Honda Motor Co., Ltd.

Honda Giken Kogyo Kabushiki Kaisha

Advanced Telecommunications Research Institute International

Koji Akatsuka

Hiroshi Tsujino

Tadaaki Hasegawa

Hiroshi Uematsu

Soshi Iba

Yugo Ueda

Hiroshi Kondo

Norikazu Sugimoto

Shinichi Nagai

Atsushi Miura

Toru Takenaka

Yasushi Ikeuchi

Takamasa Koshizen

Takahiro Fujishiro

Tomoyuki Shimono

Yu Goto

Provided is a method for evaluating muscle strength characteristics of a limb based on a muscle group model including a first pair of antagonistic one-joint muscles, a second pair of antagonistic one-joint muscles, and a pair of antagonistic two-joint muscles, where the limb has a first rod having a proximal end supported by a first joint and a second rod supported on a free end of the first rod through a second joint. The method includes: measuring a maximum output of a free end of the second rod in at least one predetermined direction; measuring orbiting outputs of the free end of the second rod in all directions in the plane; and creating a hexagonal maximum output distribution corresponding to a contribution amount of each muscle of the muscle group model based on the maximum output in the predetermined direction and the orbiting outputs.

Method for evaluating muscular strength characteristics

It is possible to perform robot motor learning in a quick and stable manner using a reinforcement learning apparatus including: a first-type environment parameter obtaining unit that obtains a value of one or more first-type environment parameters; a control parameter value calculation unit that calculates a value of one or more control parameters maximizing a reward by using the value of the one or more first-type environment parameters; a control parameter value output unit that outputs the value of the one or more control parameters to the control object; a second-type environment parameter obtaining unit that obtains a value of one or more second-type environment parameters; a virtual external force calculation unit that calculates the virtual external force by using the value of the one or more second-type environment parameters; and a virtual external force output unit that outputs the virtual external force to the control object.

Reinforcement learning apparatus, control apparatus, and reinforcement learning method

A reinforcement learning system () of the present invention utilizes a value of a first value gradient function (dV/dt) in the learning performed by a second learning device (), namely in evaluating a second reward (r(t)). The first value gradient function (dV/dt) is a temporal differential of a first value function (V) which is defined according to a first reward (r(t)) obtained from an environment and is served as a learning result given by a first learning device (). An action policy which should be taken by a robot (R) to execute a task is determined based on the second reward (r(t)).

Reinforcement learning system

Disclosed is a driver-assistance vehicle including one or more lighting members which are placed within peripheral vision of a driver and which are arranged on respective sides of the vehicle. Furthermore, the driver-assistance vehicle includes a vehicle behavior sensing unit for predicting or sensing a state of the vehicle, and a light controller for controlling the lighting members, based on the sensed state. With this driver-assistance vehicle, the driver can be assisted in distributing his attention.

Driver-assistance vehicle

An object detection apparatus and method capable of detecting objects based on visual images captured by a self-moving unit. A sequential images output section makes a train of a first input image and a second input image sequential to the first input image and outputs said train. A local area image processor calculates local flows based on said first input image and said second input image. An inertia information acquiring section measures self-motion of the unit to calculate inertia information thereof. A global area image processor uses said inertia information to estimate global flow, which is a motion field of the entire view associated to the self-motion, using said global flow and said first input image and creates a predictive image of said second input image. The global area image processor then calculates differential image data, which is a difference between said predictive image and said second input image. A figure-ground segregation section uses said differential image data to refine said local flows and compares the refined local flows with a predetermined threshold value to extract a figure candidate area, which is the area having a high probability of an object existing in the input image. An object presence/absence determination section determines presence/absence of objects in said figure candidate area.

Image-based object detection apparatus and method

An image recognizing apparatus and method is provided for recognizing behavior of a mobile unit accurately with an image of external environment acquired during the mobile unit is moving. Behavior command output blockoutputs behavior commands to cause the mobile unitmove. Local feature extraction blockextracts features of local areas of the image from the image of external environment acquired on the mobile unitwhen the behavior command is output. Global feature extraction blockextracts feature of global area of the image using the features of local areas. Learning blockcalculates probability models for recognizing behavior given to the mobile unitbased on the feature of global area of the image. After learning is finished, behavior of the mobile unitmay be recognized rapidly and accurately by applying the probability models to an image of external environment acquired in mobile unitafresh.

Image recognizing apparatus and method

An object detection apparatus is provided for detecting both stationary objects and moving objects accurately from an image captured from a moving mobile unit. The object detection apparatus of the present invention applies Gabor filter to two or more input images captured by an imaging device such as CCD camera mounted on a mobile unit, and calculates optical flow of local areas in the input images. Then the object detection apparatus closely removes optical flow produced by motion of the mobile unit by estimating optical flow produced from background of the input images. In other words, the object detection apparatus clarifies the area where object is not present ('ground') in the input images. By removing such 'ground' part, the area where objects seems to be present (&#x201c;feature&#x201d;) is extracted from the input images. Finally, the object detection apparatus determines whether objects are present or not using flow information of the extracted &#x201c;feature&#x201d; part.

Growing community of inventors

Saitama, Japan

Koji Akatsuka