During recent years, walking humanoid robots have gained popularity from wheeled vehicle robots in various assistive roles in human’s environment. Self-localization is a necessary requirement for the humanoid robots ...During recent years, walking humanoid robots have gained popularity from wheeled vehicle robots in various assistive roles in human’s environment. Self-localization is a necessary requirement for the humanoid robots used in most of the assistive tasks. This is because the robots have to be able to locate themselves in their environment in order to accomplish their tasks. In addition, autonomous navigation of walking robots to the pre-defined destination is equally important mission, and therefore it is required that the robot knows its initiate location precisely. The indoor navigation is based on the map of the environment used by the robot. Assuming that the walking robot is capable of locating itself based on its initiate location and the distance walked from it, there are still factors that impair the map-based navigation. One of them is the robot’s limited ability to keep its direction when it is walking, which means that the robot is not able to walk directly from one point to another due to a stochastic error in walking direction. In this paper we present an algorithm for straightening the walking path using distance measurements by built-in sonar sensors of a NAO humanoid robot. The proposed algorithm enables the robot to walk directly from one point to another, which enables precise map-based indoor navigation.展开更多
Indoor navigation has received much attention by both industry and academia in recent years. To locate users, a number of existing methods use various localization algorithms in combination with an indoor map, which r...Indoor navigation has received much attention by both industry and academia in recent years. To locate users, a number of existing methods use various localization algorithms in combination with an indoor map, which require expensive infrastructures deployed in advance. In this study, we propose the use of existing indoor objects with attached RFID tags and a reader to navigate users to their destinations, without the need for any additional hardware. The key insight upon which our proposal is based is that a person＇s movement has an impact on the frequency shift values collected from indoor objects when they near a tag. We leverage this local human-item spatial relation to infer the user＇s position and then navigate the user to the desired destination step by step. We implement a prototype navigation system, called Roll Caller, and conduct a comprehensive range of experiments to examine its performance.展开更多
In view of the poor information integrity of the 3D model used to make the indoor road network and the lack of versatility of the constructed indoor road network, a method for building an indoor navigation network mod...In view of the poor information integrity of the 3D model used to make the indoor road network and the lack of versatility of the constructed indoor road network, a method for building an indoor navigation network model that can be seamlessly connected with outdoor paths is proposed in this paper. First, the IFC model is converted to the CityGML model using the BIM model as the indoor data source. Then, using GIS technology and limited Delaunay triangulation refinement algorithm, the necessary elements of indoor navigate on network model such as semantic information, geometric information and topological relationship contained in CityGML model are extracted. Finally, it is visualized and verified based on experimental model data. The results show that the indoor navigation network model constructed based on the CityGML model can accurately perform indoor navigation, make the constructed road network more general, and provide reference and technical support for the integrated construction of indoor and outdoor road network models.展开更多
The design and implementation of indoor security robot can well integrate the two fields of indoor navigation and object detection, in order to achieve a more powerful robot system, the development of this project has...The design and implementation of indoor security robot can well integrate the two fields of indoor navigation and object detection, in order to achieve a more powerful robot system, the development of this project has certain theoretical research significance and practical application value. The project development is completed in ROS (Robot Operating System). The main tools or frameworks used include AMCL (Adaptive Monte Carlo Localization) package, SLAM (Simultaneous Localization and Mapping) algorithm, Darknet deep learning framework, YOLOv3 (You Only Look Once)algorithm, etc. The main development methods include odometer information fusion, coordinate transformation, localization and mapping, path planning, YOLOv3 model training, function package configuration and deployment. Indoor security robot has two main functions: first, it can complete real-time localization, mapping and navigation of indoor environment through sensors such as lidar and camera;Second, object detection is accomplished through USB camera. Through the detailed analysis and research of the functional design of the two modules, the expected function is finally realized, which can meet the daily use needs.展开更多
The impact of location services on people’s lives has grown significantly in the era of widespread smart device usage.Due to global navigation satellite system(GNSS)signal rejection,weak signal strength in indoor env...The impact of location services on people’s lives has grown significantly in the era of widespread smart device usage.Due to global navigation satellite system(GNSS)signal rejection,weak signal strength in indoor environments and radio signal interference caused by multiwall environments,which collectively lead to significant positioning errors,vision-based positioning has emerged as a crucial method in indoor positioning research.This paper introduces a scale hierarchical matching model to tackle challenges associated with large visual databases and high scene similarity,both of which will compromise matching accuracy and lead to prolonged positioning delays.The proposed model establishes an image feature database using GIST features and speeded up robust feature(SURF)in the offline stage.In the online stage,a positioning navigating algorithm is constructed based on Dijkstra’s path planning.Additionally,a corresponding Android application has been developed to facilitate visual positioning and navigation in indoor environments.Experimental results obtained in real indoor environments demonstrate that the proposed method significantly enhances positioning accuracy compared with similar algorithms,while effectively reducing time overhead.This improvement caters to the requirements for indoor positioning and navigation,thereby meeting user needs.展开更多
Car routing solutions are omnipresent and solutions for pedestrians also exist.Furthermore,public or commercial buildings are getting bigger and the complexity of their internal structure has increased.Consequently,th...Car routing solutions are omnipresent and solutions for pedestrians also exist.Furthermore,public or commercial buildings are getting bigger and the complexity of their internal structure has increased.Consequently,the need for indoor routing solutions has emerged.Some prototypes are available,but they still lack semantically-enriched modelling (e.g.,access constraints,labels,etc.) and are not suitable for providing user-adaptive length-optimal routing in complex buildings.Previous approaches consider simple rooms,concave rooms,and corridors,but important characteristics such as distinct areas in huge rooms and solid obstacles inside rooms are not considered at all,although such details can increase navigation accuracy.By formally defining a weighted indoor routing graph,it is possible to create a detailed and user-adaptive model for route computation.The defined graph also contains semantic information such as room labels,door accessibility constraints,etc.Furthermore,one-way paths inside buildings are considered,as well as three-dimensional building parts,e.g.,elevators or stairways.A hierarchical structure is also possible with the presented graph model.展开更多
A combined algorithm for the loosely fused ultra wide band(UWB)and inertial navigation system(INS)-based measurements is designed under the indoor human navigation conditions with missing data.The scheme proposed fuse...A combined algorithm for the loosely fused ultra wide band(UWB)and inertial navigation system(INS)-based measurements is designed under the indoor human navigation conditions with missing data.The scheme proposed fuses the INS-and UWB-derived positions via a data fusion filter.Since the UWB signal is prone to drift in indoor environments and its outage highly affects the integrated scheme reliability,we also consider the missing data problem in UWB measurements.To overcome this problem,the loosely-coupled INS/UWB-integrated scheme is augmented with a prediction option based on the predictive unbiased finite impulse response(UFIR)fusion filter.We show experimentally that,the standard UFIR fusion filter has higher robustness than the Kalman filter.It is also shown that the predictive UFIR fusion filter is able to produce an acceptable navigation accuracy under temporary missing UWB-data.展开更多
It is discussed with the design and implementation of an architecture for a mobile robot to navigate in dynamic and anknown indoor environments. The architecture is based on the framework of Open Robot Control Softwar...It is discussed with the design and implementation of an architecture for a mobile robot to navigate in dynamic and anknown indoor environments. The architecture is based on the framework of Open Robot Control Software at KTH （OROCOS@KTH）, which is also discussed and evaluated to navigate indoor efficiently, a new algorithm named door-like-exit detection is proposed which employs 2D feature oft. door and extracts key points of pathway from the raw data of a laser scanner. As a hybrid architecture, it is decomposed into several basic components which can be classified as either deliberative or reactive. Each component can concurrently execute and communicate with another. It is expansible and transferable and its components are reusable.展开更多
Dear Editor,This letter addresses the challenges of sparse and delayed rewards in complex indoor navigation tasks. To this end,we propose a task decomposition-based reinforcement learning framework that integrates a r...Dear Editor,This letter addresses the challenges of sparse and delayed rewards in complex indoor navigation tasks. To this end,we propose a task decomposition-based reinforcement learning framework that integrates a reinforcement learning(RL) algorithm with a path planner.展开更多
3D navigation within a 3D-GIS environment is increasingly getting more popular and spreading to various fields.In thelast decade,especially after the 9/11 disaster,evacuating the complex and tall buildings of today in...3D navigation within a 3D-GIS environment is increasingly getting more popular and spreading to various fields.In thelast decade,especially after the 9/11 disaster,evacuating the complex and tall buildings of today in case of emergencyhas been an important research area for scientists.Most of the current navigation systems are still in the 2D environmentand that is insufficient to visualize 3D objects and to obtain satisfactory solutions for the 3D environment.Therefore,there is currently still a lack of implementation of 3D network analysis and navigation for indoor spaces in respect toevacuation.The objective of this paper is to investigate and implement 3D visualization and navigation techniques andsolutions for indoor spaces within 3D-GIS.For realizing this,we have proposed a GIS implementation that is capable ofcarrying out 3D visualization of a building model stored in the CityGML format and perform analysis on a networkmodel stored in Oracle Spatial.The proposed GUI also provides routing simulation on the calculated shortest paths withvoice commands and visual instructions.展开更多
The use of dead reckoning and fngerprint matching for navigation is a widespread technical method.However,fngerprint mismatching and low fusion accuracy are prevalent issues in indoor navigation systems.This work pres...The use of dead reckoning and fngerprint matching for navigation is a widespread technical method.However,fngerprint mismatching and low fusion accuracy are prevalent issues in indoor navigation systems.This work presents an improved dynamic time warping and a chicken particle flter to handle these two challenges.To generate the Horizontal and Vertical(HV)fngerprint,the pitch and roll are employed instead of the original fngerprint intensity to extract the horizontal and vertical components of the magnetic feld fngerprint.Derivative dynamic time warping employs the HV fngerprint in its derivative form,which receives higher-level features because of the consideration of fngerprint shape information.Chicken Swarm Optimization(CSO)is used to enhance particle weights,which minimizes position error to tackle the particle impoverishment problem for a fusion navigation system.The results of the experiments suggest that the enhanced algorithm can improve indoor navigation accuracy signifcantly.展开更多
In landmark-based way-finding,determining the most salient landmark from several candidates at decision points is challenging.To overcome this problem,current approaches usually rely on a linear model to measure the s...In landmark-based way-finding,determining the most salient landmark from several candidates at decision points is challenging.To overcome this problem,current approaches usually rely on a linear model to measure the salience of landmarks.However,linear models are not always able to establish an accurate quantitative relationship between the attributes of a landmark and its perceived salience.Furthermore,the numbers of evaluated scenes and of volunteers participating in the testing of these models are often limited.With the aim of overcoming these gaps,we propose learning a non-linear salience model by means of genetic programming.We compared our proposed approach with conventional algorithms by using photographs of two hundred test scenes collected from two shopping malls.Two hundred volunteers who were not in these environments were asked to answer questionnaires about the collected photographs.The results from this experiment showed that in 76%of the cases,the most salient landmark(according to the volunteers’perception)was correctly predicted by our proposed approach.This accuracy rate is considerably higher than the ones achieved by conventional linear models.展开更多
Micro-aerial vehicles(MAVs)find it extremely difficult to navigate in GNSS-denied indoor staircase environments with obstructed Global navigation satellite system(GNSS)signals.To avoid hitting both static and moving o...Micro-aerial vehicles(MAVs)find it extremely difficult to navigate in GNSS-denied indoor staircase environments with obstructed Global navigation satellite system(GNSS)signals.To avoid hitting both static and moving obstacles,MAV must estimate its position and heading in the staircase indoor scenes.In order to detect vanishing points and estimate heading for MAV navigation in a staircase environment,five different input colour space image frames—namely RGB image into a grayscale image and RGB image into hyper-opponent colour space—O1,O2,O3,and Sobel R channel image frames—have been used in this work.To determine the position and direction of the MAV,the Hough transform technique and K-means clustering algorithm have been incorporated for line and vanishing point recognition in the staircase image frames.The position of the vanishing point detected in the staircase image frames indicates the position of the MAV(Centre,left or right)in the staircase.In addition,to compute the heading of MAV,the Euclidean distance between the staircase picture centre,mid-pixel coordinates at the image’s last row,and the detected vanishing point pixel coordinates in the succeeding staircase image frames are used.The position and heading measurement can be utilised to send the MAV a suitable control signal and align it at the centre of the staircase when it deviates from the centre.The integrated Hough transform technique and K-means clustering-based vanishing point detection are suitable for real-time MAV heading measurement using the O2 channel staircase image frames for indoor MAVs with a high accuracy of±0.15°when compared to the state-of-the-art grid-based vanishing point detection method heading accuracy of±1.5°.展开更多
基金Technology Development Center of Finland(TEKES)for financial support
文摘During recent years, walking humanoid robots have gained popularity from wheeled vehicle robots in various assistive roles in human’s environment. Self-localization is a necessary requirement for the humanoid robots used in most of the assistive tasks. This is because the robots have to be able to locate themselves in their environment in order to accomplish their tasks. In addition, autonomous navigation of walking robots to the pre-defined destination is equally important mission, and therefore it is required that the robot knows its initiate location precisely. The indoor navigation is based on the map of the environment used by the robot. Assuming that the walking robot is capable of locating itself based on its initiate location and the distance walked from it, there are still factors that impair the map-based navigation. One of them is the robot’s limited ability to keep its direction when it is walking, which means that the robot is not able to walk directly from one point to another due to a stochastic error in walking direction. In this paper we present an algorithm for straightening the walking path using distance measurements by built-in sonar sensors of a NAO humanoid robot. The proposed algorithm enables the robot to walk directly from one point to another, which enables precise map-based indoor navigation.
基金supported in part by the National Natural Science Foundation of China (No. 61190110)the National High-Tech Research and Development (863) Program of China (No. 2011AA010100)+1 种基金the National Key Basic Research and Development (973) Program of China (No. 2012CB316200)the support from the codes of USRP2reader from the Open RFID Lab (ORL) project
文摘Indoor navigation has received much attention by both industry and academia in recent years. To locate users, a number of existing methods use various localization algorithms in combination with an indoor map, which require expensive infrastructures deployed in advance. In this study, we propose the use of existing indoor objects with attached RFID tags and a reader to navigate users to their destinations, without the need for any additional hardware. The key insight upon which our proposal is based is that a person＇s movement has an impact on the frequency shift values collected from indoor objects when they near a tag. We leverage this local human-item spatial relation to infer the user＇s position and then navigate the user to the desired destination step by step. We implement a prototype navigation system, called Roll Caller, and conduct a comprehensive range of experiments to examine its performance.
文摘In view of the poor information integrity of the 3D model used to make the indoor road network and the lack of versatility of the constructed indoor road network, a method for building an indoor navigation network model that can be seamlessly connected with outdoor paths is proposed in this paper. First, the IFC model is converted to the CityGML model using the BIM model as the indoor data source. Then, using GIS technology and limited Delaunay triangulation refinement algorithm, the necessary elements of indoor navigate on network model such as semantic information, geometric information and topological relationship contained in CityGML model are extracted. Finally, it is visualized and verified based on experimental model data. The results show that the indoor navigation network model constructed based on the CityGML model can accurately perform indoor navigation, make the constructed road network more general, and provide reference and technical support for the integrated construction of indoor and outdoor road network models.
文摘The design and implementation of indoor security robot can well integrate the two fields of indoor navigation and object detection, in order to achieve a more powerful robot system, the development of this project has certain theoretical research significance and practical application value. The project development is completed in ROS (Robot Operating System). The main tools or frameworks used include AMCL (Adaptive Monte Carlo Localization) package, SLAM (Simultaneous Localization and Mapping) algorithm, Darknet deep learning framework, YOLOv3 (You Only Look Once)algorithm, etc. The main development methods include odometer information fusion, coordinate transformation, localization and mapping, path planning, YOLOv3 model training, function package configuration and deployment. Indoor security robot has two main functions: first, it can complete real-time localization, mapping and navigation of indoor environment through sensors such as lidar and camera;Second, object detection is accomplished through USB camera. Through the detailed analysis and research of the functional design of the two modules, the expected function is finally realized, which can meet the daily use needs.
基金Supported by the National Natural Science Foundation of China(No.61971162,61771186)the Natural Science Foundation of Heilongjiang Province(No.PL2024F025)+1 种基金the Open Research Fund of National Mobile Communications Research Laboratory in Southeast University(No.2023D07)the Fundamental Scientific Research Funds of Heilongjiang Province(No.2022-KYYWF-1050).
文摘The impact of location services on people’s lives has grown significantly in the era of widespread smart device usage.Due to global navigation satellite system(GNSS)signal rejection,weak signal strength in indoor environments and radio signal interference caused by multiwall environments,which collectively lead to significant positioning errors,vision-based positioning has emerged as a crucial method in indoor positioning research.This paper introduces a scale hierarchical matching model to tackle challenges associated with large visual databases and high scene similarity,both of which will compromise matching accuracy and lead to prolonged positioning delays.The proposed model establishes an image feature database using GIST features and speeded up robust feature(SURF)in the offline stage.In the online stage,a positioning navigating algorithm is constructed based on Dijkstra’s path planning.Additionally,a corresponding Android application has been developed to facilitate visual positioning and navigation in indoor environments.Experimental results obtained in real indoor environments demonstrate that the proposed method significantly enhances positioning accuracy compared with similar algorithms,while effectively reducing time overhead.This improvement caters to the requirements for indoor positioning and navigation,thereby meeting user needs.
基金the Chair of GIScience,University of Heidelberg and the Klaus-Tschira Foundation (KTS) Heidelberg
文摘Car routing solutions are omnipresent and solutions for pedestrians also exist.Furthermore,public or commercial buildings are getting bigger and the complexity of their internal structure has increased.Consequently,the need for indoor routing solutions has emerged.Some prototypes are available,but they still lack semantically-enriched modelling (e.g.,access constraints,labels,etc.) and are not suitable for providing user-adaptive length-optimal routing in complex buildings.Previous approaches consider simple rooms,concave rooms,and corridors,but important characteristics such as distinct areas in huge rooms and solid obstacles inside rooms are not considered at all,although such details can increase navigation accuracy.By formally defining a weighted indoor routing graph,it is possible to create a detailed and user-adaptive model for route computation.The defined graph also contains semantic information such as room labels,door accessibility constraints,etc.Furthermore,one-way paths inside buildings are considered,as well as three-dimensional building parts,e.g.,elevators or stairways.A hierarchical structure is also possible with the presented graph model.
基金supported in part by the National Natural Science Foundation of China(61803175)in part by the Project of Shandong Provincial Natural Science Foundation(ZR2018LF010)
文摘A combined algorithm for the loosely fused ultra wide band(UWB)and inertial navigation system(INS)-based measurements is designed under the indoor human navigation conditions with missing data.The scheme proposed fuses the INS-and UWB-derived positions via a data fusion filter.Since the UWB signal is prone to drift in indoor environments and its outage highly affects the integrated scheme reliability,we also consider the missing data problem in UWB measurements.To overcome this problem,the loosely-coupled INS/UWB-integrated scheme is augmented with a prediction option based on the predictive unbiased finite impulse response(UFIR)fusion filter.We show experimentally that,the standard UFIR fusion filter has higher robustness than the Kalman filter.It is also shown that the predictive UFIR fusion filter is able to produce an acceptable navigation accuracy under temporary missing UWB-data.
基金The project is supported by European Open Robot Control Software Founda-tion(No.IST-2000-31064), National Natural Science Foundation of China(No.60475031) and the Swedish Foundation for Strategic Research, Sweden.
文摘It is discussed with the design and implementation of an architecture for a mobile robot to navigate in dynamic and anknown indoor environments. The architecture is based on the framework of Open Robot Control Software at KTH （OROCOS@KTH）, which is also discussed and evaluated to navigate indoor efficiently, a new algorithm named door-like-exit detection is proposed which employs 2D feature oft. door and extracts key points of pathway from the raw data of a laser scanner. As a hybrid architecture, it is decomposed into several basic components which can be classified as either deliberative or reactive. Each component can concurrently execute and communicate with another. It is expansible and transferable and its components are reusable.
基金supported by the National Natural Science Foundation of China(62303009,62236002)
文摘Dear Editor,This letter addresses the challenges of sparse and delayed rewards in complex indoor navigation tasks. To this end,we propose a task decomposition-based reinforcement learning framework that integrates a reinforcement learning(RL) algorithm with a path planner.
基金This study was supported by TUBITAK–The Scientific and Technological Research Council of Turkey(Project No.112Y050)research grant.We are indebted for its financial support.
文摘3D navigation within a 3D-GIS environment is increasingly getting more popular and spreading to various fields.In thelast decade,especially after the 9/11 disaster,evacuating the complex and tall buildings of today in case of emergencyhas been an important research area for scientists.Most of the current navigation systems are still in the 2D environmentand that is insufficient to visualize 3D objects and to obtain satisfactory solutions for the 3D environment.Therefore,there is currently still a lack of implementation of 3D network analysis and navigation for indoor spaces in respect toevacuation.The objective of this paper is to investigate and implement 3D visualization and navigation techniques andsolutions for indoor spaces within 3D-GIS.For realizing this,we have proposed a GIS implementation that is capable ofcarrying out 3D visualization of a building model stored in the CityGML format and perform analysis on a networkmodel stored in Oracle Spatial.The proposed GUI also provides routing simulation on the calculated shortest paths withvoice commands and visual instructions.
基金supported by Grant EGD21QD15,the Research project of Shanghai Polytechnic University。
文摘The use of dead reckoning and fngerprint matching for navigation is a widespread technical method.However,fngerprint mismatching and low fusion accuracy are prevalent issues in indoor navigation systems.This work presents an improved dynamic time warping and a chicken particle flter to handle these two challenges.To generate the Horizontal and Vertical(HV)fngerprint,the pitch and roll are employed instead of the original fngerprint intensity to extract the horizontal and vertical components of the magnetic feld fngerprint.Derivative dynamic time warping employs the HV fngerprint in its derivative form,which receives higher-level features because of the consideration of fngerprint shape information.Chicken Swarm Optimization(CSO)is used to enhance particle weights,which minimizes position error to tackle the particle impoverishment problem for a fusion navigation system.The results of the experiments suggest that the enhanced algorithm can improve indoor navigation accuracy signifcantly.
基金the National Key R&D Program of China(No.2016YFB0502203)the National Natural Science Foundation of China(Grant No.41271440)the China Scholarship Council.
文摘In landmark-based way-finding,determining the most salient landmark from several candidates at decision points is challenging.To overcome this problem,current approaches usually rely on a linear model to measure the salience of landmarks.However,linear models are not always able to establish an accurate quantitative relationship between the attributes of a landmark and its perceived salience.Furthermore,the numbers of evaluated scenes and of volunteers participating in the testing of these models are often limited.With the aim of overcoming these gaps,we propose learning a non-linear salience model by means of genetic programming.We compared our proposed approach with conventional algorithms by using photographs of two hundred test scenes collected from two shopping malls.Two hundred volunteers who were not in these environments were asked to answer questionnaires about the collected photographs.The results from this experiment showed that in 76%of the cases,the most salient landmark(according to the volunteers’perception)was correctly predicted by our proposed approach.This accuracy rate is considerably higher than the ones achieved by conventional linear models.
文摘Micro-aerial vehicles(MAVs)find it extremely difficult to navigate in GNSS-denied indoor staircase environments with obstructed Global navigation satellite system(GNSS)signals.To avoid hitting both static and moving obstacles,MAV must estimate its position and heading in the staircase indoor scenes.In order to detect vanishing points and estimate heading for MAV navigation in a staircase environment,five different input colour space image frames—namely RGB image into a grayscale image and RGB image into hyper-opponent colour space—O1,O2,O3,and Sobel R channel image frames—have been used in this work.To determine the position and direction of the MAV,the Hough transform technique and K-means clustering algorithm have been incorporated for line and vanishing point recognition in the staircase image frames.The position of the vanishing point detected in the staircase image frames indicates the position of the MAV(Centre,left or right)in the staircase.In addition,to compute the heading of MAV,the Euclidean distance between the staircase picture centre,mid-pixel coordinates at the image’s last row,and the detected vanishing point pixel coordinates in the succeeding staircase image frames are used.The position and heading measurement can be utilised to send the MAV a suitable control signal and align it at the centre of the staircase when it deviates from the centre.The integrated Hough transform technique and K-means clustering-based vanishing point detection are suitable for real-time MAV heading measurement using the O2 channel staircase image frames for indoor MAVs with a high accuracy of±0.15°when compared to the state-of-the-art grid-based vanishing point detection method heading accuracy of±1.5°.
