An aerial vehicle according to an embodiment of the present technology includes a recording unit, a detection unit, and a reproduction unit. The recording unit records a flight parameter during flight in a state in which no sensor abnormality is detected. The detection unit detects the sensor abnormality. The reproduction unit reproduces the flight parameter on the basis of the sensor abnormality detected by the detection unit.

Lawn maintenance devices and tracking systems and methods for lawn maintenance devices are provided. A lawn maintenance device includes a frame; a wheel supporting the frame, wherein the wheel comprises: a body defining a central axis about which the body is rotatable; and a detectable element radially offset from the central axis; a detector that detects a relative position of the detectable element; and control circuitry that receives information from the detector and determines a position of the wheel based on the received information, the information associated with the detected relative position of the detectable element.

A system includes a vehicle and a control device. The vehicle includes a reception unit for receiving an instruction related to remote control from the control device, a vehicle control unit for executing any one of first vehicle control and second vehicle control, the first vehicle control being control based on the instruction related to the remote control, and the second vehicle control being control determined by the vehicle itself in accordance with a traveling environment, and a transmission unit for notifying a predetermined control result to the control device when the second vehicle control is executed by the vehicle control unit. The control device includes a remote control unit, a transmission unit, and a reception unit. When the control result is notified from the vehicle, the remote control unit of the control device executes the remote control based on a content of the control result.

The vehicle is configured to be able to communicate with an autonomous driving kit configured to be detachable from the vehicle, and includes an interface unit that gives a control instruction related to automated driving control to each unit of the vehicle based on an instruction from the autonomous driving kit, and an active safety device that realizes a preventive safety function of the vehicle. The active safety device includes performance evaluation unit for evaluating the driving performance of the autonomous driving kit based on the degree of deviation between the reference traveling data in the area in which the vehicle is traveling and the traveling data of the vehicle.

The vehicle is configured to be able to communicate with an autonomous driving kit configured to be detachable from the vehicle, and includes an interface unit that gives a control instruction related to automated driving control to each unit of the vehicle based on an instruction from the autonomous driving kit, and an active safety device that realizes a preventive safety function of the vehicle. The active safety device includes performance evaluation unit for evaluating the driving performance of the autonomous driving kit based on the degree of deviation between the reference traveling data in the area in which the vehicle is traveling and the traveling data of the vehicle.

The present embodiment relates to a cloud-based robot control method for controlling a plurality of robots which are positioned in a plurality of spaces divided arbitrarily, the method comprising the steps of: generating a control base model which can be applied to the plurality of robots in a cloud server; distributing the control base model to edge servers allocated to respective spaces; upgrading the control base model in accordance with the plurality of robots of a space, in the edge server; directly transmitting the upgraded control model from the edge server to another edge server; and controlling the plurality of robots by means of the upgraded control model in the edge server. Therefore, by sharing a deep-learning model among edge servers, supporting heterogeneous robots and heterogeneous services is possible. Further, a base deep-learning model from the cloud server is tuned into a customized deep-learning model to be suitable for respective robots in the edge server, and the deep-learning model is upgraded to an adaptive deep-learning model to be suitable for a service provided by respective robots, and thus an optimized service can be provided.

The present embodiment relates to a cloud-based robot control method for controlling a plurality of robots which are positioned in a plurality of spaces divided arbitrarily, the method comprising the steps of: generating a control base model which can be applied to the plurality of robots in a cloud server; distributing the control base model to edge servers allocated to respective spaces; upgrading the control base model in accordance with the plurality of robots of a space, in the edge server; directly transmitting the upgraded control model from the edge server to another edge server; and controlling the plurality of robots by means of the upgraded control model in the edge server. Therefore, by sharing a deep-learning model among edge servers, supporting heterogeneous robots and heterogeneous services is possible. Further, a base deep-learning model from the cloud server is tuned into a customized deep-learning model to be suitable for respective robots in the edge server, and the deep-learning model is upgraded to an adaptive deep-learning model to be suitable for a service provided by respective robots, and thus an optimized service can be provided.

A return method or device for an unmanned aerial vehicle (UAV), a UAV and a storage medium are provided. The method includes: detecting whether a sensor for obstacle avoidance fails; if the sensor fails, determining a return path of the UAV based on a first return strategy; if the sensor operates normally, determining the return path of the UAV based on a second return strategy; the first return strategy includes controlling the UAV to fly to a return altitude; the second return strategy includes determining the return path of the UAV based on detection data from the sensor. The combination of these two return strategies can achieve a balance between the return efficiency and safety of the UAV.

A return method or device for an unmanned aerial vehicle (UAV), a UAV and a storage medium are provided. The method includes: detecting whether a sensor for obstacle avoidance fails; if the sensor fails, determining a return path of the UAV based on a first return strategy; if the sensor operates normally, determining the return path of the UAV based on a second return strategy; the first return strategy includes controlling the UAV to fly to a return altitude; the second return strategy includes determining the return path of the UAV based on detection data from the sensor. The combination of these two return strategies can achieve a balance between the return efficiency and safety of the UAV.

A system accesses Autonomous Vehicle Communication Gateway (AVCG) information that comprises information associated with an AVCG manager. The AVCG manager is a software resource configured to transition among states in which the autonomous vehicle operates in response to detecting a respective trigger event. The system determines an autonomy status associated with the autonomous vehicle. The system detects a change in the autonomy status by accessing historical records of event, tracking back through the historical records of events, and tracking back through the AVCG information. The system determines one or more particular events from among one or both of the historical records of events and the AVCG information that led to the change in the autonomy status. The system outputs the cause of the change in the autonomy status.