Tracking People in a Mobile Robot From 2D LIDAR Scans Using Full Convolutional Neural Networks for Security in Cluttered Environments.

Ángel Manuel Guerrero-Higueras,Francisco J. Rodríguez-Lera,Vicente Matellán,Camino Fernández-Llamas,Francisco Martín Rico,Claudia Álvarez-Aparicio,María Carmen Calvo Olivera

doi:10.3389/fnbot.2018.00085

Ángel Manuel Guerrero-Higueras, Francisco J. Rodríguez-Lera + Show 5 more

Open Access

https://doi.org/10.3389/fnbot.2018.00085

Copy DOI

Abstract

Tracking people has many applications, such as security or safe use of robots. Many onboard systems are based on Laser Imaging Detection and Ranging (LIDAR) sensors. Tracking peoples' legs using only information from a 2D LIDAR scanner in a mobile robot is a challenging problem because many legs can be present in an indoor environment, there are frequent occlusions and self-occlusions, many items in the environment such as table legs or columns could resemble legs as a result of the limited information provided by two-dimensional LIDAR usually mounted at knee height in mobile robots, etc. On the other hand, LIDAR sensors are affordable in terms of the acquisition price and processing requirements. In this article, we describe a tool named PeTra based on an off-line trained full Convolutional Neural Network capable of tracking pairs of legs in a cluttered environment. We describe the characteristics of the system proposed and evaluate its accuracy using a dataset from a public repository. Results show that PeTra provides better accuracy than Leg Detector (LD), the standard solution for Robot Operating System (ROS)-based robots.

Highlights

Detecting and tracking people are very useful capabilities for different systems, in particular for improving navigation in mobile robots and to facilitate more socially acceptable robots, and in security applications, for instance using biometric data (Ngo et al, 2015; Gavrilova et al, 2017) or safely using robotics platforms (Morante et al, 2015)
Laser Imaging Detection and Ranging (LIDAR) sensors are reliable and currently affordable range sensors that provide information about a dynamic environment at good rates (∼ 20 − 30 Hz) that can be processed in real-time, as each scan consists of an array of just a few 100 integers
We propose a system based on Convolutional Neural Network (CNN) developed by the Robotics Group at the University of León, named PeTra, for developing tracking systems based on LIDAR measurements

Summary

Introduction

Detecting and tracking people are very useful capabilities for different systems, in particular for improving navigation in mobile robots and to facilitate more socially acceptable robots, and in security applications, for instance using biometric data (Ngo et al, 2015; Gavrilova et al, 2017) or safely using robotics platforms (Morante et al, 2015). There are many solutions in the literature that try to solve this problem using a multi-modal approach, typically with vision and range sensors (Arras et al, 2012), but these kinds of approaches are very expensive both from the point of view of the cost of the sensor and the computing capabilities needed for processing and integrating, and are more likely to generate contradictory information. For this reason, systems based only on range sensors are more desirable. Laser Imaging Detection and Ranging (LIDAR) sensors are reliable and currently affordable range sensors that provide information about a dynamic environment at good rates (∼ 20 − 30 Hz) that can be processed in real-time, as each scan consists of an array of just a few 100 integers.

Methods

Results

Discussion

Conclusion