Knowledge-based Robotics Research Articles

What to buy, Pepper? – Bridging the Physical and the Digital World with Recommendations from Humanoid Robots

ABSTRACT While e-commerce has flourished in the past decades, brick-and-mortar retail stores face increasing challenges in attracting customers. Prior research indicates that humanoid robots may constitute a promising means to counteract this development. However, their capability to acquire and make use of rich information from the physical world (e.g. regarding customers’ physical characteristics) in combination with knowledge from (online) databases has not been adequately exploited yet. Thus, we aim at bringing together the best of the physical and the digital world by supplementing the traditional consultation process in brick-and-mortar retail stores with humanoid robots. Following a design-oriented approach, we propose a novel knowledge-based humanoid robot recommender process. We demonstrate our approach in cooperation with an optician and evaluate it using a customer survey and expert interviews. Results show that the approach achieves the design objectives and yields high customer satisfaction.

A Knowledge-Based Industrial Robot Selection System for Manufacturing Industries

Nowadays, robots can be used for different applications and environment. The capabilities and specification of the robot will determine its usage. The large number of the robot in the market has made the selection of the suitable robot becoming difficult. This paper presents the development of knowledge-based system for robot selection using expert system shell. The aim of the work is to select the suitable industry robot for manufacturing industry. The selection criteria are based upon application, payload, maximum reach, number of axes, repeatability and mounting position. The system consists of several modules such as knowledge acquisition module, inference engine module and user interface module. The development system helps the industrial engineers to select the most appropriate robot for an application.

A Knowledge-Based Robot Searching for an Unpredictable Goal under Unknown Environment

This paper describes a knowledge-based robot that explores an unknown environment for an unpredictable goal. Distinguishing characteristics of such environments for robotic navigation are that the goal's position is unpredictable and some obstacles cannot be sensed directly. Considering such features we propose a search algorithm for finding the goal and a simplified DPLL to allow robotic reasoning. Moreover we demonstrate the completeness and the execution cost of the search algorithm and also support the completeness and soundness of the simplified DPLL. The set memory rules allow for computer processing limitations. In addition, the simulation results of randomly produced environments demonstrate the completeness, soundness and effectiveness of method.

Knowledge-based robotics†

A major hurdle in the development of intelligent robots is that we still do not possess efficient computational and representational methodologies for emulating knowledge and expectation driven behaviour so basic to human cognition and problem solving. Even if we use techniques such as geometric modelling for representing objects in the robot world, we are still lacking in methods for linking such representations with sensory feedback. In this paper, we have proposed the use of intermediate representations—we call them sensor-tuned representations—for linking CSG based solid modelling with sensory information. We also discuss how sensor-tuned representations are constructed from range data and how object recognition can be done with sensor-tuned representations. Finally, we show results of manipulation experiments produced by the current implementation of the system.

Fuzziness in knowledge-based robotics systems

This paper addresses how fuzziness is employed in a robotics system, for the purposes of object representation, object or feature location and as a means of representing actions performed on objects. Many, perhaps most, robotics systems do not take advantage of either regular data bases nor Solid Geometry data bases. This paper describes a robotic system which would use a multi-modal representation knowledge base (KB). The focus of the present paper is on the use of fuzziness in this robotic system. Keyboard entered natural language phrases would be used by a human user of the robot. The robot system would, in practice, translate these phrases into executable commands and coordinates. There are several points of departure that would be employed and the first of these is the use of ‘fuzzy descriptions’ rather than the conventional binary distinctive feature matrix (such as SHRDLU) or a point cluster approach. A fuzzy descriptor is a generalization of a geometric description of an object from the system's geometric data base. How the fuzzy descriptor works is described. Object or (geometric) feature location is handled by means of extrapolating the object description method. Named concrete or specific coordinate locations, or named abstract locations which involve a range of coordinates, are used to do this; by means of the familiar ‘linguistic variable’ which we all use in everyday speech. Some means whereby this is done is explained. The user of this robotic system may semantically attach linguistic variables to a fuzzy mapping of knowledge base object descriptions. The paper provides some details as to how a robotic system might be operated in an ‘action abstraction’ mode.