Intelligent low-altitude unmanned aerial vehicle obstacle avoidance path planning method and system

Abstract

The application discloses a kind of intelligent low-altitude unmanned aerial vehicle obstacle avoidance path planning method and system, method includes: multi-modal data acquisition, space-time alignment fusion, three-dimensional dynamic trajectory reconstruction, obstacle avoidance path planning and system verification.The application belongs to the technical field of path planning, specifically refers to a kind of intelligent low-altitude unmanned aerial vehicle obstacle avoidance path planning method and system, the scheme adopts incremental dynamic updating mechanism, through the double correction mechanism of implicit space normal estimation and global discretization constraint, the precision of three-dimensional trajectory reconstruction is improved, BEV feature optimization fusion is generated to generate double enhanced feature map;For trajectory prediction point, construct hybrid bounding box, calculate dynamic minimum distance and design dynamic safety threshold that fuses unmanned aerial vehicle real-time speed, priority, combined with potential collision time, priority, construct space-time coupling risk index to complete fine risk classification, construct priority weighted reward reinforcement learning model, solve the problem of uneven distribution of right of way in low-altitude multi-priority unmanned aerial vehicle obstacle avoidance.

Images