Abstract: An image processor (1) for subjecting an image picked up by an imaging apparatus (21) to image processing to extract a specific object from the image, the image processor comprising: an image processing section (3) which subjects a plurality kinds of images (t, t?1, . . . , t?k) picked up by the imaging apparatus to the image processing based on a processing program comprising image filters (F) combined in a form of a tree structure, and which forms an output image (O) in which the specific object is extracted.

Abstract: There are equipped a first recurrent neural network formed by connecting plural nodes so as to have a loop in which the output from one node is input to another node in accordance with a predetermined coupling weight coefficient. Meanwhile, the output of at least one node is fed back to the node concerned or another node, and an optimizing unit for determining the optimum solution of the coupling weight coefficient in the first recurrent neural network based on a learning rule using a hereditary algorithm. In this case, the first recurrent neural network outputs a first parameter indicating a motion state of a vehicle based on predetermined input information, thereby functioning as a vehicle motion model.

Abstract: A tent fabric comprising a woven fabric made of yarns containing kenaf fibers in an amount of 10 wt. % or more. The tent fabric after use can easily be recycled and hence contributes to resource saving and environmental protection.

Abstract: There are equipped a first recurrent neural network formed by connecting plural nodes so as to have a loop in which the output from one node is input to another node in accordance with a predetermined coupling weight coefficient. Meanwhile, the output of at least one node is fed back to the node concerned or another node, and an optimizing unit for determining the optimum solution of the coupling weight coefficient in the first recurrent neural network based on a learning rule using a hereditary algorithm. In this case, the first recurrent neural network outputs a first parameter indicating a motion state of a vehicle based on predetermined input information, thereby functioning as a vehicle motion model.

Abstract: A tent fabric comprising a woven fabric made of yarns containing kenaf fibers in an amount of 10 wt. % or more. The tent fabric after use can easily be recycled and hence contributes to resource saving and environmental protection.

Abstract: A control apparatus and method for an autonomous traveling vehicle having a teaching mode in which a vehicle position and a vehicle azimuth in respective points on a running path are memorized and a play-back mode in which the vehicle is operated autonomously based on the vehicle position and vehicle azimuth memorized in the teaching mode comprises a virtual traction point establishing means for establishing a virtual traction point located away from a vehicle position by a specified distance in a direction of a vehicle azimuth, a current vehicle position determining means for determining a current vehicle position corresponding to the vehicle position in a play-back mode, a target azimuth calculating means for calculating a target azimuth based on a positional relationship between the current vehicle position and the virtual traction point, a vehicle steering means for steering the vehicle in a direction of the target azimuth in the play-back mode and a vehicle speed control means for controlling a vehicle s

Abstract: For an optimization system, which employs a genetic algorithm to calculate an optimal parameter that matches an evaluation condition consisting of multiple conditions, multiple GA engines 1 are provided at multiple stages, from the lowermost to the topmost, and employ a genetic algorithm to output, as gene groups PGn (n=1 to N), parameter candidates that match evaluation conditions that are individually set for the stages. Each of gene migration controllers 2 moves specific genes between a lower gene group PGn and a higher genre group PGn+1. A convergence determination unit 3 determines the convergence of an optimization based on a gene group PGN calculated by the GA engine 1 at the highest stage. In order to set the evaluation conditions for the stages, conditions are added stepwise from the lowermost to the topmost stage.

Abstract: An autonomous running control system capable of guiding a lawn-mowing work vehicle to a target point unmanned with high accuracy. Normally, the vehicle runs autonomously according to the D-GPS/dead reckoning navigation method. When the vehicle runs in an area where obstacles and ups-and-downs exists, the running control is switched to a magnetic guidance and the vehicle moves along the magnetic rail underground. When the vehicle comes into a normal operation again, the running control is shifted to the G-GPS/dead reckoning navigation method again. Further, when the vehicle comes near a target points, the running control is switched to the dead reckoning navigation method capable of guiding the vehicle accurately to the target point. When the vehicle arrives at the work area, it conducts a lawn mowing work according to the trace running control, finding the boundary between mowed and unmowed areas.

Abstract: The position of the vehicle is detected by the position information from satellites and by the correction information based on the position data of a known point. On the other hand, the position of the vehicle is found based on the running histories since the reference point. Next, the difference between the position data from satellites and the position data based on the running histories at each moment when the position data is received from satellites is calculated and those differences are averaged to obtain a correction value. Finally the current position of the vehicle is calculated by correcting the position data based on the running histories by the newest correction value. Consequently, in the autonomous running control system an accurate position of the vehicle can be found without stopping the vehicle, even when the position data from satellites does not have a sufficient accuracy. Thus, according to the present invention an efficient and accurate autonomous running can be achieved.