When a remotely controlled work machine loses a wireless connection on a work site, operation of the work machine should be terminated for safety purposes. However, if the work machine is moving when the wireless connection is lost, the work machine will continue moving for some time due to inertia. Accordingly, embodiments predict the signal quality of a wireless connection as a work machine approaches a new geographical location. When the predicted signal quality is low, the work machine may be proactively derated before it enters the geographical location. After entering the geographical location, if the actual signal quality is significantly better than the predicted signal quality, the work machine may be rerated. The predicted signal qualities may be determined based on a signal map that is independently maintained and updated by each work machine, so as to evolve over time with the work site and the work machine.

When a remotely controlled work machine loses a wireless connection on a work site, operation of the work machine should be terminated for safety purposes. However, if the work machine is moving when the wireless connection is lost, the work machine will continue moving for some time due to inertia. Accordingly, embodiments predict the signal quality of a wireless connection as a work machine approaches a new geographical location. When the predicted signal quality is low, the work machine may be proactively derated before it enters the geographical location. After entering the geographical location, if the actual signal quality is significantly better than the predicted signal quality, the work machine may be rerated. The predicted signal qualities may be determined based on a signal map that is independently maintained and updated by each work machine, so as to evolve over time with the work site and the work machine.

Various aspects of methods, systems, and use cases include techniques for robotic relocalization. A robot may be configured to perform relocalization using operations to determine a cause of a loss of pose; use a nearest neighbor process to select a set of milestones from a roadmap when the cause of the loss of pose is due to a malfunction, or use a ranking process to select the set of milestones from the roadmap when the cause of the loss of pose is not due to the malfunction, the roadmap including a plurality of milestones; generate particle clouds around each milestone in the set of milestones; and perform localization on each milestone in the set of milestones to attempt to relocalize the robot.

Various aspects of methods, systems, and use cases include techniques for robotic relocalization. A robot may be configured to perform relocalization using operations to determine a cause of a loss of pose; use a nearest neighbor process to select a set of milestones from a roadmap when the cause of the loss of pose is due to a malfunction, or use a ranking process to select the set of milestones from the roadmap when the cause of the loss of pose is not due to the malfunction, the roadmap including a plurality of milestones; generate particle clouds around each milestone in the set of milestones; and perform localization on each milestone in the set of milestones to attempt to relocalize the robot.

Methods, systems and apparatus, including computer programs encoded on computer storage media for unmanned aerial vehicle visual line of sight flight operations. A UAV computer system may be configured to ensure the UAV is operating in visual line of sight of one or more ground operators. The UAV may confirm that it has a visual line of sight with the one or more user devices, such as a ground control station, or the UAV may ensure that the UAV does not fly behind or below a structure such that the ground operator would not be able to visually spot the UAV. The UAV computer system may be configured in such a way that UAV operation will maintain the UAV in visual line of sight of a base location.

Methods, systems and apparatus, including computer programs encoded on computer storage media for unmanned aerial vehicle visual line of sight flight operations. A UAV computer system may be configured to ensure the UAV is operating in visual line of sight of one or more ground operators. The UAV may confirm that it has a visual line of sight with the one or more user devices, such as a ground control station, or the UAV may ensure that the UAV does not fly behind or below a structure such that the ground operator would not be able to visually spot the UAV. The UAV computer system may be configured in such a way that UAV operation will maintain the UAV in visual line of sight of a base location.

An unmanned driving system includes a moving object movable by remote control; a moving object configured to be movable by remote control; a remote control unit configured to perform the remote control for the moving object, wherein the remote control unit moves the moving object that has been finished a first work at a first place in a factory to a second place in the factory by the remote control, wherein the first work is a work using production equipment, wherein the second place is a place for performing a second work on the moving object; an information acquisition unit configured to acquire abnormality information, wherein the abnormality information includes at least one of information regarding abnormality in the production equipment, information regarding abnormality in the moving object, and information regarding abnormality in another moving object of the same type as the moving object; and an estimation unit configured to estimate whether or not the moving object has an abnormality using the abnormality information, wherein the remote control unit moves an estimated moving object to a third place in the factory, wherein the estimated moving object is the moving object that is estimated to have an abnormality by the estimation unit, wherein the third place is different from both the first place and the second place.

An unmanned driving system includes a moving object movable by remote control; a moving object configured to be movable by remote control; a remote control unit configured to perform the remote control for the moving object, wherein the remote control unit moves the moving object that has been finished a first work at a first place in a factory to a second place in the factory by the remote control, wherein the first work is a work using production equipment, wherein the second place is a place for performing a second work on the moving object; an information acquisition unit configured to acquire abnormality information, wherein the abnormality information includes at least one of information regarding abnormality in the production equipment, information regarding abnormality in the moving object, and information regarding abnormality in another moving object of the same type as the moving object; and an estimation unit configured to estimate whether or not the moving object has an abnormality using the abnormality information, wherein the remote control unit moves an estimated moving object to a third place in the factory, wherein the estimated moving object is the moving object that is estimated to have an abnormality by the estimation unit, wherein the third place is different from both the first place and the second place.