Wheel-legged robot adaptive anti-rollover method and system based on visual-inertial fusion

By using visual-inertial fusion technology to estimate the road surface adhesion coefficient and path curvature in real time, dynamically calibrating the visual feedforward tilt angle and combining it with IMU feedback, the problem of sideslipping and overturning of wheeled robots when cornering at high speeds was solved, and stable cornering control on complex road surfaces was achieved.

CN122195060APending Publication Date: 2026-06-12JIMEI UNIV
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
JIMEI UNIV
Filing Date
2026-04-21
Publication Date
2026-06-12

AI Technical Summary

Technical Problem

Existing wheeled robots suffer from sideslip and overturning problems when cornering at high speeds due to sudden environmental changes and nonlinearity of the actuators, which are particularly difficult to control effectively when the friction coefficient changes or the vision sensor fails.

Method used

By using visual-inertial fusion technology, the road surface adhesion coefficient and path curvature are estimated in real time, the visual feedforward tilt angle is dynamically calibrated, and weight allocation is performed in combination with IMU feedback to generate the final tilt command. Inverse kinematics is used to control the robot's posture.

Benefits of technology

This improves the system's robustness and accuracy in extreme environments, ensuring the robot can stably navigate curves on complex surfaces, avoiding sideslip and overturning, and achieving adaptive anti-roll control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122195060A_ABST
    Figure CN122195060A_ABST
Patent Text Reader

Abstract

This invention relates to an adaptive anti-tilt method and system for wheeled and legged robots based on visual-inertial fusion, belonging to the field of robot motion control technology. The method includes: First, fusing visual road surface semantics, IMU acceleration, and angular velocity information to estimate the ground adhesion coefficient online in real time, and dynamically calibrating the theoretical tilt angle calculated from the visual path curvature accordingly. Second, the system dynamically adjusts the weight ratio of visual feedforward control and IMU feedback control based on the confidence level of visual path recognition, achieving an adaptive fusion of aggressive prediction and robust disturbance resistance. Finally, the fused final tilt command is precisely mapped to the angle control command of the drive joint servo motors through an analytical solution of the inverse kinematics of a five-bar linkage based on spatial geometry and the cosine theorem, achieving error-free conversion from macroscopic attitude to low-level execution. This system improves the robot's cornering stability and safety in dynamic unstructured environments.
Need to check novelty before this filing date? Find Prior Art