Visually-extended vector polar histogram applied to robot route navigation

Lee, Seung Hwan; Lee, Heoncheol; Lee, Beom-Hee

doi:10.1007/s12555-011-0414-x

Cited by 7 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…VPH+ was used to compute the desired direction while MPC generated a constrained model predictive trajectory [18]. Additionally, VPH+ was visually extended in a way suitable for camera sensors [19]. For enhanced accuracy of visual data, a hidden Markov model and an extended Kalman filter were employed.…”

Section: Introductionmentioning

confidence: 99%

An Extended Vector Polar Histogram Method Using Omni-Directional LiDAR Information

2023

View full text Add to dashboard Cite

This study presents an extended vector polar histogram (EVPH) method for efficient robot navigation using omni-directional LiDAR data. Although the conventional vector polar histogram (VPH) method is a powerful technique suitable for LiDAR sensors, it is limited in its sensing range by the single LiDAR sensor to a semicircle. To address this limitation, the EVPH method incorporates multiple LiDAR sensor’s data for omni-directional sensing. First off, in the EVPH method, the LiDAR sensor coordinate systems are directly transformed into the robot coordinate system to obtain an omni-directional polar histogram. Several techniques are also employed in this process, such as minimum value selection and linear interpolation, to generate a uniform omni-directional polar histogram. The resulting histogram is modified to represent the robot as a single point. Subsequently, consecutive points in the histogram are grouped to construct a symbol function for excluding concave blocks and a threshold function for safety. These functions are combined to determine the maximum cost value that generates the robot’s next heading angle. Robot backward motion is made feasible based on the determined heading angle, enabling the calculation of the velocity vector for time-efficient and collision-free navigation. To assess the efficacy of the proposed EVPH method, experiments were carried out in two environments where humans and obstacles coexist. The results showed that, compared to the conventional method, the robot traveled safely and efficiently in terms of the accumulated amount of rotations, total traveling distance, and time using the EVPH method. In the future, our plan includes enhancing the robustness of the proposed method in congested environments by integrating parameter adaptation and dynamic object estimation methods.

show abstract

Section: Introductionmentioning

confidence: 99%

An Extended Vector Polar Histogram Method Using Omni-Directional LiDAR Information

2023

View full text Add to dashboard Cite

show abstract

“…O presente trabalho utiliza duas estruturas probabilísticas para realizar o rastreamento da posição de um robô móvel planar não holonômico: o HMM (hidden Markov model ) e o EKF (extended Kalman filter ). Na literatura encontram-se várias pesquisas utilizando o HMM e o EKF para localizar robôs a partir de leituras de sensores (Tong et al, 2018;Savage et al, 2018;Pomárico-Franquiz et al, 2014;Lee et al, 2011). Experimentos são realizados no software V-REP, no qual são passadas algumas trajetórias a serem seguidas pelo robô, e compara-se o resultado da estimação da posição obtido com as duas estruturas.…”

Section: Introductionunclassified

Estimação da localização de um robô não holonômico utilizando modelo oculto de Markov (HMM) e o filtro de Kalman estendido (EKF)

Monteiro

Maia

Gonçalves

2019

Anais Do 14º Simpósio Brasileiro De Automação Inteligente

View full text Add to dashboard Cite

Knowing the location of a robot is fundamental to correctly planning a safe navigation towards the destination. In this article we use the hidden Markov model (HMM) and the extended Kalman filter (EKF) to estimate the position of a non-holonomic mobile robot, during the tracing of parametrized trajectories in time. The proposed location system consists of a transceiver coupled to the robot, which communicates with three other transceivers in predetermined positions. By sending periodic messages to other transceivers, the robot can estimate its position relative to other transceivers. These measurements are used in HMM and EKF to estimate the location of the robot. Experiments were performed, and the results show that the methods used present robustness to estimate the location of robots. Resumo: Conhecer a localização de um robôé fundamental para planejar corretamente uma navegação segura em direção ao local de destino. Neste artigo utiliza-se o modelo oculto de Markov (HMM) e o filtro de Kalman estendido (EKF) para estimar a posição de um robô móvel não holonômico, durante o rastreamento de trajetórias parametrizadas no tempo. O sistema de localização propostoé constituído de um transceptor acoplado ao robô, que se comunica com outros três transceptores em posições predeterminadas. Ao enviar mensagens periódicas aos outros transceptores, o robô consegue estimar sua posição relativa aos demais transceptores. Estas medidas são usadas no HMM e no EKF para estimar a localização do robô. Experimentos foram realizados, e os resultados mostram que os métodos utilizados apresentam robustez para estimar a localização de robôs.

show abstract

“…In addition, it is also important to avoid collisions with moving obstacles such as humans and robots as well as stationary obstacles. As a result, many collision-free navigation methods have been developed [3]. Recently, vision sensors are usually employed for SLAM instead of range sensors such as laser range finder, sonar sensors, and infra-red scanners, because of objects sensed by vision sensors enable data association simpler in real environment [4].…”

Section: Introductionmentioning

confidence: 99%

Collision-Free Multi-Robot Navigation Using Autonomous Object Selection

Lee

Jeon

Kim

et al. 2013

AMM

View full text Add to dashboard Cite

For successful SLAM, landmarks for pose estimation should be continuously observed. Firstly, we proposed the object selection algorithm from 2D images and 3D depth maps without human’s supervision. We used the SIFT algorithm to obtain descriptors of point features inside the object, and the surface segmentation algorithm to obtain separated objects from point clouds of 3D depth maps. Automatically selected objects were tested by the threshold function using repeatability, distinctiveness and saliency whether the objects were suitable or not for reusing and sharing between the robots. Secondly, we suggested the closed-form solution to estimate the 3D pose of robots from the information of selected objects. Furthermore, we provided the effective way to accomplish the tasks using multi-robot by compensating the accumulated navigating errors and re-planning the collision-free motion of the robots using the extended collision map algorithm.

show abstract

Visually-extended vector polar histogram applied to robot route navigation

Cited by 7 publications

References 23 publications

An Extended Vector Polar Histogram Method Using Omni-Directional LiDAR Information

An Extended Vector Polar Histogram Method Using Omni-Directional LiDAR Information

Estimação da localização de um robô não holonômico utilizando modelo oculto de Markov (HMM) e o filtro de Kalman estendido (EKF)

Collision-Free Multi-Robot Navigation Using Autonomous Object Selection

Contact Info

Product

Resources

About