Community Research and Development Information Service - CORDIS

Abstract

Ultrasonic data interpretation in robotics navigation is affected by specular reflections and sensor crosstalk. The first of these problems can be overcome by using multiple sensors in appropriate geometric layouts. This paper focuses on the problem of local navigation by using special perception maps built from multi-sensorial ultrasonic data. The main properties of these maps are their topology and geometry. These properties are adapted to sensor characteristics, measurement reliability and spatial redundancy. This results in a non-Cartesian grid where the decision to consider a cell free or occupied comes from more than one sensor. These maps are built using real data from a 24-ultrasonic sensor array. A neural network performs the mapping between ultrasonic data and cell occupancy.

Additional information

Authors: SANTOS V, JRC Ispra (IT);GONÇALVES J G M, JRC Ispra (IT);VAZ F, Universidade de Aveiro (PT);GONCALVES J G M, JRC Ispra (IT)
Bibliographic Reference: Paper presented: Workshop on Multisensor Applications, Bruxelles (BE), November 25, 1993
Availability: Available from (1) as Paper EN 38037 ORA
Record Number: 199410082 / Last updated on: 1994-11-28
Category: PUBLICATION
Original language: en
Available languages: en
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top