Abstract: This disclosure provides more effective and/or efficient techniques for determining information about a physical environment. Such techniques optionally complement or replace other techniques for determining information about a physical environment. Some techniques described herein cover switching which cameras are used to calculate a depth of a location in a physical environment. The switch may occur when current images do not have sufficient feature correlation for calculating the depth of the location. Other techniques described herein cover switching which cameras are used to obtain sufficient data for a location within a representation (e.g., a three-dimensional representation) of a physical environment. The switch may occur in response to determining that there is not sufficient data for the location.

Abstract: A processor coupled to memory is configured to receive an identification of a geographical location associated with a target specified by a user remote from a vehicle. A machine learning model is utilized to generate a representation of at least a portion of an environment surrounding the vehicle using sensor data from one or more sensors of the vehicle. At least a portion of a path to a target location corresponding to the received geographical location is calculated using the generated representation of the at least portion of the environment surrounding the vehicle. At least one command is provided to automatically navigate the vehicle based on the determined path and updated sensor data from at least a portion of the one or more sensors of the vehicle.

Abstract: A processor coupled to memory is configured to receive an identification of a geographical location associated with a target specified by a user remote from a vehicle. A machine learning model is utilized to generate a representation of at least a portion of an environment surrounding the vehicle using sensor data from one or more sensors of the vehicle. At least a portion of a path to a target location corresponding to the received geographical location is calculated using the generated representation of the at least portion of the environment surrounding the vehicle. At least one command is provided to automatically navigate the vehicle based on the determined path and updated sensor data from at least a portion of the one or more sensors of the vehicle.

Abstract: A processor coupled to memory is configured to receive an identification of a geographical location associated with a target specified by a user remote from a vehicle. A machine learning model is utilized to generate a representation of at least a portion of an environment surrounding the vehicle using sensor data from one or more sensors of the vehicle. At least a portion of a path to a target location corresponding to the received geographical location is calculated using the generated representation of the at least portion of the environment surrounding the vehicle. At least one command is provided to automatically navigate the vehicle based on the determined path and updated sensor data from at least a portion of the one or more sensors of the vehicle.

Abstract: Technology is described that includes a method of feature specification via semantic queries. The method can include the operation of obtaining a data set having an identifier for each data row and a plurality of data features for each data row. A semantic query can be received that can be applied to the dataset that is usable by a machine learning tool. A entity feature map can be supplied that has entities and associated features for use by the machine learning tool. Further, a query structure can be analyzed using the entity feature map to identify input from the dataset for the machine learning tool.

Abstract: Described are techniques to facilitate temporal features in a semantic data store. Information about lifetimes of facts in a semantic store is maintained. Even when a fact is logically deleted, a physical record is kept available. The record of a logically deleted or invalid fact has associated lifetime information. For example, valid-from and valid-to time values. The record of a fact not yet deleted may have a valid-from time value indicating when it was created, became valid, etc. Queries against the semantic store may specify a timeslice (a point in time or a time range). The lifetime information can be used to satisfy such time-specific queries. Because records are maintained after they are logically deleted, it is also possible to accurately query a past state of the semantic store. Even if such a query is run at different times, same results may be obtained.

Abstract: Described are techniques to facilitate temporal features in a semantic data store. Information about lifetimes of facts in a semantic store is maintained. Even when a fact is logically deleted, a physical record is kept available. The record of a logically deleted or invalid fact has associated lifetime information. For example, valid-from and valid-to time values. The record of a fact not yet deleted may have a valid-from time value indicating when it was created, became valid, etc. Queries against the semantic store may specify a timeslice (a point in time or a time range). The lifetime information can be used to satisfy such time-specific queries. Because records are maintained after they are logically deleted, it is also possible to accurately query a past state of the semantic store. Even if such a query is run at different times, same results may be obtained.

Abstract: Technology is described that includes a method of feature specification via semantic queries. The method can include the operation of obtaining a data set having an identifier for each data row and a plurality of data features for each data row. A semantic query can be received that can be applied to the dataset that is usable by a machine learning tool. A entity feature map can be supplied that has entities and associated features for use by the machine learning tool. Further, a query structure can be analyzed using the entity feature map to identify input from the dataset for the machine learning tool.

Abstract: An underwater substation pod (USP) adapted to collect and process the electrical outputs of an array of offshore power generating devices includes a voltage boosting transformer for combining and transmitting with increased efficiency an amplified version of the collected electrical outputs to an on shore facility. Combining the outputs and transmitting at a higher voltage reduces transmission losses and the number of cables required to transmit the electrical outputs. The USP is mounted on the seabed but operated at atmospheric pressure to accommodate standard components. The pod may be designed to include remotely controlled operation and to have a long service life since few, if any, moving parts are used. Also, the equipment may be designed to have a high degree of redundancy to provide greater reliability.

Abstract: An underwater substation pod (USP) adapted to collect and process the electrical outputs of an array of offshore power generating devices includes a voltage boosting transformer for combining and transmitting with increased efficiency an amplified version of the collected electrical outputs to an on shore facility. Combining the outputs and transmitting at a higher voltage reduces transmission losses and the number of cables required to transmit the electrical outputs. The USP is mounted on the seabed but operated at atmospheric pressure to accommodate standard components. The pod may be designed to include remotely controlled operation and to have a long service life since few, if any, moving parts are used. Also, the equipment may be designed to have a high degree of redundancy to provide greater reliability.