Abstract: According to one aspect, a method includes obtaining a first supervisory request from a first vehicle. The first supervisory request is processed by a teleoperations monitor arrangement. The method includes determining a first priority for the first supervisory request. After determining the first priority, the first supervisory request is added to a queue according to the first priority. The queue includes at least a second supervisory request having a second priority. Finally, the method includes determining whether the first priority is higher than the second priority. When it is determined that the first priority is higher than the second priority, the first supervisory request is processed before the second supervisory request. The first supervisory request is obtained from the queue and processed by the teleoperations monitor arrangement. Processing the first supervisory request includes determining whether the first vehicle is to be remotely operated by the teleoperations operator arrangement.

Abstract: According to one aspect, a method includes autonomously operating a vehicle along a first path, identifying a work zone, and determining whether the vehicle is able to continue operating along the first path after identifying the work zone. When it is determined that the vehicle is not able to continue operating along the first path, it is determined whether an autonomy system is able to identify a second path that routes around the work zone. When the autonomy system is able to identify the second path, the vehicle is autonomously operated along the second path. When the autonomy system is unable to identify the second path, the method includes requesting assistance from a teleoperations monitor arrangement. The vehicle is configured to obtain, from the teleoperations monitor arrangement, a waypoint or a first indication of a teleoperations operation arrangement assigned to remotely operate the vehicle around the work zone.

Abstract: An optical coherence tomography image system and an autofocus method thereof are provided. The autofocus method captures a reference chart at a plurality of preset diopter positions, receives an interference signal generated by the reflection of a light beam projected onto an eyeball, and analyzes the reference chart and the interference signal to obtain an analysis value and a corresponding diopter. The method compares the plurality of analysis values to obtain one meeting the standard condition as the target analysis value. According to the target analysis value and the corresponding diopter, the focusing driving device is controlled to move to the position corresponding to the diopter to complete autofocusing. Therefore, the present invention can reduce the time of autofocusing, obtain a higher shooting success rate, provide better user experience, and use a lower-order computing device to reduce costs.

Abstract: According to one aspect, a method for detecting a location from which at least one sound signal originates, includes obtaining, on a microphone array of a vehicle, the at least one sound signal from a sound source, the sound source being external to the vehicle, the vehicle having a plurality of sides. The method also includes identifying, based on at least one measure associated with the at least one sound signal as obtained on the microphone array, at least a first side of the plurality of sides as being closest to the sound source.

Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.

Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.

Abstract: According to one aspect, a method for detecting a location from which at least one sound signal originates, includes obtaining, on a microphone array of a vehicle, the at least one sound signal from a sound source, the sound source being external to the vehicle, the vehicle having a plurality of sides. The method also includes identifying, based on at least one measure associated with the at least one sound signal as obtained on the microphone array, at least a first side of the plurality of sides as being closest to the sound source.

Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.

Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.

Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.

Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.

Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.

Abstract: A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.

Abstract: Disambiguating multiple readings in language conversion is disclosed, including: receiving an input data to be converted into a set of characters comprising a symbolic representation of the input data in a target symbolic system; and using a language model that distinguishes between a first reading and a second reading of a character of the target symbolic system to determine a probability that the heteronymous character should be used to represent a corresponding portion of the input data.

Abstract: Disambiguating multiple readings in language conversion is disclosed, including: receiving an input data to be converted into a set of characters comprising a symbolic representation of the input data in a target symbolic system; and using a language model that distinguishes between a first reading and a second reading of a character of the target symbolic system to determine a probability that the heteronymous character should be used to represent a corresponding portion of the input data.