Check patentability & draft patents in minutes with Patsnap Eureka AI!

Flight path planning method based on deep Q network and fast search random tree algorithm

A track planning, random tree technology, applied in three-dimensional position/channel control, vehicle position/route/altitude control, instruments, etc. The effect of strong obstacle ability, taking into account the completeness of probability, and improving the efficiency of exploration

Pending Publication Date: 2022-05-31
BEIHANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention proposes a RRT-GoalBias path planning optimization algorithm based on a deep Q network (DQN-RRTGoalBias ) to improve algorithm efficiency and stability

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Flight path planning method based on deep Q network and fast search random tree algorithm
  • Flight path planning method based on deep Q network and fast search random tree algorithm
  • Flight path planning method based on deep Q network and fast search random tree algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Below in conjunction with example the present invention is described in further detail.

[0037] The present invention is based on the track planning method of depth Q network and fast search random tree algorithm, such as figure 1 As shown, the specific steps are as follows:

[0038] Step 1: Markov decision process modeling of the RRT algorithm

[0039] Reinforcement learning usually uses Markov decision process (MDP) as the basic framework. In the simulation of MDP, the agent perceives the current system state, selects and implements actions from the action space according to the optimal strategy, thereby changing the environment and its own state. And get the feedback (reward) from the environment. In order to introduce the reinforcement learning algorithm, it is first necessary to abstract the Markov decision process (Markov Decision Process, MDP) in the RRT algorithm. Due to the randomness of RRT growth, for each expansion process, it can be regarded as a Markov...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a flight path planning method based on a deep Q network and a fast search random tree algorithm. The method comprises the following steps: firstly, abstracting a Markov decision process in an RRT algorithm; due to the randomness of RRT growth, for each expansion process, the expansion process can be regarded as a Markov process, and an MDP model of the expansion process is established. And then training the deep Q network, and obtaining the optimal action corresponding to each state according to the deep Q network: introducing the optimal action and then carrying out improved RRT path planning. According to the method, the obstacle avoidance capability of the RRT-GoalBias algorithm can be stronger, and the opportunity of greedy expansion is increased, so that the efficiency and stability of the algorithm are improved.

Description

technical field [0001] The invention relates to the field of track planning, in particular to a track planning method combining a deep Q network and a fast search random tree algorithm. Background technique [0002] Trajectory planning technology is one of the key links in the intelligence of unmanned aerial vehicles, and it is developing rapidly driven by computer technology, information technology and artificial intelligence technology. The path planning algorithm is the core of the trajectory planning technology. Its purpose is to find a path solution from the starting point to the target point in the model space. The path solution must meet certain constraints and meet certain performance indicators according to actual needs ( path length, time, energy consumption, etc.). Therefore, the path not only needs to meet various platform constraints, but also needs to ensure that the agent does not collide with obstacles when running along the path. The Rapidly-exploring Rand...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G05D1/10
CPCG05D1/106
Inventor 李昭莹石若凌欧一鸣
Owner BEIHANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com