Environments for supporting the navigation of assistive mobile robots

• Grant number: 11/09113-7
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: November 01, 2011
• End date: October 31, 2015
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Eleri Cardozo
• Grantee: Eric Rohmer
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 13/07559-3 - BRAINN - The Brazilian Institute of Neuroscience and Neurotechnology, AP.CEPID

Abstract

This project has as its main objective to design, implement, and evaluate a smart environment to help the navigation of assistive robots carrying disabled persons. The project is in line with the DesTINe (Development of Information Technologies for Neurology) project recently approved by FINEP (Financiadora de Estudos e Projetos) and with a thematic project to be submitted to FAPESP (Fundação de Amparo à Pesquisa do Estado de São Paulo). The DesTINe project has three main lines of research: neurology, digital signal processing, and mobile robotics. The ultimate goal is to build an assistive mobile robot (e.g., a robotized wheelchair) that can navigate with signals acquired from the operator and from the environment. Example of signals generated by the operator include brain activity captured by brain headsets, eye and face tracking acquired from cameras, and whispers acquired from microphones. Once acquired, signals must be processed by a classification system in order to extract high level commands. Such commands are submitted to the robotic vehicle that in its turn translate them into movements. The robot must have high autonomy to navigate safely in crowded areas, avoiding transient and permanent obstacles. We consider that the environment where the vehicle navigates plays an important role in the navigation. If the environment has a set of sensors (cameras, RFID tag readers, fixed infrared rangefinders, etc.) it can supply the robot several environmental data such as positions, presence of obstacles, crowded areas etc., simplifying the sensing capabilities required from the robot. The development of this smart environment is the focus of this post-doctoral project. Both virtual (simulated) and real smart environments will be addressed. The virtual environment is of prime importance to assess and calibrate the digital signal processing and mobile robotics algorithms, as well as for training disabled persons in the conduction of assistive robots. In the second year, a real smart environment of small dimensions based on cameras and RFID tag readers will be deployed in cooperation with other researchers of the DesTINe project. This two year project will be conducted by a post-doctoral researcher co-supervising a team of graduate and undergraduate students (around five students are foreseen) and interacting with researchers from FEEC/Unicamp and CTI Renato Archer working in the DesTINe project. (AU)