A method for unmanned aerial vehicle path planning based on semantic context-aware reinforcement learning

By constructing a multi-attribute 3D map and utilizing a reinforcement learning strategy network to output path planning preference weights, combined with a global path planning algorithm, the environmental perception and safety issues of UAV path planning in complex environments are solved, achieving efficient and safe path planning.

CN122108166BActive Publication Date: 2026-07-07ZHEJIANG UNIV OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
ZHEJIANG UNIV OF TECH
Filing Date
2026-04-30
Publication Date
2026-07-07

AI Technical Summary

Technical Problem

Existing UAV path planning methods lack environmental awareness in complex environments, making it difficult to distinguish between scenarios such as narrow passages and high-risk areas. Furthermore, traditional planners have poor cost weight adaptability, and end-to-end reinforcement learning cannot guarantee path feasibility and safety boundaries.

Method used

We employ a semantic context-aware reinforcement learning approach. By constructing a multi-attribute 3D map, we integrate spatial occupancy information, distance information, and semantic risk attributes. We utilize the path planning preference weights output by the reinforcement learning policy network, combine them with a global path planning algorithm to generate feasible paths, and then apply safety constraints and smoothing processing.

Benefits of technology

It enhances the UAV's environmental perception and navigation decision-making focus in complex environments, balances adaptability and planning safety, and possesses strong generalization ability and rapid migration characteristics, ensuring the feasibility and safety of path planning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122108166B_ABST
    Figure CN122108166B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of unmanned aerial vehicle three-dimensional path planning, and particularly relates to an unmanned aerial vehicle path planning method based on semantic context perception reinforcement learning. The present application comprises: fusing multi-source sensing data collected by the unmanned aerial vehicle to construct a multi-attribute three-dimensional map; constructing an envelope region between the current position and the target position of the unmanned aerial vehicle, and obtaining an environmental context vector; inputting the environmental context vector into a pre-trained reinforcement learning strategy network to output a set of path planning preference weights; obtaining path planning weights through path connectivity testing; constructing a comprehensive cost function based on the path planning weights; using a global path planning algorithm to search for a feasible path in the multi-attribute three-dimensional map according to the comprehensive cost function, and converting the feasible path into continuous flight instructions. The present application improves the environmental perception capability and navigation decision concentration, takes into account adaptability and planning safety, and has strong generalization capability and rapid migration characteristics.
Need to check novelty before this filing date? Find Prior Art