Robotic vision is concerned with providing, primarily through image sensory data acquisition and analysis, the basis for planning robotic manipulator actions upon and within a restricted world of solid objects. Ideally, its function should correspond to the human visual system's capacity to guide hand/eye coordination or body/eye navigation tasks. Fundamental to the notion of functionality in a 3D space partially filled with solid objects, is the requirement to appreciate the depth dimension, from a particular viewpoint. Human vision abounds with depth cues derivable from imagery and many of these have been the subjects of study for robotic vision application. However, direct range recovery using time-of-flight methods (ultrasonic or light) has distinct advantages for robotics and it is easy to justify these alternative approaches despite (and maybe even because of) their independence from visual cues.

This paper presents work in progress in the Computer Vision and Robotics Laboratory at The Australian National University towards implementing a robotic hand/eye coordination system with applicability in the scene domain of brightly coloured, simply shaped objects with relatively untextured surfaces in arbitrary 3 dimensional configurations. The advantages of using directly acquired range data (via a laser time-of-flight range scanner) in enhancing the scene segmentation phase of analysis is emphasised and fairly convincing results presented. Actual vision-driven manipulation has not yet been developed but plans towards this end are included.

A new elastic structure of a robot wrist, which exhibits a six decree of freedom flexural capability, is described. Force and compliance analysis is made, and algorithms for geometrical parameter synthesis are proposed. Owing to the technological simplicity of the designed structure, it is possible to construct cost-effective compliance devices. The intended use is to permit the assembly of close tolerance parts with industrial robots having relatively low positional accuracy. It could also be applied to other manual or automatic matching operations.

Vibrations in robot action, both in the arm control system and arm itself, and in the transported load, are a serious problem in the development of high speed systems. The paper discusses the typical causes of vibration resulting from the motion command in path controlled robots and those due to the failure of a system to meet the specified command through power and performance limitations. Experimental results illustrating such phenomena are presented. Methods of reducing the magnitude or occurrence of such vibrations through the improved design of motion commands, which take account of the vibratory nature of the system and load, are presented.

A learning algorithm for the inference of sequential machines from input/output behaviour is developed. The construction of the models is sequentially achieved by processing input/output (i/o) sequences, and through an induction-contradiction-discrimination scheme. The various states are discriminated after the discovery of contradictory i/o sequences. The properties of the inferred machines and some reported experiments indicate the efficiency of the learning concept of contradiction for this application. Possible application in Robotics for the learning of assembling models is also mentioned.

The tactile sensor is constructed as a part of the finger of a parallel jaw hand; it is of the size of a finger and allows for a large displacement of the sensor element in response to force. The structure of the tactile sensor incorporates 20 successively and closely aligned elements, which allow for a 2.5 mm maximum displacement for each element. In the described experiments we present the capabilities of the tactile sensor. The tactile sensor has the functions of: 1) discriminating the shape of the partial surface of an object; and 2) tracing by finger on the surface along the profile of an object.

Taylor Hitec Ltd are active in the field of inventive design and successful construction of unique robotic implements for remote working in nuclear power plant and associated waste processing. The company has widened its operation and expertise to provide a concept-to-commission service in consultant and applications engineering for the introduction of robots and FMS in manufacturing and process industries. In the profile presented here are some examples of the manipulators produced by the company and their technical evolution, together with an outline of the successful widening of business into the fields of industrial robotics and flexible manufacturing systems.

A curvilinear robot constructed from a number of modular flexible sections of fixed length and diameter but independently controlled radius and direction of curvature has been equipped with an optical fibre image guide transmitting images from between the gripper jaws to the remote TV camera of Microvision-100, a microcomputer controlled real-time DMA-based vision System that is easily trained to recognise the shape, position and orientation of components. The gripper position and orientation is controlled by feedback from the vision System, the action taken depending on component recognition and inspection for defects. Redundant degrees of freedom enable the curvilinear robot to avoid obstacles and work in confined spaces.

The author makes the point that progress is slow, though inexorable, and one can discern an upward drift of unemployment, even in good times. After analysing the various views concerning this phenomenon, the author points to two major problems, viz. the transitional one of the redundant heavy manual worker and the long-term one of employment for the unskilled. He then considers these problems from the point of view of automation and robotics with particular reference to the reaction of the human society to the qualitative changes in the manufacturing industries.

This paper presents an intelligent robot vision system using TOSPIX which has been newly developed to realize frequently-used and time-consuming image processing functions at low-cost and high-speed. The vision system has been studied for use in observing surface information about electric parts (dry batteries), inspecting them and then placing good ones into a given box. Three major robot vision functions are implemented here: object recognition, inspection and position determination by binary and gray-scale image processing techniques. While binary image techniques are used in battery terminal inspection and box position determination gray-scale image processing functions are performed in a label pattern check on a battery surface, front or rear surface determination, and surface defect inspection.

We discuss the use of fuzzy set based methodologies as a tool for helping robots develop and implement plans. We are particularly concerned with matching fuzzily described states with fuzzy antecedents in production rules.

Minimum distance algorithms allow users of robot simulation programs to maneuver manipulation arms around and between workspace obstacles. Additionally, they can be used to generate configuration maps for path planning of the manipulator “point” through a more abstract configuration space. This paper summarizes an algorithm for determining minimum distances between two polyhedral elements. Examples of configuration space maps and Cartesian stepping techniques demonstrate algorithmic utility for robot path planning. A number of accelerating strategies which depend on a heirarchical spatial representation of manipulator and workspace elements maintain reasonable CPU times for the simulation user.

This note describes a new class of devices, corrugated polyvinylidene fluoride bimorphs. It describes the fabrication, testing and analysis of one simple configuration and discusses the general potential of the devices. As actuators, they offer promise for applications involving relatively large amplitude displacements and small forces with ease of control. As tactile sensors, the devices offer considerable promise due to their potentially high resolution, selectable compliance, sensitivity and durability.