Honda Motor Co., Ltd.

Honda Giken Kogyo Kabushiki Kaisha

Carnegie Mellon University

Taku Osada

Hiroshi Hasegawa

Takeo Kanade

Takahide Yoshiike

Yasushi Okada

Yoshiaki Sakagami

Koji Kawabe

Minami Asatani

Tomoki Watabe

Tsukasa Sugino

Yuichi Yoshida

Takashi Nakayama

Akira Nagao

Jun Ishii

Shigeto Nakayama

Kensuke Ishikawa

Shintarou Fujita

Provided is a system capable of further reducing risk such as a contact between a moving body such as a vehicle and a traffic participant present around the moving body. According to an environment recognition system () of the present invention, a database () stores each of a plurality of reference symbol strings describing the state of an environmental element constituting each of a plurality of scenes assumed to be around the moving body. A first arithmetic processing element () detects a scene around the moving body and generates a symbol string describing the state of the environmental element constituting the detected scene. A second arithmetic processing element () evaluates similarity between the symbol string and each of the plurality of reference symbol strings stored in the database ().

Environment recognition system

The present invention provides an interactive device which allows quick utterance recognition results and sequential output thereof and which diminishes a recognition rate decrease even if user's utterance is divided by a short interval into frames for quick decision. The interactive device: sets a recognition section for voice recognition; performs voice recognition for the recognition section; when the voice recognition includes a key phrase, determines response actions corresponding thereto; and executes the response actions. The interactive device repeatedly updates the set recognition terminal point to a frame which is the predetermined time length ahead of the set recognition terminal point to set a plurality of recognition sections. The interactive device performs voice recognition for each recognition section.

Interactive device that recognizes input voice of a user and contents of an utterance of the user, and performs a response corresponding to the recognized contents

Disclosed is a space-saving autonomous mobile robot capable of switching two types of light irradiation appropriately. The robot includes a moving mechanism, an autonomous movement controller for controlling the moving mechanism, a self-location recognition unit for sensing a self-location of the robot, a map data storage unit for storing a map data on locations of marks, a slit light device for irradiating a detection area with slit light, an infrared device for irradiating a detection area with infrared rays, and a switch determination unit for comparing a mark-formed region and the self-location, and then, for switching between the slit light and infrared devices, based on the comparison result. Moreover, the infrared device irradiates the detection area when the self-location is within the mark-formed region, while the slit light device irradiates the detection area when the self-location is outside the mark-formed region.

Autonomous mobile robot

A polyhedron recognition system that is not easily affected by the camera position and camera range when the shape of a staircase or other polyhedron is recognized from an image obtained by photography, and that can also recognize the shape with good accuracy. In the system, predetermined regions (staircase candidate regions) within the image input from two CCD cameras are selected, and a range image is obtained stereoscopically with the two cameras, while also a candidate region upon the range image obtained based on the selected region is set, and the shape of the staircase or other polyhedron is recognized based on the set range image within the candidate region.

Polyhedron recognition system

A legged mobile robot for accurately calculating the positional relationship between a leg and an obstacle to the walking of the robot has a base body and a plurality of legs operatively connected to the base body. A vision sensor mounted on the base body captures image data containing both an image of a portion of a foot of one of the legs and an image of an obstacle in the course of robot walking. The legged mobile robot calculates the positional relationship between the leg and the obstacle from the captured image data, and walks while recognizing the positional relationship as calculated between the obstacle and the foot.

Legged mobile robot

An image line-segment extracting apparatus which in processing steps to conduct Hough transformation of a sequence of edge pixels composing an image, to plot a histogram based on Hough function values, to successively detect peaks from the histogram and to extract a plurality of line segments existing in the image, can detect the only true peaks, effectively eliminating false peaks. The process also includes a feature by which region is defined and the amount of influence of a remarkable one of the peaks in a histogram upon frequency distribution on the histogram are determined and then histogram frequency values of other peaks in the defined region are corrected according to the determined amount of influence to partially rewrite the histogram.

Image line-segment extracting apparatus

The first aspect of this invention relates to a peak data extracting device used in picture processing devices. The peak data extracting device comprises a DDA (data differential analysis) computing unit, an peak filter and a sorting unit. The computing unit gives Hough curves (sine curves) based on points to be processed on an original picture. The peak filter extracts peak data. The sorting unit sorts the peak data extracted with the noise components removed. The second aspect of this invention relates to a rotary motion recurrence formula computing device which are used in the DDA computing unit. The device computes the rotary motion formula

Growing community of inventors

Wako, Japan

Taku Osada