Practical indoor mobile robot navigation using hybrid maps

Navigation of autonomous vehicles and robots can be divided into two categories: indoor navigation and outdoor navigation. In general the outdoor navigation is more difficult and complex task because often the environment does not have characteristic points that can be identified and with respect to which robots could relate their position. If environment is unstructured (e.g. off-road environment), problems related to autonomous navigation are very difficult. Problems related to navigation in the unstructured environment could be divided into mapping, localization, collision avoidance and trajectory tracking.

2013 Latin American Robotics Symposium and Competition, 2013

One of the main goals of a household robot is to navigate in an environment in a safe way. Some prior work has addressed this assumption by using dead reckoning in combination with reactive behaviours to interact with unknown dynamic environment. This paper presents a mobile robot navigation system that uses a topological landmark based representation of the environment from which it is possible to find paths using the Dijkstra algorithm. In this way the robot is able to achieve its goal while avoiding obstacles using a reactive navigation approach based on the coordination of state machines.

Cognitive Systems Research, 2003

This article reviews map-learning and path-planning strategies within the context of map-based navigation in mobile robots. Concerning map-learning, it distinguishes metric maps from topological maps and describes procedures that help maintain the coherency of these maps. Concerning path-planning, it distinguishes continuous from discretized spaces and describes procedures applicable when the execution of a plan fails. It insists on the need for an integrated conception of such procedures, which must be tightly tailored to the specific robot that is used, notably to the capacities and limitations of its sensory-motor equipment, and to the specific environment that is experienced. A hierarchy of navigation strategies is outlined in the discussion, together with the sort of adaptive capacities each affords to cope with unexpected obstacles or dangers encountered on an animat or robot's way to its goal. 

2006

This thesis addresses the enabling of technologies needed by a navigating robot. The interest in lowcost 3D imaging sensors like the Kinect has increased rapidly during the last two years. It has been used by many workers with accurate success in many recent projects, replacing the professional and expensive laserscanners. In this project, its capabilities are tested on a medium-sized indoor mobile robot as the main input sensor. Data acquisition, information extraction, 2D obstacle mapping and obstacle avoidance are implemented in this application while trying to cope with real life situations. Furthermore, an external localization module is interfaced with the Kinect in order to obtain global-coordination. All the steps are led towards a good localization and a precise autonomous navigation, with respect to indoor-robot typical tasks. i Preface This report is submitted as partial fulfillment of the requirements for graduation in the above education at the Technical University of Denmark. The work was performed in the period February 2012-January 2013 at the Department of Automation and Control, DTU. The supervisors are Jens Christian Andersen, Nils Axel Andersen and Ole Ravn; all three are from the Department of Automation and Control, DTU This dissertation analyzes the capabilities of a low-cost 3D imaging sensor for a middle-sized robot in an indoor environment with respect to autonomous navigation tasks. The work is organized in six main chapters. The first chapter motivates the study, reviews previous work, states the limitations imposed and is concluded with the purpose of the current application. The second chapter analyses the main hardware and software components with respect to the goal of the project. The third chapter addresses Kinect sensor calibration, 3D spacial data acquisition and data filtering. It continues by the extraction of information as: walls, floors and obstacles. The forth chapter presents mapping solution for obstacle avoidance. The fifth chapter contains a proposed solution for interfacing an external localizer module. The results are presented and discussed. The sixth (and final) chapter contains the conclusions of the dissertation and suggests topics for further improvement. iii I would like to express my sincere thanks to my supervisors Jens Christian Andersen, Nils Axel Andersen and Ole Ravn for the patience that was offered in the beginning and for the cooperation and freedom-of-thought under which this project was done. I would also kindly like to thank Elbert Hendricks for showing me how a chain of thoughts can be expressed in writing clearly and precisely. Additionally I would like to acknowledge other members of the robotics group for all of the informal talks that served as a good inspiration and a constant food for thought. A warm embrace is avowed to Lisbeth Winter for her help in the robotics group. Friendly gratitude is directed to Adriana Sidea, Gabriel Zsurzsan and Marius Ioan Muntianu for sharing many days, nights and weekends at school in a hyggelige collegial ambiance. A special thanks again is said once more to Laura Standardi for her lovely proofreading assistance and, moral support during the writing of this thesis. And finally, this project would never have been possible without the support and encouragements of my beloved parents: Iliana Ferent and Vasile Ferent.

International Journal of Advanced Robotic Systems, 2016

The aim of the work presented in this article is to develop a navigation system that allows a mobile robot to move autonomously in an indoor environment using perceptions of multiple events. A topological navigation system based on events that imitates human navigation using sensorimotor abilities and sensorial events is presented. The increasing interest in building autonomous mobile systems makes the detection and recognition of perceptions a crucial task. The system proposed can be considered a perceptive navigation system as the navigation process is based on perception and recognition of natural and artificial landmarks, among others. The innovation of this work resides in the use of an integration interface to handle multiple events concurrently, leading to a more complete and advanced navigation system. The developed architecture enhances the integration of new elements due to its modularity and the decoupling between modules. Finally, experiments have been carried out in several mobile robots, and their results show the feasibility of the navigation system proposed and the effectiveness of the sensorial data integration managed as events.

Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292), 2002

In the present paper a system for generation of topological maps is going to be presented. This system is considered as one of the deliberative skills of the mobile robots architecture named AD. AD is a two level architecture: deliberative and automatic. Those skills which require high computational time as consequence of high level reasoning are found in the deliberative level, while the automatic level skills interacts with robot sensors and actuators.

International Journal of Automation and Control, 2009

Present research and development in the area of mobile robots mainly aims at study of various techniques, methods and sensors being used for navigation of mobile robots. Different techniques have been discussed for the navigation of mobile robots in the first part. These techniques can be subdivided as (1) fuzzy logic technique, (2) neural network technique and (3) genetic algorithm technique. In the second part, five methods are being discussed for navigation of mobile robots. These methods are (1) potential field method, (2) grid-type method, (3) heuristic method, (4) adaptive navigation method and (v) Virtual Impedance method. The last segment focuses on different sensors being used for navigation of mobile robots. The sensors discussed are (1) ultrasonic sensor, (2) laser sensor, (3) magnetic compass disk sensor, (4) infrared sensor and (5) vision (camera) sensor. Keeping the above strategies in forefront, a comprehensive discussion has been made and is described methodologically in the current paper.

IFAC Proceedings Volumes, 1997

To derive cost efficient solutions, navigation of mobile robots should take advantage of known facts of the environment, like maps of buildings. This paper discusses the use of range sensor measurements at characteristic locations to periodically correct the drift in odometry data, in order to derive the vehicle's position and orientation with sufficient accuracy. The main objective is to provide a low cost navigation system without the need for external reference marks. This paper outlines the approach, the sensor data processing algorithm and results of performance tests in industrial environments.

2007

A new approach on robot navigation is described which enables the robot to drive through the environment using only a vision system as its sensor. In an exploration phase the robot is driven manually through the environment while taking images. By computing similarities between these images the robot constructs a topological map in the form of an appearance graph. Navigation on this graph involves homing from one node to the other until the goal node is reached. No explicit metrical information is modelled by this approach. Rather the distances in the topological map provide directly information about the ability and the robustness of visual navigation in the environment. Real world experiments were conducted under varying environmental conditions.