Method for manned vehicle to supervise and control obstacle avoidance of unmanned aerial vehicle

Abstract

The invention provides a method for a manned vehicle to supervise and control obstacle avoidance of an unmanned aerial vehicle (UAV), which relates to the field of UAVs. According to the method, the values of environmental factors, obstacle avoidance actions and supervision and control modes are defined, and a UAV infers and judges optional obstacle avoidance actions and makes judgment according to the judgment result so as to avoid obstacles. For a known obstacle, the UAV gives full play to the autonomous ability to independently avoid the obstacle. For an unknown obstacle, the UAV must be guided by a manned vehicle to avoid the obstacle. The variable autonomous supervision and control method gives full play to the autonomous execution ability of the UAV and the analysis and judgment ability of a manned vehicle operator. In an extreme case such as communication interruption, the UAV ensures its own safety by adjusting the supervision and control mode while waiting for the recovery ofcommunication. The variable autonomous supervision and control mode can well adapt to different types of obstacles and environmental conditions based on the characteristics of UAV and the manned vehicle.

Description

technical field

[0001] The invention relates to the field of unmanned aerial vehicles, in particular to an avoidance judgment method. Background technique

[0002] When the UAV faces obstacles during its travel, the human-machine operator interacts with the UAV to ensure that the UAV completes the obstacle avoidance. Supervisory control refers to the manned machine interacting with the UAV intermittently, receiving feedback and giving instructions to control the process of the UAV in the mission environment.

[0003] However, in the practical application of UAS obstacle avoidance, traditional methods generally use operator manual operation for obstacle avoidance, or use path planning, rules or automata for obstacle avoidance by calculating cost functions. In this way, there will be two problems: ① due to the complexity of the environment, the operator's "overload" phenomenon; Not in the loop" (Out-of-the-Loop, OOTL) phenomenon. The two problems show that the supervision a...

Examples

Embodiment 1

[0149] (1) Step1: Representation of environmental factors and obstacle avoidance actions

[0150] It can be seen from Table 5 that if the obstacle type is a known obstacle, then V1=1, V4=0; if the obstacle distance is long, then V3=0, V5=1; if the communication status is normal, then V2=0, the drone Actions A1 to A4 are all initialized to 0, and the initial supervisory control mode is exception management mode L3;

[0151] (2) Step2: Reasoning and judgment of optional obstacle avoidance actions

[0152] The state vector is:

[0153]

[0154] Iterating it, the state vector of the output node is:

[0155]

[0156] The output results show that the optional action of the UAV in Example 1 is autonomous obstacle avoidance A1, so for known obstacles, the UAV can give full play to its autonomous ability and complete obstacle avoidance independently.

[0157] (3) Step3: Judgment of the final obstacle avoidance action

[0158] For example 1, the obstacle type is a known obstac...

Embodiment 2

[0178] For Example 2, the obstacle type is an unknown obstacle, and the UAV does not have the ability to avoid obstacles autonomously, so it needs to interact with the manned machine; the manned machine receives the obstacle image information and location information returned by the UAV, and updates the obstacle information , so that the type becomes a known obstacle; the UAV then performs reasoning and judgment on the optional obstacle avoidance action according to the current environmental state. At this time, the obstacle type is a known obstacle, and the UAV has the ability to avoid obstacles autonomously. And in the exception management mode L3, the UAV has the authority to perform autonomous obstacle avoidance actions, so it does not need to interact with the manned machine, and the UAV can complete the obstacle avoidance process autonomously. The process is as follows: image 3 shown.

Embodiment 3

[0180] (1) Step1: Representation of environmental factors and obstacle avoidance actions

[0181] From embodiment 3, if the obstacle type is an unknown obstacle, then V1=0, V4=1; if the obstacle distance is far away, then V3=0, V5=1; if the communication status is a communication interruption, then V2=1, and the drone moves A1~A4 are all initialized to 0, and the supervisory control mode is exception management mode L3.

[0182] (2) Step2: Reasoning and judgment of optional obstacle avoidance actions

[0183] The state vector is:

[0184]

[0185] Iterating it, the state vector of the output node is:

[0186]

[0187]The output results show that in the case of Example 3, the UAV does not have the ability to autonomously avoid obstacles, so it slows down and waits for command A2, but due to the interruption of communication, it cannot receive the command from the manned machine. In order to ensure its own safety, the execution returns to Operate A4.

[0188] (3) Step3...

technical field

[0001] The invention relates to the field of unmanned aerial vehicles, in particular to an avoidance judgment method. Background technique

[0002] When the UAV faces obstacles during its travel, the human-machine operator interacts with the UAV to ensure that the UAV completes the obstacle avoidance. Supervisory control refers to the manned machine interacting with the UAV intermittently, receiving feedback and giving instructions to control the process of the UAV in the mission environment.

[0003] However, in the practical application of UAS obstacle avoidance, traditional methods generally use operator manual operation for obstacle avoidance, or use path planning, rules or automata for obstacle avoidance by calculating cost functions. In this way, there will be two problems: ① due to the complexity of the environment, the operator's "overload" phenomenon; Not in the loop" (Out-of-the-Loop, OOTL) phenomenon. The two problems show that the supervision a...

Examples

Embodiment 1

[0149] (1) Step1: Representation of environmental factors and obstacle avoidance actions

[0150] It can be seen from Table 5 that if the obstacle type is a known obstacle, then V1=1, V4=0; if the obstacle distance is long, then V3=0, V5=1; if the communication status is normal, then V2=0, the drone Actions A1 to A4 are all initialized to 0, and the initial supervisory control mode is exception management mode L3;

[0151] (2) Step2: Reasoning and judgment of optional obstacle avoidance actions

[0152] The state vector is:

[0153]

[0154] Iterating it, the state vector of the output node is:

[0155]

[0156] The output results show that the optional action of the UAV in Example 1 is autonomous obstacle avoidance A1, so for known obstacles, the UAV can give full play to its autonomous ability and complete obstacle avoidance independently.

[0157] (3) Step3: Judgment of the final obstacle avoidance action

[0158] For example 1, the obstacle type is a known obstac...

Embodiment 2

[0178] For Example 2, the obstacle type is an unknown obstacle, and the UAV does not have the ability to avoid obstacles autonomously, so it needs to interact with the manned machine; the manned machine receives the obstacle image information and location information returned by the UAV, and updates the obstacle information , so that the type becomes a known obstacle; the UAV then performs reasoning and judgment on the optional obstacle avoidance action according to the current environmental state. At this time, the obstacle type is a known obstacle, and the UAV has the ability to avoid obstacles autonomously. And in the exception management mode L3, the UAV has the authority to perform autonomous obstacle avoidance actions, so it does not need to interact with the manned machine, and the UAV can complete the obstacle avoidance process autonomously. The process is as follows: image 3 shown.

Embodiment 3

[0180] (1) Step1: Representation of environmental factors and obstacle avoidance actions

[0181] From embodiment 3, if the obstacle type is an unknown obstacle, then V1=0, V4=1; if the obstacle distance is far away, then V3=0, V5=1; if the communication status is a communication interruption, then V2=1, and the drone moves A1~A4 are all initialized to 0, and the supervisory control mode is exception management mode L3.

[0182] (2) Step2: Reasoning and judgment of optional obstacle avoidance actions

[0183] The state vector is:

[0184]

[0185] Iterating it, the state vector of the output node is:

[0186]

[0187]The output results show that in the case of Example 3, the UAV does not have the ability to autonomously avoid obstacles, so it slows down and waits for command A2, but due to the interruption of communication, it cannot receive the command from the manned machine. In order to ensure its own safety, the execution returns to Operate A4.

[0188] (3) Step3...

Images