Fast Transformations to Provide Simple Geometric Models of Moving Objects

Abstract

Models are compared for use with a sensor system working in real time (in this case a simple image processing system). A static robot work-cell is modelled as several solid polyhedra. This model is updated as new objects enter or leave the workplace. Similar 2-D slices in joint space, and spheres and simple polhedra are used to model these objects. The three models are compared for their ability to be updated with new information and for the efficiency of the whole system in accessing data concerning new objects. The system supplies data to a "Path Planner" containing a geometric model of the static environment and a robot. The robot structure is modelled as connected cylinders and spheres and the range of motion is quantised.

Introducing dead bands within two-dimensional clusters of user data to improve data classification

“…The work used a keyboard and mouse but on-going research is experimenting with different sensors [14,15] and user interfaces [ 16,17] such as joysticks [18][19][20][21][22][23] and the use of Al is being trialed [24][25][26][27][28][29][30][31][32], using Blackboard systems [33,34], ANNs [35][36][37] and fuzzy systems [38][39][40][41] with a view to improving the gathering of user data and identification of correlations between relevance ratings for WWW pages and their actual perceived usefulness. The methods are also being introduced to a simulation based robot command library [42].…”

Rule-Based System to Assist a Tele-Operator with Driving a Mobile Robot

“…This paper presents a method that partly optimises a minimum-cost route to a target destination. Speed is mostly regulated by the movement of a joystick, but input from a path suggested by simple AI systems [12][13][14][15] is also considered. The straightforward and quick reasoning uses perception based rules that are comparable to some presented by Parhi & Singh for an autonomous mobile robot [1].…”

Rule-based system to assist a powered wheelchair driver

“…Research described in this paper presents techniques to partly optimise minimum-cost routes towards a destination. A joystick mostly regulates speed and direction, but a simple AI system also provides and input [14][15][16][17]. Perception based rules are used that are similar to those used by Sanders in [35] and Parhi & Singh in [3].…”