阅读说明：本技术 一种无人机的安全降落方法、装置、无人机及介质 (Safe landing method and device for unmanned aerial vehicle, unmanned aerial vehicle and medium ) 是由 李劲松 张立天 于 2018-11-28 设计创作，主要内容包括：一种无人机的安全降落方法、装置、无人机及计算机存储介质,其中方法包括：当无人机丢失导航信号时,确定无人机的返航目标位置和第一返航路径(S101)；控制无人机基于所述第一返航路径和返航目标位置进行返航(S102)；当返航过程中无人机的当前位置在距离返航目标位置的第一预设范围内时,进行安全降落点检测,并记录可供无人机降落的安全降落点(S103)；根据记录的安全降落点进行降落(S104),该方法有助于为无人机的安全降落提供保障。(A safe landing method and device for an unmanned aerial vehicle, the unmanned aerial vehicle and a computer storage medium are provided, wherein the method comprises the following steps: when the unmanned aerial vehicle loses the navigation signal, determining a return target position and a first return path of the unmanned aerial vehicle (S101); controlling the unmanned aerial vehicle to return based on the first return path and the return target position (S102); when the current position of the unmanned aerial vehicle is within a first preset range from the return target position in the return process, detecting a safe landing point, and recording the safe landing point for landing of the unmanned aerial vehicle (S103); and landing according to the recorded safe landing points (S104), wherein the method is helpful for providing guarantee for the safe landing of the unmanned aerial vehicle.)

A safe landing method of an unmanned aerial vehicle is characterized by comprising the following steps:

when the unmanned aerial vehicle loses the navigation signal, determining a return target position and a first return path of the unmanned aerial vehicle;

controlling the unmanned aerial vehicle to carry out return voyage based on the first return voyage path and the return voyage target position;

when the current position of the unmanned aerial vehicle is within a first preset range from the return target position in the return process, detecting a safe landing point, and recording the safe landing point for landing of the unmanned aerial vehicle;

and landing according to the recorded safe landing point.

The method of claim 1, further comprising:

when the current position of the unmanned aerial vehicle is within a second preset range from the return target position in the return process, detecting a safe landing point, wherein the first preset range is larger than the second preset range;

if the detection result is that the safe falling point is not detected, executing the step of falling according to the recorded safe falling point;

and if the detection result is that the safe falling point is detected, falling is carried out according to the detected safe falling point.

The method of claim 2, wherein said landing according to the recorded safe landing point comprises:

determining a second return route according to the current position of the unmanned aerial vehicle and the recorded safe landing point;

flying to the recorded safe landing point based on the second return route;

and when the current position of the unmanned aerial vehicle is the recorded safe landing point, controlling the unmanned aerial vehicle to land.

The method of claim 2, wherein said landing in accordance with the detected safe landing point comprises:

continuously detecting whether the detected safe landing point is safe or not in the landing process;

if the detected safe landing points are detected to be safe continuously, determining that the landing is successful;

if the detected safe landing point is detected to be unsafe, adjusting the current flying height of the unmanned aerial vehicle to be a preset flying height, and executing the step of landing according to the recorded safe landing point;

and the preset flying height is the flying height of the unmanned aerial vehicle during the back-flying.

The method of claim 2, further comprising:

if no safe falling point is recorded in a first preset range from the return target position and no safe falling point is detected in a second preset range from the return target position, carrying out safe falling point detection according to a preset track in a third preset range from the return target position, wherein the preset track comprises a spiral track or a zigzag track;

and when a safe falling point is detected in the preset track, falling is carried out according to the detected safe falling point.

The method of claim 2, further comprising:

and if no safe landing point is recorded in a first preset range from the return target position and no safe landing point is detected in a second preset range from the return target position, controlling the unmanned aerial vehicle to hover at the return target position.

The method of claim 1, further comprising:

when the unmanned aerial vehicle reaches the return target position, carrying out safe landing point detection on the return target position;

if the detection result is that the return voyage target position is a safe landing point, performing landing at the return voyage target position;

and if the detection result is that the return voyage target position is not the safe landing point, executing the step of landing according to the recorded safe landing point.

The method of claim 1, wherein determining the return target position and the first return path of the drone comprises:

selecting any position from at least one preset return position as a return target position of the unmanned aerial vehicle;

determining a first return direction according to the return target position;

and determining the first return route according to the first return direction and the return target position.

The method of claim 1, wherein said controlling said drone to return based on said first return path and said return target location comprises:

and controlling the unmanned aerial vehicle to return based on the first return route, the return target position and the position information provided by the visual odometer.

The method of claim 3, wherein a second return direction corresponding to the second return path is opposite to a first return direction corresponding to the first return path.

The method of any one of claims 1-10, wherein the safety drop point is a planar and non-surface location.

The method of any one of claims 1-10, wherein performing safety drop point detection comprises:

and carrying out safe drop point detection based on the binocular vision sensor.

The method of any one of claims 1-10, wherein performing safety drop point detection comprises:

and carrying out plane detection on the current position of the unmanned aerial vehicle according to a preset plane detection algorithm, and carrying out water surface detection on the current position of the unmanned aerial vehicle according to a preset water surface detection algorithm.

The method of any of claims 1-10, wherein the navigation signal comprises at least one of: the signal of the positioning sensor, the signal of the compass.

The method of claim 13, wherein the performing plane detection on the current position of the drone according to a preset plane detection algorithm comprises:

determining a region to be detected for carrying out plane detection from an observation region corresponding to the current position, wherein the region to be detected is smaller than the observation region;

determining a two-dimensional projection image corresponding to the area to be detected;

converting any pixel point in the two-dimensional projection image into a three-dimensional space point to obtain a three-dimensional space point set corresponding to the two-dimensional projection image;

and carrying out plane detection on the current position according to the three-dimensional space point set.

The method of claim 14, wherein the performing plane detection on the current position according to the three-dimensional space point set comprises:

acquiring a standard plane equation;

calculating the distance between any three-dimensional space point in the three-dimensional space point set and the standard plane equation, and determining the number of interior points in the three-dimensional space point set according to the distance, wherein the interior points are three-dimensional space points of which the distance is smaller than or equal to a preset distance threshold value;

and when the number of the inner points is greater than or equal to a preset number threshold, determining that the current position is a plane.

The method of claim 13, wherein said detecting the current position of the drone for the water surface according to a preset water surface detection algorithm comprises:

determining a region to be detected for water surface detection from the observation region corresponding to the current position, wherein the region to be detected is smaller than the observation region;

determining a two-dimensional projection image corresponding to the area to be detected;

and inputting the two-dimensional projection image into a convolutional neural network model, and determining whether the current position is the water surface or not according to the output of the convolutional neural network model.

A safe landing device is applied to an unmanned aerial vehicle and is characterized by comprising a memory and a processor;

the memory is used for storing program codes;

the processor, invoking the program code, when executed, is configured to:

when the unmanned aerial vehicle loses the navigation signal, determining a return target position and a first return path of the unmanned aerial vehicle;

controlling the unmanned aerial vehicle to carry out return voyage based on the first return voyage path and the return voyage target position;

when the current position of the unmanned aerial vehicle is within a first preset range from the return target position in the return process, detecting a safe landing point, and recording the safe landing point for landing of the unmanned aerial vehicle;

and landing according to the recorded safe landing point.

The apparatus of claim 18, wherein the apparatus is further configured to:

when the current position of the unmanned aerial vehicle is within a second preset range from the return target position in the return process, detecting a safe landing point, wherein the first preset range is larger than the second preset range;

if the detection result is that the safe landing point is not detected, executing the step of landing according to the recorded safe landing point;

and if the detection result is that the safe falling point is detected, falling is carried out according to the detected safe falling point.

The apparatus of claim 19, wherein upon landing according to the recorded safe landing point, performing the following operations:

determining a second return route according to the current position of the unmanned aerial vehicle and the recorded safe landing point;

flying to the recorded safe landing point based on the second return route;

and when the current position of the unmanned aerial vehicle is the recorded safe landing point, controlling the unmanned aerial vehicle to land.

The apparatus of claim 19, wherein upon landing in accordance with the detected safe landing point, performing the following:

continuously detecting whether the detected safe landing point is safe or not in the landing process;

if the detected safe landing points are detected to be safe continuously, determining that the landing is successful;

if the detected safe landing point is detected to be unsafe, adjusting the current flying height of the unmanned aerial vehicle to be a preset flying height, and executing the step of landing according to the recorded safe landing point;

and the preset flying height is the flying height of the unmanned aerial vehicle during the back-flying.

The apparatus of claim 19, wherein the apparatus is further configured to:

if no safe falling point is recorded in a first preset range from the return target position and no safe falling point is detected in a second preset range from the return target position, carrying out safe falling point detection according to a preset track in a third preset range from the return target position, wherein the preset track comprises a spiral track or a zigzag track;

and when a safe falling point is detected in the preset track, falling is carried out according to the detected safe falling point.

The apparatus of claim 19, wherein the apparatus is further configured to:

and if no safe landing point is recorded in a first preset range from the return target position and no safe landing point is detected in a second preset range from the return target position, controlling the unmanned aerial vehicle to hover at the return target position.

The apparatus of claim 18, wherein the apparatus is further configured to:

when the unmanned aerial vehicle reaches the return target position, carrying out safe landing point detection on the return target position;

if the detection result is that the return voyage target position is a safe landing point, performing landing at the return voyage target position;

and if the detection result is that the return voyage target position is not the safe landing point, executing the step of landing according to the recorded safe landing point.

The apparatus of claim 18, wherein the determining the return target position and the first return path of the drone performs the following operations:

selecting any position from at least one preset return position as a return target position of the unmanned aerial vehicle;

determining a first return direction according to the return target position;

and determining the first return route according to the first return direction and the return target position.

The apparatus of claim 18, wherein the control of the drone to perform the following operations while navigating back based on the first return path and the return target location:

and controlling the unmanned aerial vehicle to return based on the first return route, the return target position and the position information provided by the visual odometer.

The apparatus of claim 20, wherein a second return direction corresponding to the second return path is opposite to a first return direction corresponding to the first return path.

The apparatus of any one of claims 18-27, wherein the safety landing point is a planar and non-surface location.

The apparatus according to any one of claims 18 to 27, wherein the following is performed when performing the safety landing point detection:

and carrying out safe drop point detection based on the binocular vision sensor.

The apparatus according to any one of claims 18 to 27, wherein the following is performed when performing the safety landing point detection:

and carrying out plane detection on the current position of the unmanned aerial vehicle according to a preset plane detection algorithm, and carrying out water surface detection on the current position of the unmanned aerial vehicle according to a preset water surface detection algorithm.

The apparatus of any one of claims 18-27, wherein the navigation signal comprises at least one of: the signal of the positioning sensor, the signal of the compass.

The apparatus of claim 30, wherein when performing plane detection on the current position of the drone according to a preset plane detection algorithm, the following operations are performed:

determining a region to be detected for carrying out plane detection from an observation region corresponding to the current position, wherein the region to be detected is smaller than the observation region;

determining a two-dimensional projection image corresponding to the area to be detected;

converting any pixel point in the two-dimensional projection image into a three-dimensional space point to obtain a three-dimensional space point set corresponding to the two-dimensional projection image;

and carrying out plane detection on the current position according to the three-dimensional space point set.

The apparatus according to claim 31, wherein the plane detection of the current position according to the three-dimensional space point set is performed as follows:

acquiring a standard plane equation;

calculating the distance between any three-dimensional space point in the three-dimensional space point set and the standard plane equation, and determining the number of interior points in the three-dimensional space point set according to the distance, wherein the interior points are three-dimensional space points of which the distance is smaller than or equal to a preset distance threshold value;

and when the number of the inner points is greater than or equal to a preset number threshold, determining that the current position is a plane.

The apparatus of claim 30, wherein the following operations are performed when the current position of the drone is detected according to a preset water level detection algorithm:

determining a region to be detected for water surface detection from the observation region corresponding to the current position, wherein the region to be detected is smaller than the observation region;

determining a two-dimensional projection image corresponding to the area to be detected;

and inputting the two-dimensional projection image into a convolutional neural network model, and determining whether the current position is the water surface or not according to the output of the convolutional neural network model.

An unmanned aerial vehicle, comprising:

a body;

the power system is arranged on the machine body and used for providing power for the unmanned aerial vehicle;

and a safety landing device of any one of claims 18-34.

The drone of claim 35, further comprising:

a sensor mounted to the body, the sensor including at least one of: a binocular vision sensor or a visual odometer;

the binocular vision sensor is used for detecting a safe landing point;

the visual odometer is used for providing position information of the unmanned aerial vehicle during the back-navigation.

A computer storage medium having computer program instructions stored therein, which when executed by a processor, is configured to perform a method of secure landing of a drone according to any one of claims 1 to 17.