Localization for autonomous vehicles in urban environment using continuous occupancy maps

• Grant number: 12/02354-1
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: May 01, 2013
• End date: May 31, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Denis Fernando Wolf
• Grantee: Alberto Yukinobu Hata
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated scholarship(s): 14/09096-3 - Localização de Veículos utilizando Mapas continuos de processos Gaussianos, BE.EP.DR

Abstract

Localization is one of the most relevant problems in mobile robotics, and is basis for other robot functionalities, such as mapping, path planning and motion controlling. Currently there are devices like GPS, odometer and digital compass that provide the position with high accuracy. However, these sensors can accumulate errors over time that prejudice the robot navigation. These errors are originated by external disturbance, as example, discontinuity in the GPS signal caused by building obstruction. In order to fix these failures, there are methods that incorporate into the localization system, information regards the sensor data (cameras or laser range finders) matching with the environment map. For this, it is necessary a map building step, that most of times are impractical for areas of city sizes. To overcome this problem, the actual project proposes the employment of satellite map, which is available freely by several sources, moreover, has high resolution and precise longitude and latitude information. The localization system will be deployed in real vehicles to obtain its localization relative to this map while driving in urban environments. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

HATA, ALBERTO Y.; WOLF, DENIS F.. Feature Detection for Vehicle Localization in Urban Environments Using a Multilayer LIDAR. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, v. 17, n. 2, p. 420-429, FEB 2016. (12/02354-1, 14/09096-3)

HATA, ALBERTO YUKINOBU; WOLF, DENIS FERNANDO; RAMOS, FABIO TOZETO; KULIC, D; NAKAMURA, Y; KHATIB, O; VENTURE, G. Particle Filter Localization on Continuous Occupancy Maps. 2016 INTERNATIONAL SYMPOSIUM ON EXPERIMENTAL ROBOTICS, v. 1, p. 10-pg., 2017-01-01. (14/09096-3, 12/02354-1)

HATA, ALBERTO Y.; RAMOS, FABIO T.; WOLF, DENIS E.. Monte Carlo Localization on Gaussian Process Occupancy Maps for Urban Environments. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, v. 19, n. 9, p. 2893-2902, SEP 2018. (12/02354-1, 14/09096-3)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

HATA, Alberto Yukinobu. Road features detection and sparse map-based vehicle localization in urban environments. 2016. Doctoral Thesis - Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB) São Carlos.