No abstract

A vision-based vehicle guidance system working in road environments has three main roles: road detection, sign recognition, and obstacles detection. There are many and good works in road detection, some about obstacles detection but few ones on sign recognition. Traffic signs provide very valuable information about the road in order to make it safer and driving easier for people. We think that they will still play the same part for autonomous vehicles. They are designed to be easily recognized by human drivers mainly because their color and shapes are very different from natural environments. The algorithm presented in this paper makes the best of these features. The algorithm has two main parts. The first one, for the detection, uses the color and shape of the sign to detect it. The second one, for the classification, uses a neural network. Some results from natural scenes are shown. INTRODUCTION.

This paper deals with the application of a large range robot for on site assembly operations in the construction industry. The wall erection task, using standard and special concrete blocks, is the main operation of the robot. The assembly process and the robot have been developed under the Computer Integrated Construction (CIC) concept. It means that the robot is easily integrated in the complete CIC system by adequated interfaces. Special attention has been paid to the manmachine interface (MMI) which permits to program and control the system in an automatic and friendly way, i.e., from the CAD building design the system commands and sequences are automatically generated. The hydraulically driven robot is a 6 DOF articulated manipulator with a working range of 8.5 m and it is able to carry payloads up to 500 kg. This work is part of the European ESPRIT III project n° 6450 ROCCO (Robot Assembly System for Computer Integrated Construction).

No abstract

No abstract