Apparatuses, methods, and systems for supervising remotely operated vehicles over sparse datalinks

A non-transitory machine-readable storage medium containing machine-executable instructions for performing a method of operating a remotely operated vehicle (ROV) to perform a task over a communications network containing at least one sparse datalink, wherein the at least one sparse datalink has at least one of 1) a bandwidth that is narrower than the bandwidth needed for one or more remote operators to supervise the ROV so that it successfully performs the task and 2) a latency that is higher than the maximum latency tolerable for being able to successfully perform the task, and wherein the communications network has a remote operator side and an ROV side, the method comprising:

• receiving, on the ROV side of the communications network, a remote supervisory command over the communications network from the remote operator side of the communications network, wherein the remote supervisory command is a high-level objective-based instruction requiring context of task, purpose, and desired end state and is a command for the ROV to perform the task;
• receiving awareness data from the ROV;
• maintaining, on the ROV side of the communications network, awareness information based on the awareness data, wherein maintaining the awareness information includes maintaining a feature map of a situational environment of the ROV using the awareness data;
• and
• controlling, on the ROV side of the communications network, operations of the ROV as a function of the remote supervisory command and the awareness information so that the ROV performs the task, including, on the ROV side of the communications network and downstream of the at least one sparse datalink, using an autonomy model on an edge-computing node local to the ROV that is configured to control the ROV to perform the task based on the remote supervisory command and the feature map, wherein the autonomy model contains control commands that control operations of one or more systems onboard the ROV to perform the task in response to receiving the remote supervisory command for the task, and wherein all loop closures for controlling the ROV to perform the task are done on the edge-computing node local to the ROV.

A local awareness/autonomy node for a remotely operated vehicle (ROV), wherein the local awareness/autonomy node allows a remote operator to operate the ROV to perform a task over a communications network containing at least one sparse datalink and having a remote operator side and an ROV side, wherein the at least one sparse datalink has at least one of 1) a bandwidth that is narrower than the bandwidth needed for one or more remote operators to supervise the ROV so that it successfully performs the task and 2) a latency that is higher than the maximum latency tolerable for being able to successfully perform the task, the local awareness/autonomy node comprising:

• memory containing machine-executable instructions for performing a method of operating the ROV to perform the task over the communications network, the method comprising:
• receiving, on the ROV side of the communications network, a remote supervisory command over the communications network from the remote operator side of the communications network, wherein the remote supervisory command is a high-level objective-based instruction requiring context of task, purpose, and desired end state and is a command for the ROV to perform the task;
• receiving awareness data from the ROV;
• maintaining, on the ROV side of the communications network, awareness information based on the awareness data, wherein maintaining the awareness information includes maintaining a feature map of a situational environment of the ROV using the awareness data;
• and
• controlling, on the ROV side of the communications network, operations of the ROV as a function of the remote supervisory command and the awareness information so that the ROV performs the task, including, on the ROV side of the communications network and downstream of the at least one sparse datalink, using an autonomy model on the local awareness/autonomy node, the local awareness/autonomy node being an edge-computing node local to the ROV, that is configured to control the ROV to perform the task based on the remote supervisory command and the feature map, wherein the autonomy model contains control commands that control operations of one or more systems onboard the ROV to perform the task in response to receiving the remote supervisory command for the task, and wherein all loop closures for controlling the ROV to perform the task are done on the local awareness/autonomy node;
• one or more communications ports configured to interface with systems aboard the ROV;
• one or more microprocessors:
• in operative communication with the memory;
• when the local awareness/autonomy node is deployed, in operative communication with the one or more communications ports;
• and
• configured to execute the machine-executable instructions so as to control the ROV to perform the task in response to the remote supervisory command.