Control method and device of pool underwater step cleaning robot

By constructing a three-dimensional step model and combining a depth-deterministic policy gradient algorithm and an adaptive control model, the problems of unstable posture and insufficient cleaning power of existing cleaning robots in pool step environments are solved, achieving a more efficient cleaning effect.

CN120909298BActive Publication Date: 2026-01-13YITUO ELECTRIC CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202511393369.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-09-28
Publication Date
2026-01-13
Estimated Expiration
2045-09-28

AI Technical Summary

Technical Problem

Existing cleaning robots are difficult to adapt flexibly to pool steps of different sizes, resulting in poor posture stability, low cleaning power, and easy malfunctions.

Method used

A three-dimensional step model is constructed by scanning the target step area. An initial control strategy is generated using a depth deterministic policy gradient algorithm. Combined with sliding mode control, fuzzy control, and inverted pendulum control models, the robot's motion state and posture are optimized in real time to adapt to the cleaning process of the target step area.

Benefits of technology

This improves the robot's environmental adaptability and posture stability in complex underwater step environments, enhances cleaning efficiency and effectiveness, and solves the problem of insufficient adaptability of traditional cleaning equipment to unstructured step environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120909298B_ABST
    Figure CN120909298B_ABST
Patent Text Reader

Abstract

The embodiment of the application relates to the technical field of robot control, and provides a control method and device of a pool underwater step cleaning robot. The method comprises the following steps: scanning a step structure in a target step region to construct a three-dimensional step model; generating an initial control strategy according to the three-dimensional step model by a deep deterministic policy gradient algorithm before water entry cleaning, and starting the robot to enter the target step region based on the initial control strategy; collecting motion state data and attitude monitoring data of the robot in real time during the cleaning process; based on an adaptive control model of an inverted pendulum balance theory, the motion state data, the attitude monitoring data and step structure parameters in the three-dimensional step model are cooperatively optimized to obtain a real-time control strategy of the robot; and the motion state of the robot is adjusted based on the real-time control strategy to adapt to the step cleaning process in the target step region, and the environmental adaptability, attitude stability and operation efficiency of the robot in a complex underwater step environment are improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Underwater cleaning robot

    CN101139007A

  • Pool wall obstacle avoidance moving method and device of swimming pool cleaning robot and electronic equipment

    CN116466725A