A vehicle which is capable of recognizing shapes in a predetermined area, comprising: a plurality of ultrasonic sensors, an encoder, map drawing means for sequentially and continuously drawing a map of the prescribed area determined by information received from the encoder and ultrasonic sensors, memory means for storing the map drawn by the map drawing means and control means for instructing rectilinear movement, starting stopping and turning of the vehicle so as to move in a serpentine fashion, wherein the ultrasonic sensors, encoder and map drawing means are operated by the control means, the memory means writes and stores a history of its own movements in the area and as information is received remembers detected information from the encoder, and a change of direction of the vehicle which is instructed by the control means is determined by information on the map as well as the areas through which the vehicle has previously passed.
Different bonus values and penalty values are allotted for each partial task of the unit such as, for example, drive from A to B, hold your positional uncertainty below a specific threshold, or draw up a map of the surroundings and add landmarks to it. Performance weightings for the individual tasks are yielded, in conjunction with a need to carry the latter out, after analysis of the bonus values and penalty values, and are evaluated in a control unit. Furthermore, in the context of the method a local planning horizon is specified in which the surroundings of the unit are subdivided into grid cells. Preferred directions, which lead the unit by the shortest path to already known or unconfirmed landmarks are stored for these grid cells, with the aim of reducing the positional uncertainty, or of being able to confirm a landmark. All the different routes which are possible within the framework of this grid are then investigated as to what contribution they make to enable the unit to reach the goal. In this process, the different costs and benefits per partial task are added up along each path. That route is selected which has the greatest benefit or the lowest loss. Finally, a destination which is situated outside the local planning horizon is reached by carrying out the method cyclically.
Light detection apparatus for determining the location of a body within a predetermined area comprises at least two light detecting devices (10,10',10"), supported on the body and capable of receiving light at points which are spaced about a central axis (8). The apparatus further includes means for supplying information representative of the level of light detected by each light detecting device (10, 10', 10"). Information received from the light detection apparatus is compared with information previously received from the light detection apparatus and stored in a memory so as to identify when the light detected by the light detection apparatus is the same or substantially the same as light previously detected by the light detection apparatus. When used on an autonomous vehicle, this can allow the vehicle to determine when it has returned to a similar position in an area. The received light signals can be filtered or processed to derive information representative of different types of light (natural, incandescent) or colours of light.
The present invention relates to an apparatus and method for recognizing self-position employing a virtual map divided into directional reflex distance data and cell unit, and a computer-readable recording medium for recording a program containing the method of the invention. The apparatus for recognizing self-position in a robot system includes: a reflex distance detecting unit for outputting a designated signal to each direction obtained by equally dividing 360.degree. as designated, detecting a point where the outputted signal reaches a designated object by using the signal reflected and inputted, and based on the detection result, detecting the distance to the object in each direction; direction detecting unit for providing information of absolute direction; and, controlling unit for controlling general operation of the reflex distance detecting unit and the direction detecting unit, dividing the region on a virtual map into a cell unit to generate directional reflex distance information per cell, and recognizing the present position by comparing the directional reflex distance information of each cell with the directional reflex distance information from the present position of a detected robot.
A cleaning robot is operable in either a cord mode (by means of a plugged-in cord) or a cordless mode (by means of a battery). The robot includes a self-propulsion mechanism for advancing the robot during a cleaning operation, and a cord that can be plugged into an external power supply for powering the cleaning device and self-propulsion mechanism and a vacuuming mechanism during the cleaning operation. Following the cleaning operation, the vacuuming mechanism is deactivated, and the self-propulsion mechanism is powered by a battery carried by the robot for advancing the robot to the next area to be cleaned.
Portable threshold locators (32B, 32C, 32D) are placed in a room (120) at locations to define at least part of a boundary within which an autonomous vehicular appliance is to be confined. Typically, the threshold locator is placed in a doorway (32B) or at the top of a staircase (32D). The vehicle has a detection system which allows the autonomous vehicular appliance to detect the presence of the portable threshold locator. The detection system receives a signal from the threshold locator and the autonomous vehicular appliance uses the received signal to avoid the threshold marked by the locator (32B, 32C, 32D). The autonomous vehicular appliance is preferably a robotic floor cleaning appliance, such as a robotic vacuum cleaner.
