Development of autonomous vehicles: a hybrid method for identifying markings in urban traffic

• Grant number: 11/21956-0
• Support Opportunities: Scholarships abroad - Research Internship - Doctorate
• Start date: August 01, 2012
• End date: July 31, 2013
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Denis Fernando Wolf
• Grantee: Patrick Yuri Shinzato
• Supervisor: Christoph Stiller
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Institution abroad: Karlsruhe Institute of Technology (KIT), Germany
• Associated to the scholarship: 10/01305-1 - A vehicle driving assistance system based on sensor fusion., BP.DR

Abstract

The development of autonomous vehicles has been studied since the 80's. This type of technology will help reduce traffic accidents and and provide transportation to physically handicapped or visually impaired people. Despite its importance and the great attention that this topic has received from researchers this problem still presents many challenges and open issues due to its high complexity. Typically, the urban scenario has several visual cues that indicate rules of conduct on that stretch of road. For an autonomous vehicle can travel in the same scenario in harmony with other vehicles, it should recognize the road which can travel and recognize these cues.Since the development of a fully autonomous vehicle is still a major challenge, this research project proposes the development of a system of recognition of semantic information in urban environments based on sensor fusion. This system will be part of a assisted steering system for vehicles in urban environments that will build a navigable map of the environment enriched by semantic information regarding traffic rules of the place. Based on this map, the vehicle driver can be warned at risk of collision, holes in the track, proximity the curb or even traffic violations. (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)

SHINZATO, PATRICK Y.; WOLF, DENIS E.; STILLER, CHRISTOPH; IEEE. Road Terrain Detection: Avoiding Common Obstacle Detection Assumptions Using Sensor Fusion. 2014 IEEE INTELLIGENT VEHICLES SYMPOSIUM PROCEEDINGS, v. N/A, p. 6-pg., 2014-01-01. (10/01305-1, 11/21956-0)