scheme is adopted to reduce the computational burden and to enhance the navigation system reliability. The filter, which feeds back the estimated errors to the main navigation system, mutually compensates the encoder errors and the gyroscope errors. To evaluate the filter performance, the observability of the filter was analyzed. The characteristics of unbounded position error growth in dead reckoning navigation system' has been shown by the observability analysis. The experimental results show that the proposed mobile robot navigation algorithm provides the reliable position and heading angle of the mobile robot without any help of external positioning system.

Modeling of ultrasonic range sensors for localization of autonomous mobile robots

This paper presents a probabilistic model of ultrasonic range sensors using backpropagation neural networks trained on experimental data. The sensor model provides the probability of detecting mapped obstacles in the environment, given their position and orientation relative to the transducer. The detection probability can be used to compute the location of an autonomous vehicle from those obstacles that are more likely to be detected. The neural network model is more accurate than other existing approaches, since it captures the typical multilobal detection pattern of ultrasonic transducers. Since the network size is kept small, implementation of the model on a mobile robot can be efficient for real-time navigation. An example that demonstrates how the credence could be incorporated into the extended Kalman filter (EKF) and the numerical values of the final neural network weights are provided in the appendices.