Module for underwater remotely operated vehicles

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling a remotely operated vehicle (ROV) for performing an underwater task. One apparatus includes a watertight housing; a mounting hardware that attaches the watertight housing to the ROV; one or more sensors in the watertight housing, the one or more sensors configured to generate sensor data that is associated with an underwater task; and one or more processors in the watertight housing, the one or more processors configured to: receive the sensor data from the one or more sensors; generate a navigation plan for the ROV using the sensor data; determine, using the navigation plan, control instructions configured to control the ROV to perform the underwater task; and provide the control instructions to an interface of the ROV configured to communicate with the apparatus.

What is claimed is: 
     
         1 . An apparatus configured to attach to a remotely operated vehicle (ROV), the apparatus comprising:
 a watertight housing;   a mounting hardware that attaches the watertight housing to the ROV;   one or more sensors in the watertight housing, the one or more sensors configured to generate sensor data that is associated with an underwater task; and   one or more processors in the watertight housing, the one or more processors configured to:
 receive the sensor data from the one or more sensors; 
 generate a navigation plan for the ROV using the sensor data; 
 determine, using the navigation plan, control instructions configured to control the ROV to perform the underwater task; and 
 provide the control instructions to an interface of the ROV configured to communicate with the apparatus. 
   
     
     
         2 . The apparatus of  claim 1 , wherein the one or more processors comprise a graphics processing unit configured to process the sensor data using a machine learning algorithm. 
     
     
         3 . The apparatus of  claim 1 , comprising a machine learning engine trained generate a result of one or more computer vision tasks based on input indicative of the sensor data. 
     
     
         4 . The apparatus of  claim 1 , wherein the mounting hardware comprises at least one of a clamping system, a screwing system, or a magnetic system. 
     
     
         5 . The apparatus of  claim 1 , wherein the ROV is untethered to any surface vessel. 
     
     
         6 . The apparatus of  claim 1 , wherein the one or more sensors are customized for the apparatus in accordance with the underwater task. 
     
     
         7 . The apparatus of  claim 1 , comprising a communication engine configured to communicate with a surface vessel or another ROV. 
     
     
         8 . The apparatus of  claim 1 , wherein the one or more processors are configured to generate the navigation plan for the ROV using the sensor data by fusing the sensor data obtained from multiple sensors. 
     
     
         9 . The apparatus of  claim 1 , wherein the interface of the ROV comprises an application programming interface (API) through which the ROV receives control instructions. 
     
     
         10 . A computer-implemented method, comprising:
 receiving sensor data from one or more sensors included in an apparatus, wherein the apparatus is configured to attach to a remotely operated vehicle (ROV), wherein the one or more sensors is in a watertight housing and is configured to generate sensor data that is associated with an underwater task, wherein a mounting hardware attaches the watertight housing to the ROV;   generating a navigation plan for the ROV using the sensor data;   determining, using the navigation plan, control instructions configured to control the ROV to perform the underwater task; and   providing the control instructions to an interface of the ROV configured to communicate with the apparatus.   
     
     
         11 . The method of  claim 10 , comprising: processing, by a graphics processing unit, the sensor data using a machine learning algorithm. 
     
     
         12 . The method of  claim 10 , comprising: generating, by a machine learning engine, a result of one or more computer vision tasks based on input indicative of the sensor data. 
     
     
         13 . The method of  claim 10 , wherein the mounting hardware comprises at least one of a clamping system, a screwing system, or a magnetic system. 
     
     
         14 . The method of  claim 10 , wherein the ROV is untethered to any surface vessel. 
     
     
         15 . The method of  claim 10 , wherein the one or more sensors are customized for the apparatus in accordance with the underwater task. 
     
     
         16 . The method of  claim 10 , wherein the apparatus comprises a communication engine configured to communicate with a surface vessel or another ROV. 
     
     
         17 . The method of  claim 10 , wherein generating the navigation plan for the ROV using the sensor data comprises fusing the sensor data obtained from multiple sensors to generate the navigation plan. 
     
     
         18 . The method of  claim 10 , wherein the interface of the ROV comprises an application programming interface (API) through which the ROV receives control instructions. 
     
     
         19 . A system comprising one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
 receiving sensor data from one or more sensors included in an apparatus, wherein the apparatus is configured to attach to a remotely operated vehicle (ROV), wherein the one or more sensors is in a watertight housing and is configured to generate sensor data that is associated with an underwater task, wherein a mounting hardware attaches the watertight housing to the ROV;   generating a navigation plan for the ROV using the sensor data;   determining, using the navigation plan, control instructions configured to control the ROV to perform the underwater task; and   providing the control instructions to an interface of the ROV configured to communicate with the apparatus.   
     
     
         20 . The system of  claim 19 , the operations comprise: processing, by a graphics processing unit, the sensor data using a machine learning algorithm.