Indoor substation unmanned aerial vehicle visual navigation system and method

Abstract

The invention discloses an indoor substation unmanned aerial vehicle visual navigation system and method. The system comprises a forward binocular perception module and a downward binocular perceptionmodule which are connected with an unmanned aerial vehicle flight control end. The flight control terminal comprises: a path planning unit configured to obtain a binocular image in real time throughan unmanned aerial vehicle forward visual perception module in the flight process of the unmanned aerial vehicle, construct a depth map, and perform path planning based on the depth map; and a visualodometer unit which is configured to acquire an image in real time through the downward visual perception module and calculate the current mileage of the unmanned aerial vehicle in the flight processof the unmanned aerial vehicle. Obstacle avoidance and path planning can be achieved only through a local map, and the operand is greatly reduced; and through multiple identification codes, accumulated errors in the unmanned aerial vehicle positioning process can be conveniently corrected in time.

Description

technical field [0001] The invention belongs to the technical field of substation inspection, and in particular relates to a visual navigation system and method for an indoor substation unmanned aerial vehicle. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] SLAM technology is a technology that is used for indoor navigation and simultaneous positioning and map construction. It was first applied in the field of robotics. Its goal is to build a map of the surrounding environment in real time based on sensor data without any prior knowledge This map infers its own location. SLAM that only utilizes cameras as external perception sensors is called visual SLAM. The camera has the advantages of rich visual information and low hardware cost. The classic visual SLAM system generally includes front-end visual odometry, back-end optimization, clos...

AI Technical Summary

Problems solved by technology

[0004] However, according to the inventor’s knowledge, if the traditional visual SLAM technology is applied to UAV substation inspection, there will be the following problems: 1) The step of closed-loop detection is very critical, but the reliability is not good, and the success rate of closed-loop detection is not 100%. %, once the closed-loop detection cannot be performed, the accumulation of positioning errors cannot be corrected, and the drone will fail to locate, and the inspection function cannot be completed at this time

2) The environment of the indoor substation is complex, and the UAV may need to circumvent from the top, left or right of the equipment during flight, which requires higher environmental perception capabilities. Therefore, if you rely on established maps for path planning, it is recommended The amount of calculation of the graph is huge, and it is difficult to realize real-time processing on the processor on the airborne side

Images