System-controlled user interaction within the service robotic control architecture MASSiVE

Abstract

SUMMARYThis paper presents an approach to reduce the technical complexity of a service robotic system by means of systematic and well-balanced user-involvement. By taking advantage of the user's cognitive capabilities during task execution, a technically manageable robotic system, which is able to execute tasks on a high level of abstraction reliably and robustly, emerges. For the realisation of this approach, the control architecture MASSiVE has been implemented, which is used for the control of the rehabilitation robot FRIEND II. It supports task execution on the basis of a priori defined and formally verified task-knowledge. This task-knowledge contains all possible sequences of operations as well as the symbolic representation of objects required for the execution of a specific task. The seamless integration of user interactions into this task-knowledge, in combination with MASSiVE's user-adapted human–machine interface layer, enables the system to deliberately interact with the user during run-time.

Brain-Computer Interface for high-level control of rehabilitation robotic systems

“…In the context of the MASSiVE control architecture, these sub-tasks are called skills. If a problem would occur during the execution of these sub-tasks and the user has to be involved, the sequencer invokes a special user interaction skill using its interface to the HMI and the situation is resolved by the user [22]. From the sequencer's point of view, these user interaction skills are like normal skills executed by hardware components, except the fact that the user processes them.…”

A BCI-controlled robotic assistant for quadriplegic people in domestic and professional life

“…The FRIEND system is the result of more than a decade's work in the field of assistive robotics performed at the Institute of Automation from the University of Bremen in Germany. The robotic system presented in this paper is the 3rd generation of assistive robots designed at the institute, after FRIEND I [6], built in 1997, and FRIEND II [7], built in 2003. Throughout the paper, the 3rd FRIEND system will be mentioned only as FRIEND.…”

Closed-Loop Control in Image Processing for Improvement of Object Recognition

“…task planning, machine vision, motion planning, Human Machine Interface (HMI) etc. (Prenzel [2007]). Within this architecture an important role plays the Machine Vision Framework.…”

“…Then, by mapping from 3D to image plane and using a priori known dimensions of the container, the image ROI is determined. In the second case, the user of the FRIEND II system uses the HMI to select the ROI in the image (Prenzel [2007]).…”