No abstract

Tactile sensor systems are an essential prerequisite for the implementation of complex manipulation and exploration tasks using robots. Tactile exploration has not yet found its way into many laboratories, because most tactile sensors are technically demanding and expensive.The desire to perform real-time control and pattern recognition with tactile sensors led us to the design of a cost-effective artificial fingertip. At our laboratory two distinct types of sensors are in use: force/position sensors, and slippage detectors. We report on first experimental results with a fingertip prototype performing rolling and sliding movements over a flat surface.To facilitate experimentation with tactile sensors, we designed and developed a data acquisition and transportation system that fulfils our demands on bandwidth, flexibility, and cost. This system consists of two hardware components, a configurable multi-channel analog signal sampler (MASS) to acquire sensor data, and an intelligent dual-ported random-access buffer (BRAD) to avoid data transportation bottlenecks.

A major goal for the realization of a new generation of intelligent robots is the capability of instructing work tasks by interactive demonstration. To make such a process e&ient and convenient for the human user requires that both the robot and the user can establish and maintain a common focus of attention. We describe a hybrid architecture that combines neural networks and finite state machines into a flexible framework for controlling the behaviour of a vision based robot called GRAVIS-robot (Gestural Recognition Active VIsion System robot). It consists of a binocular camera head, a 6 DOF robot arm and a 9 DOF multifinsered hand. We focus primarily on non-verbal communication based on gestural commands of a human instructor which will at a later stage be complemented by spoken instructions.