Fusing vision and odometry for accurate indoor robot localization

Bischoff, Bastian; Nguyen-Tuong, Duy; Streichert, Felix; Ewert, Marlon; Knoll, Alois

doi:10.1109/icarcv.2012.6485183

Cited by 22 publications

(14 citation statements)

References 10 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Drawbacks of systems such as [3] are mostly the cost of the system, the basic cause for which almost none of SPL teams have employed such systems. The other drawback which also exists in [4] can be named as time consuming setup procedure, including placing markers on robot and camera geometric calibration. Besides, markers on robot can distract robot detection algorithms.…”

Section: Related Workmentioning

confidence: 99%

Ground-truth localisation system for humanoid soccer robots using RGB-D camera

Nezhad

Ghiasvand

2017

IJCVR

View full text Add to dashboard Cite

An essential step to develop an autonomous mobile robot behavior is establishment of a groundtruth detection system which can be used for both the localisation and behavior analysis. Depend on the requirements of the application there are some constraints for such a system like: diversity in types of providing information, accuracy of the data and ease of use -since the calibration is needed in both color classification and geometry position -and also the cost of the system, which all should be considered. In this paper, a low cost system is presented, using Asus Xtion depth camera, capable of providing ground-truth position information of the humanoid robots and the ball which is required to estimate the errors of a localisation system in RoboCup Standard Platform League (SPL) and Humanoid kid Size League (HSL) soccer robots. Furthermore the user input requirements are reduced to very few compared to other similar systems. Source code of the system is available online at: https://github.com/mrlspl/ As the result of literature review, three main factors could be named as properties of an appropriate ground-truth system: Total system cost  Ease of system calibration procedure  Diversity in types of provided information In this paper we present a low cost ground-truth localisation system which minimizes user's role in system calibration and provides most of the information from the soccer match including: robots, ball and referees positions in addition to team color identification.SPL and HSL game fields (9 6 meters [1] and 6 4 [2]) and their corresponding robots -namely NAO and DARwIn -have been chosen as the system's testbed.

show abstract

Section: Related Workmentioning

confidence: 99%

Ground-truth localisation system for humanoid soccer robots using RGB-D camera

Nezhad

Ghiasvand

2017

IJCVR

View full text Add to dashboard Cite

show abstract

“…Em seguida, a posiçãoé calculada por meio de integração numérica. Contudo, este processo resulta no erro da localização ao longo do tempo (Bischoff et al, 2012). Outras tarefas importantes dos sistemas de navegação tratam do planejamento de caminho (planejamento da rota a ser seguida pelo robô) e planejamento de movimento, ou seja, como o robô irá se mover de um ponto a outro seguindo o caminho especificado (Engedy and Horvath, 2019).…”

Section: Introductionunclassified

Desenvolvimento de um Sistema de Navegação para Robôs Móveis Baseado em Visão Computacional

Ribeiro¹,

Filho

Medeiros

et al. 2019

Anais Do 14º Simpósio Brasileiro De Automação Inteligente

View full text Add to dashboard Cite

Mobile robotics has applications in many different areas, such as in industries, homes and military. For the development of navigation system for mobile robotics, localization is one of the main tasks, since this parameter is necessary to assist decisions making and plan how the robot will achieve the desired points. Several approaches to this problem are used, with odometry widely applied. However, odometry often do not present good precision results when applied to indoor environments. In this context, this work presents the development of a navigation system considering localization and position control based on computer vision applied to mobile robots in indoor environments. It is presented a comparison between the location system based on odometry and the proposed system based on computer vision. The experimental results demonstrates the efficiency of the proposed localization system and compares it to an odometrybased method. Resumo: A robótica móvel possui aplicações nas mais diversasáreas, como em indústrias, residências e até militar. Para o desenvolvimento de um sistema de navegação para sistemas robóticos, a localizaçãoé uma tarefa primordial, uma vez que este parâmetroé necessário para planejar como robô chegará aos pontos desejados e auxiliar na tomada de decisões. São utilizadas diversas abordagens para este problema, sendo a odometria amplamente aplicada. Entretanto, a odometria costuma não apresentar bons resultados relacionadosà precisão quando aplicada a ambientes internos. Neste contexto, este trabalho apresenta o desenvolvimento de um sistema de navegação (englobando localização e controle de posição) baseado em visão computacional, aplicado a robôs móveis em ambientes internos.É apresentado ainda um comparativo entre o sistema de localização baseado em odometria e o sistema proposto baseado em visão computacional. Ao fim do trabalho,é demonstrada (por meio de resultados experimentais) a eficiência do sistema de localização baseado em visão computacional em comparação com a localização por odometria.

show abstract

“…In [16], Chen presents a review of contributions of Kalman filtering in solving mobile robot problems such as localization, mapping and navigation. In literature, many authors have fused motion sensor measurements with vision sensor data for mobile robot localization using the Kalman filter [14], [17], [18], [19]. In these works, often different types of motion sensors (i.e.…”

Section: Introductionmentioning

confidence: 99%

“…We do not manipulate the environment by using artificial landmarks for localization [17], [23], and we do not modify the mobile platform ( power wheelchair) to be more suitable for autonomous motion. In addition, we not only detect the localization error, but also design a control scheme to correct it.…”

Section: Introductionmentioning

confidence: 99%

Design, implementation and evaluation of a motion control scheme for mobile platforms with high uncertainties

Mashali

Alqasemi

Sarkar

et al. 2014

5th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics

View full text Add to dashboard Cite

In this work, we present a motion control scheme for a robotic mobile platform using low-cost vision sensor to update encoder values. We track the pose of a power wheelchair using wheel encoders along with a Microsoft Kinect camera. Two methods of pose estimation are implemented and tested. These methods are a) encoder-based odometry and b)ICP(Iterative Closest Point)-based updated odometry. We evaluate the performance of each method using precise wheelchair pose ground truth data acquired via a state-of-theart VICON R system with eight motion capture cameras. Offline data processing is performed to refine the ICP parameters and estimate the covariance matrices of the Kalman filter. The offline data processing results demonstrate that our ICP-based updated odometry has very accurate pose tracking. By implementing our control scheme, the position error is improved by a factor of 15 and the localization orientation error is improved by a factor of 13. In online implementation, there was 4 times improvement for both position and orientation angle estimation. To demonstrate the robustness of our approach, we apply it for online obstacle avoidance. A wheelchair-mounted robotic arm (WMRA) is also included in this platform and will be used for future work on combined mobility and manipulation control with sensor assistance.

show abstract

Fusing vision and odometry for accurate indoor robot localization

Cited by 22 publications

References 10 publications

Ground-truth localisation system for humanoid soccer robots using RGB-D camera

Ground-truth localisation system for humanoid soccer robots using RGB-D camera

Desenvolvimento de um Sistema de Navegação para Robôs Móveis Baseado em Visão Computacional

Design, implementation and evaluation of a motion control scheme for mobile platforms with high uncertainties

Contact Info

Product

Resources

About