A K-Nearest Neighbours Based Inverse Sensor Model for Occupancy Mapping

Research output: Contribution to conferencePaper

14 Downloads (Pure)

Abstract

OctoMap is a popular 3D mapping framework which can model the data consistently and keep the 3D models compact with the octree. However, the occupancy map derived by OctoMap can be incorrect when the input point clouds are with noisy measurements. Point cloud filters can reduce the noisy data, but it is unreasonable to apply filters in a sparse point cloud. In this paper, we present a k-nearest neighbours (k-NN) based inverse sensor model for occupancy mapping. This method represents the occupancy information of one point with the average distance from the point to its k-NN in the point cloud. The average distances derived by all the points and their corresponding k-NN are assumed to be normally distributed. Our inverse sensor model is presented based on this normal distribution. The proposed approach is able to deal with sparse and noisy point clouds. We implement the model in the OctoMap to carry out experiments in the real environment. The experimental results show that the 3D occupancy map generated by our approach is more reliable than that generated by the inverse sensor model in OctoMap.
Original languageEnglish
Publication statusAccepted/In press - 25 Apr 2019
Event20th Towards Autonomous Robotic Systems Conference: TAROS 2019 - the Centre for Advanced Robotics@Queen Mary, London, UK United Kingdom
Duration: 3 Jul 20195 Jul 2019
https://www.qmul.ac.uk/robotics/events/taros2019/

Conference

Conference20th Towards Autonomous Robotic Systems Conference
CountryUK United Kingdom
CityLondon
Period3/07/195/07/19
Internet address

Cite this

Miao, Y., Georgilas, I., & Hunter, A. J. (Accepted/In press). A K-Nearest Neighbours Based Inverse Sensor Model for Occupancy Mapping. Paper presented at 20th Towards Autonomous Robotic Systems Conference, London, UK United Kingdom.

A K-Nearest Neighbours Based Inverse Sensor Model for Occupancy Mapping. / Miao, Yu; Georgilas, Ioannis; Hunter, Alan J.

2019. Paper presented at 20th Towards Autonomous Robotic Systems Conference, London, UK United Kingdom.

Research output: Contribution to conferencePaper

Miao, Y, Georgilas, I & Hunter, AJ 2019, 'A K-Nearest Neighbours Based Inverse Sensor Model for Occupancy Mapping' Paper presented at 20th Towards Autonomous Robotic Systems Conference, London, UK United Kingdom, 3/07/19 - 5/07/19, .
Miao Y, Georgilas I, Hunter AJ. A K-Nearest Neighbours Based Inverse Sensor Model for Occupancy Mapping. 2019. Paper presented at 20th Towards Autonomous Robotic Systems Conference, London, UK United Kingdom.
Miao, Yu ; Georgilas, Ioannis ; Hunter, Alan J. / A K-Nearest Neighbours Based Inverse Sensor Model for Occupancy Mapping. Paper presented at 20th Towards Autonomous Robotic Systems Conference, London, UK United Kingdom.
@conference{f65a8ece9349485ca75ac8b155c56a21,
title = "A K-Nearest Neighbours Based Inverse Sensor Model for Occupancy Mapping",
abstract = "OctoMap is a popular 3D mapping framework which can model the data consistently and keep the 3D models compact with the octree. However, the occupancy map derived by OctoMap can be incorrect when the input point clouds are with noisy measurements. Point cloud filters can reduce the noisy data, but it is unreasonable to apply filters in a sparse point cloud. In this paper, we present a k-nearest neighbours (k-NN) based inverse sensor model for occupancy mapping. This method represents the occupancy information of one point with the average distance from the point to its k-NN in the point cloud. The average distances derived by all the points and their corresponding k-NN are assumed to be normally distributed. Our inverse sensor model is presented based on this normal distribution. The proposed approach is able to deal with sparse and noisy point clouds. We implement the model in the OctoMap to carry out experiments in the real environment. The experimental results show that the 3D occupancy map generated by our approach is more reliable than that generated by the inverse sensor model in OctoMap.",
author = "Yu Miao and Ioannis Georgilas and Hunter, {Alan J.}",
year = "2019",
month = "4",
day = "25",
language = "English",
note = "20th Towards Autonomous Robotic Systems Conference : TAROS 2019 ; Conference date: 03-07-2019 Through 05-07-2019",
url = "https://www.qmul.ac.uk/robotics/events/taros2019/",

}

TY - CONF

T1 - A K-Nearest Neighbours Based Inverse Sensor Model for Occupancy Mapping

AU - Miao, Yu

AU - Georgilas, Ioannis

AU - Hunter, Alan J.

PY - 2019/4/25

Y1 - 2019/4/25

N2 - OctoMap is a popular 3D mapping framework which can model the data consistently and keep the 3D models compact with the octree. However, the occupancy map derived by OctoMap can be incorrect when the input point clouds are with noisy measurements. Point cloud filters can reduce the noisy data, but it is unreasonable to apply filters in a sparse point cloud. In this paper, we present a k-nearest neighbours (k-NN) based inverse sensor model for occupancy mapping. This method represents the occupancy information of one point with the average distance from the point to its k-NN in the point cloud. The average distances derived by all the points and their corresponding k-NN are assumed to be normally distributed. Our inverse sensor model is presented based on this normal distribution. The proposed approach is able to deal with sparse and noisy point clouds. We implement the model in the OctoMap to carry out experiments in the real environment. The experimental results show that the 3D occupancy map generated by our approach is more reliable than that generated by the inverse sensor model in OctoMap.

AB - OctoMap is a popular 3D mapping framework which can model the data consistently and keep the 3D models compact with the octree. However, the occupancy map derived by OctoMap can be incorrect when the input point clouds are with noisy measurements. Point cloud filters can reduce the noisy data, but it is unreasonable to apply filters in a sparse point cloud. In this paper, we present a k-nearest neighbours (k-NN) based inverse sensor model for occupancy mapping. This method represents the occupancy information of one point with the average distance from the point to its k-NN in the point cloud. The average distances derived by all the points and their corresponding k-NN are assumed to be normally distributed. Our inverse sensor model is presented based on this normal distribution. The proposed approach is able to deal with sparse and noisy point clouds. We implement the model in the OctoMap to carry out experiments in the real environment. The experimental results show that the 3D occupancy map generated by our approach is more reliable than that generated by the inverse sensor model in OctoMap.

M3 - Paper

ER -