Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Hexapod robot obstacle avoidance method based on adaptive weight reinforcement learning

A hexapod robot, self-adaptive weight technology, applied in the direction of self-adaptive control, instrument, control/regulation system, etc., can solve the problem that the robot cannot walk.

Active Publication Date: 2020-08-18
NANJING UNIV
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Using this gait can show good walking ability on a plane, but in irregular terrain, especially in an unknown environment, the robot has no way to achieve stable walking, so there is an urgent need for a gait planning method that can adapt to unknown terrain

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
  • Hexapod robot obstacle avoidance method based on adaptive weight reinforcement learning
  • Hexapod robot obstacle avoidance method based on adaptive weight reinforcement learning
  • Hexapod robot obstacle avoidance method based on adaptive weight reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] like figure 1 As shown, the hexapod robot obstacle avoidance method based on adaptive weight reinforcement learning disclosed by the present invention includes the following steps:

[0070] Step 1: The hexapod robot measures the distance between the robot and obstacles in the front, left and right directions through the ranging sensor, and converts the measured obstacle distance into a finite set of states through the fuzzy membership function;

[0071] Step 2. Establish a hexapod robot obstacle avoidance model according to the limited state set, and then use the adaptive weight reinforcement learning algorithm to learn the optimal network model parameters θ*;

[0072] Step 3: Obtain the optimal target strategy of the hexapod robot for obstacle avoidance according to the above-mentioned trained optimal network model parameters θ*, and obtain the action a to be taken by the hexapod robot for obstacle avoidance at time t from the optimal target strategy t .

[0073] Fur...

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 hexapod robot obstacle avoidance method based on adaptive weight reinforcement learning. The method comprises the following steps: enabling a hexapod robot to measure the distance between the robot and each nearby obstacle through a distance measurement sensor, and converting the measured obstacle distance into a limited state set through a fuzzy membership function; establishing a hexapod robot obstacle avoidance model according to the limited state set, and learning an optimal network model parameter theta * by using an adaptive weight reinforcement learning algorithm; and obtaining an optimal target strategy for obstacle avoidance of the hexapod robot according to the trained optimal network model parameter theta *, and obtaining an action at which the hexapodrobot needs to avoid the obstacle at the moment t according to the optimal target strategy. The obstacle avoidance method can achieve a good obstacle avoidance effect in a position environment with alarge number of obstacles, and has a good market application prospect.

Description

technical field [0001] The invention relates to an obstacle avoidance method for a robot, in particular to an obstacle avoidance method for a hexapod robot based on self-adaptive weight reinforcement learning. Background technique [0002] The hexapod robot has multiple redundant degrees of freedom in structure, so it has a high adaptability to the terrain environment. Hexapod robots can walk in the field with complex road conditions, overcome obstacles, and complete transportation operations in non-structural environments that cannot be completed by wheeled or tracked types. They are used in forest logging, mining, underwater construction, nuclear industry, military transportation and It has a very broad application prospect in fields such as detection and planetary detection. Therefore, the research on hexapod robots has always attracted the attention of experts and scholars from various countries, but how to improve the mobility of hexapod robots in unstructured environm...

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
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 李华雄任其成陈春林王岚唐开强王子辉朱张青辛博
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com