Autonomous obstacle avoidance methods, devices and storage media for unmanned aerial vehicles

By generating echo over-dispersion curvature and radial contraction networks, dynamically modulating free domain evidence, constructing a signed distance field, and adjusting trajectory speed and control commands, the problem of misjudgment of thin lines in UAV obstacle avoidance is solved, thereby improving obstacle avoidance reliability and adaptability.

CN121560052BActive Publication Date: 2026-06-30STATE GRID ANHUI ELECTRIC POWER CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
STATE GRID ANHUI ELECTRIC POWER CO LTD
Filing Date
2026-01-23
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

In complex scenarios, drones have difficulty effectively avoiding thin-lined targets, leading to misjudgments of false free zones, affecting obstacle avoidance decisions, and posing a collision risk.

Method used

By generating echo overdispersion curvature, a free domain contraction field is generated using a radial contraction network. The free evidence increment is dynamically modulated to construct a signed distance field. Combined with trajectory search speed adjustment and obstacle avoidance control commands, the final obstacle avoidance control command is generated.

Benefits of technology

It effectively suppresses false free zone misjudgments, improves the reliability and practicality of drone obstacle avoidance, reduces collision risks, and can be adapted to a variety of complex scenarios without additional hardware.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121560052B_ABST
    Figure CN121560052B_ABST
Patent Text Reader

Abstract

This invention relates to the field of unmanned aerial vehicle (UAV) control technology, and discloses a method, device, and storage medium for autonomous obstacle avoidance by UAVs. The autonomous obstacle avoidance method includes the following steps: Step S101, generating echo over-dispersion curvature; Step S102, generating a free domain contraction field; Step S103, generating a risk-based occupancy map; Step S104, constructing a signed distance field; Step S105, selecting yaw angular velocity and velocity scaling factor; Step S106, generating the final obstacle avoidance control command. This invention captures abnormal features of easily missed targets such as thin lines by extracting echo over-dispersion curvature, thus avoiding false free zone misjudgments at the source. The signed distance field integrates geometric distance and risk potential, providing a reliable basis for trajectory planning with risk information. The final control command superimposes a repulsive acceleration term, balancing trajectory stability and near-range obstacle avoidance response speed, thereby reducing collision risk and improving the reliability of autonomous obstacle avoidance by UAVs.
Need to check novelty before this filing date? Find Prior Art