scispace - formally typeset
Search or ask a question

Showing papers on "Social robot published in 1984"


Journal ArticleDOI
TL;DR: A procedure for locating an autonomous robot vehicle in a three-dimensional space is described, an extension of a two-dimensional technique described by Fukui that provides the unique three- dimensional position of the robot relative to a standard mark.

68 citations


Patent
04 Jan 1984
TL;DR: A control system for a mobile robot includes operation means for calculating an instantaneous position of the robot, storage means for sequentially storing data representative of the respective robot positions, and means for studying and storing a rangewhich the robot is to travel, and calculating a running pattern of a running robot in a specific range.
Abstract: A control system for a mobile robot includes operation means for calculating an instantaneous position of the robot, storage means for sequentially storing data representative of the respective robot positions, means for studying and storing a rangewhich the robot is to travel, and means for calculating a running pattern of the robot in the specific range. The robot is allowed to travel thrpughly in the range without leaving any region non-travelled, while checking its own position.

44 citations



Journal ArticleDOI
01 Jan 1984-Robotica
TL;DR: A hierarchical robot sensory system being developed for industrial robotics is described, where at each level of the hicrarchy, sensory intcrpretativc processes are guided by exl~cctancy-enc crating modeling processes.
Abstract: A hierarchical robot sensory system being developed for industrial robotics is described. At each level of the hierarchy, sensory interpretative processes are guided by expectancy-generating modeling processes. The modeling processes are driven by a priori knowledge (object prototypes), by knowledge of the robot's movements (feed-forward from the control system), and by feedback from the interpretative processes (prior state of the sensory world). At the lowest level, the senses (vision, proximity, tactile, force, joint angle, etc.) are handled separately; above this level, they are integrated into a multi-model world model. At successively higher levels, the interpretative and modeling processes describe the world with successively higher order constructs, and over successively longer time periods. Each level of the modeling hierarchy provides output, in parallel, to guide the corresponding levels of a hierarchical robot control system.

27 citations


Patent
20 Jun 1984
TL;DR: In this article, a cellular type robot apparatus consisting of a plurality of cellular robots (11-34) each having intelligence where each cellular robot can control the operation of its own on the basis of information exchange with adjacent cellular robots, the operations of the cellular robots are as a whole coordinated, and each robot can be controlled without the necessity of change of hard-and softwares even when a part of cellular robot is out of order or is expanded.
Abstract: This invention relates to a cellular type robot apparatus consisting of a plurality of cellular robots (11-34) each having intelligence wherein each cellular robot controls the operation of its own on the basis of information exchange with adjacent cellular robots, the operations of the cellular robots are as a whole coordinated, and each cellular robot can be controlled without the necessity of change of hard- and softwares even when a part of cellular robots is out of order or is expanded. Each cellular robot can be increased or decreased in a building block arrangement. More definitely, each cellular robot has arms corresponding to hands and feet, can control the operation by itself. As the cellular robots are connected and combined through transmission routes so as to exchange information, they can operate cooperatively as a group of cellular robots. The operation of the group of cellular robots is to constitute the shape of a predetermined pattern besides the operations of entwining an object, and gripping and moving the object.

27 citations


01 Apr 1984
TL;DR: The Neptune is a tethered vehicle built for autonomous mobile robot research as discussed by the authors, and the design considerations, resulting design, and details of the mechanical structure and electrical control system are described in detail.
Abstract: : Neptune is a tethered vehicle built for autonomous mobile robot research. Included are: the design considerations, the resulting design, and details of the mechanical structure and electrical control system. Detail is sufficient to enable replication or adaptation by others. A discussion of the performance with respect to the design considerations is also included. (Author).

20 citations


Patent
06 Nov 1984
TL;DR: In this article, a pneumatic control circuit that enables a user to position the robot's gripper arm at positions intermediate of fully up and fully down is presented. But it does not specify a set of safety switches that encourage a user, when near the robot, to keep a hand on the robot so as not to be accidentally injured by its motion.
Abstract: A robotic cell, or work area, especially useful for education. The cell has a plurality of interchangable work surfaces for mounting objects that the robot manipulates. Students, researchers, or other workers can thus set up separate experiments that need not be torn down each time a different user begins work with the cell. The cell has safety switches that encourage a user, when near the robot, to keep a hand on the robot so as not to be accidentally injured by the robot's motion. There is also a dead man switch effective to disenable the robot entirely, after a short time delay. The cell has a pneumatic control circuit that enables a user to position the robot's gripper arm at positions intermediate of fully up and fully down.

18 citations



Patent
13 Apr 1984

13 citations


Journal ArticleDOI
TL;DR: It is revealed that COSMOS, the Cognitive Sensor Motor Operations Study, is investigating "cognitive sensor motor operations Study" with a focus on self-driving cars.
Abstract: 本論文は, 知能ロボット研究用に開発したプログラミングシステムCOSMOSについて述べたものである.COSMOSは, Cognitive Sensor Motor Operations Studyの略称である.高水準のロボット言語, ロボットアームとそのコントローラ, 3次元視覚機能敏感な触覚センサ, および, ユーザインターフェイスより構成される.ホストのミニコンピュータとマイクロコンピュータはGPIBで結合され, 基本ロボットコマンドによって交信している.システムは階層構造をとっており, ハードウエア, ソフトウエアともにモジュール化および拡張性が重視された設計になっている.逐次, 人工知能の手法を組み込んでゆくため, システムのソフトウエアの主な部分はLispで記述されている.本論文ではロボット言語AL/L (Assembly Language in Lisp) とその環境モデル管理システム, ロボットソフトウエアの構成およびタブレットを用いた教示システムについて述べる.ロボット言語の処理系では, 環境モデルの管理が重要な役割を占めていることが明らかになった.また, システムを用いた実験を通して, タブレットが教示用デバイスとして優れていること, およびCOSMOSのロボットプログラミングシステムとしての有効性が確認された.

8 citations



Journal ArticleDOI
TL;DR: This article describes a sensor-based obstruction avoidance technique that, if implemented on the on-board computer of a mobile robot, would enable the robot to move through an unknown environment.
Abstract: This article describes a sensor-based obstruction avoidance technique. This technique, if implemented on the on-board computer of a mobile robot, would enable the robot to move through an unknown environment. The proposed approach is driven by sensory data. The robot thus senses and adapts to the changes in the environment. The software also does path planning. As more information about the environment is obtained the robot's path planning capabilities improve. Illustrative examples are used to describe the algorithms.





01 Jan 1984
TL;DR: Attention is given to mode locked lasers in modulation rangefinders, advanced architectures for factory vision, hierarchical contour coding and generalization of shape, problems in three-dimensional imaging, and an adaptive gas metal arc welder.
Abstract: Aspects of pattern recognition for intelligent robots are discussed, taking into account linear algebra based object recognition algorithms for computer vision, planar object recognition by the computer vision method, real time textured-image segmentation based on noncausal Markovian random field models, model driven vision to control a surface finishing robot, robotic acquisition of jumbled parts from bins by visual and tactile guidance, and imaging using eddy current sensors. Other subjects explored are related to curved object recognition for robot vision, robot image understanding, robot applications, three-dimensional measurements for robot vision, robot vision, tactile and multirobot sensors, and precision robot vision measurements. Attention is given to mode locked lasers in modulation rangefinders, advanced architectures for factory vision, hierarchical contour coding and generalization of shape, problems in three-dimensional imaging, a vision system to identify car body types for a spray painting robot, and an adaptive gas metal arc welder.


Journal ArticleDOI
Masakatsu G. Fujie1, Taro Iwamoto1, Koji Kamejima1, Yuuji Hosoda1, Yoshiyuki Nakano1 
TL;DR: In this paper, an active adaptive crawler mechanism and a visual navigating system were developed to achieve practical speed for industrial use of the mobile robot, using a crawler-type mechanism to maintain vehicle stability and achieves good climbing capability without increasing weight.
Abstract: Recently, great advances have been made in intelligent mobile robot technology, advances which will provide autonomous travelling ability to robots, allowing them to surmount stairs and other obstacles. In this paper, we present an active adaptive crawler mechanism and a visual navigating system, developed to achieve practical speed for industrial use of the mobile robot. By using a crawler-type mechanism, the active adaptive suspension mechanism maintains vehicle stability and achieves good climbing capability without increasing weight. Further, we have developed technology for an intelligent navigating mechanism, to guide the robot as it passes through a building. Once the robot is provided with an inner layout plan of the respective building, it can achieve practical mobile speed for industrial use.

Book
01 Jan 1984

Proceedings ArticleDOI
01 Mar 1984
TL;DR: This paper describes a robot assembly system in which the robot is taught the steps in the new plan using natural language input.
Abstract: Robots are increasingly being used in situations requiring them to exhibit flexible behavior. In such situations point-to-point motion sequences are inadequate. Instead, robots will probably use planning mechanisms, coupled with sensors of various kinds, to carry out their tasks. Such mechanisms allow robots to perform in situations where object position cannot be exactly specified in advance and in which unanticipated events can occur. One alternative is to teach the robot new plans. This paper describes a robot assembly system in which the robot is taught the steps in the new plan using natural language input.

Proceedings ArticleDOI
01 Jan 1984
TL;DR: The resulting system is specific to a single robot, it is expandable and adaptable to other robot families, and its software provides a structure which allows the system to be tailored to specific needs.
Abstract: A significant problem in both educational and industrial systems is access to development systems. Universities typically have neither funds nor space for a broad variety of industrial robots. Few manufacturing concerns can afford the luxury of robots dedicated to system development and training.An alternative to industrial robots is a physical simulation system. This system should include a robot capable of a broad range of motions and a controller capable of emulating robot controllers. The key to this system is its software, which provides a structure which allows the system to be tailored to specific needs.Such a system is a large undertaking. This report describes a beginning in developing this system. While the resulting system is specific to a single robot, it is expandable and adaptable to other robot families.


Proceedings ArticleDOI
01 Jan 1984
TL;DR: A robot sensory system developed for industrial robotics is described, which uses knowledge of object prototypes, and of robot action, to generate visual expectancies for each frame.
Abstract: A robot sensory system developed for industrial robotics is described. Television frames and inputs from other sensors are interpreted by a hierarchically organized group of microprocessors. The system uses knowledge of object prototypes, and of robot action, to generate visual expectancies for each frame. At each level of the hierarchy, interpretative processes are guided by expectancy-generating modeling processes. The modeling processes are driven by a priori knowledge, by knowledge of the robot's movements, and by feedback from the interpretative processes. At the lowest level, other senses (proximity, tactile, force) are handled separately; above this level, they are integrated with vision into a multi-modal world model. At successively higher levels, the interpretative and modeling processes describe the world with successively higher order constructs, and over longer time periods. All levels of the hierarchy provide output, in parallel, to guide corresponding levels of a hierarchical robot control system.

Book ChapterDOI
01 Jan 1984