摘要:
An autonomous mobile body includes a storage unit arranged to store a size D2 of the autonomous mobile body, a laser range sensor arranged to acquire obstacle information, an obstacle identification unit arranged to identify, based on the acquired obstacle information, edge points indicating positions of both ends of a region in which an interfering obstacle exists, the both ends being both ends on a plane parallel or substantially parallel to a passage plane in a direction which is perpendicular or substantially perpendicular to a moving target direction of the autonomous mobile body, a direction setting unit arranged to set a pull-off direction based on the size D2 of the autonomous mobile body and the edge points, and a mobile controller arranged and programmed to control the autonomous mobile body to move toward the pull-off direction.
摘要:
An autonomous mobile device that moves while autonomously avoiding zones into which entry should be avoided even if no obstacle exists therein includes a laser range finder that acquires peripheral obstacle information, a storage unit that stores an environment map that shows an obstacle zone where an obstacle exists, and a no-entry zone map which shows a no-entry zone into which entry is prohibited, a self-location estimation unit that estimates the self-location of a host device by using the obstacle information acquired by the laser range finder and the environment map, and a travel control unit that controls the host device to autonomously travel to the destination by avoiding the obstacle zone and the no-entry zone based on the estimated self-location, the environment map, and the no-entry zone map.
摘要:
An autonomous mobile device is capable of taking action that is suitable to execute a task in accordance with a given situation includes and executes a predetermined task upon autonomously moving to a destination. The autonomous mobile device includes a storage unit that stores an environment map, a laser range finder that acquires peripheral obstacle information, an unknown information identification unit that identifies unknown obstacle information from the peripheral obstacle information, an assessment information acquisition unit that acquires a plurality of types of assessment information including movement information, relative position information, and attribute information that are related to the unknown obstacle, when the unknown obstacle information is identified, and a scenario selection unit that selects, based on the assessment information, one action scenario among a plurality of action scenarios including an action scenario which is defined to execute the task and is other than an action scenario to cancel or continue the execution of the task.
摘要:
An environmental map correction device that acquires an environmental map that matches an actual ambient environment includes a conversion unit arranged to convert object existence probability information of respective grids configuring a global map into image information (shading information of a black and white image), a display unit arranged to display a global map image based on the converted image information, an operation input unit arranged to receive a correcting operation from a user, a correction unit arranged to correct the global map image displayed by the display unit according to the correcting operation by the user, and an inversion unit arranged to acquire a corrected global map by inverting the corrected global map image (shading information) into the object existence probability information.
摘要:
An autonomous mobile body includes a laser range sensor and an electronic control device. The electronic control device includes a storage unit that stores a size D2 of the autonomous mobile body, a width identification unit that identifies a spatial size D1 in a width direction of a passage which is a region where the autonomous mobile body can move, a calculation unit that calculates a size 8 of an interfering obstacle in a direction which is substantially perpendicular to a moving target direction on a road surface based on obstacle information, an action selection unit that selects a stopping action or a retreat action based on the spatial size D1, the size D2 of the autonomous mobile body, and the size D8 of the interfering obstacle, and a mobile control unit that controls the autonomous mobile body to stop when the stopping action is selected and control the autonomous mobile body to retreat when the retreat action is selected.
摘要:
According to one embodiment, an image processing apparatus connected to an external memory and a cache memory. The apparatus includes a counter, a coordinate calculator, a tag checker, a pixel referring module, a pixel value calculator and an outputting module. The counter determines a converted coordinate according to a predetermined execution sequence. The coordinate calculator calculates a unconverted coordinate used to calculate a converted pixel value located at the converted coordinate. The tag checker generates a conversion request to calculate the converted pixel value with reference to an unconverted pixel located at the unconverted coordinate. The pixel referring module reads the unconverted pixel from the cache memory based on the conversion request when the unconverted pixel is stored in the cache memory. The pixel value calculator calculates the converted pixel value with reference to the read unconverted pixel. The outputting module writes the converted pixel having the calculated converted pixel value into the external memory.
摘要:
According to one embodiment, an image processing apparatus connected to an external memory and a cache memory. The apparatus includes a counter, a coordinate calculator, a tag checker, a pixel referring module, a pixel value calculator and an outputting module. The counter determines a converted coordinate according to a predetermined execution sequence. The coordinate calculator calculates a unconverted coordinate used to calculate a converted pixel value located at the converted coordinate. The tag checker generates a conversion request to calculate the converted pixel value with reference to an unconverted pixel located at the unconverted coordinate. The pixel referring module reads the unconverted pixel from the cache memory based on the conversion request when the unconverted pixel is stored in the cache memory. The pixel value calculator calculates the converted pixel value with reference to the read unconverted pixel. The outputting module writes the converted pixel having the calculated converted pixel value into the external memory.
摘要:
A compound semiconductor epitaxial substrate having a pseudomorphic high electron mobility field effect transistor structure including an InGaAs layer as a strained channel layer and an AlGaAs layer containing n type impurities as a front side electron-donating layer, wherein said substrate contains an InGaP layer in an orderly state on the front side of the above described InGaAs layer as the strained channel layer.
摘要:
An environmental map correction device that acquires an environmental map that matches an actual ambient environment includes a conversion unit arranged to convert object existence probability information of respective grids configuring a global map into image information (shading information of a black and white image, a display unit arranged to display a global map image based on the converted image information, an operation input unit arranged to receive a correcting operation from a user, a correction unit arranged to correct the global map image displayed by the display unit according to the correcting operation by the user, and an inversion unit arranged to acquire a corrected global map by inverting the corrected global map image (shading information) into the object existence probability information.
摘要:
An obstacle tracking apparatus includes an image input unit which acquires image sequences; an obstacle detector which detects candidate areas of an obstacle at a current time from the image sequences; a state hypothesis storage which stores a state hypothesis group including at least one state hypothesis of the obstacle at a previous time; an measurement hypothesis generator which generates a measurement hypothesis group including at least one measurement hypothesis obtained by combining measurement hypotheses for the respective positions of candidate areas of the obstacle and a measurement hypothesis in case the obstacle is not detected; a likelihood calculator which calculates likelihoods of respective combinations of the respective state hypotheses included in the state hypothesis group and the respective measurement hypotheses included in the measurement hypothesis group; a state hypothesis updater which obtains a highest likelihood from the likelihoods of the respective combinations and updates the state hypotheses at the previous time stored in the state hypothesis storage using the state hypothesis group at the current time as the state hypothesis group having the highest likelihood; and a hypothesis selector which selects the state hypothesis having the highest likelihood from the state hypothesis group at the current time as a state in which the obstacle is detected.