Robot motion sequence generation method, storage medium and electronic equipment

By constructing a mask matrix aligned with the spatiotemporal dimension of the motion sequence and combining it with a diffusion model, the problems of difficult embedding of keyframe constraints and low generation efficiency in robot motion sequence generation in existing technologies are solved. This achieves high-precision, natural and smooth motion generation, reducing data costs and deployment cycle.

CN121544764APending Publication Date: 2026-02-17AGIBOT INNOVATION (SHANGHAI) TECHNOLOGY CO LTD
4 Cites 0 Cited by

Patent Information

Application Number
CN202511526481.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-10-23
Publication Date
2026-02-17

AI Technical Summary

Technical Problem

Existing diffusion models struggle to flexibly embed keyframe constraints in robot motion sequence generation, suffer from insufficient accuracy in local pose and end-effector contact, and have lengthy inference steps, resulting in low generation efficiency.

Method used

By constructing a mask matrix aligned with the spatiotemporal dimensions of the motion sequence and combining it with a diffusion model, precise control of the robot's motion sequence is achieved, including control at the body region level, joint group level, and single joint level. This reduces the dependence on large-scale paired training data and utilizes the diffusion model for adaptive fine-tuning.

Benefits of technology

It achieves partial attitude control of any joint at any time, generating motion that satisfies precise spatial constraints and is natural and smooth, reducing data costs and deployment cycle, and improving generation efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a robot motion sequence generation method, a storage medium and electronic equipment, and relates to the field of computer animation. The robot motion sequence generation method comprises the following steps: determining a first motion sequence; a space-time mask matrix corresponding to the first motion sequence is constructed, the dimension of the space-time mask matrix corresponds to the time dimension and the space dimension of the first motion sequence, and elements in the space-time mask matrix are used for indicating to maintain or repair motion data of corresponding space-time positions in the first motion sequence; and processing the first motion sequence by using a diffusion model based on the space-time mask matrix to obtain a second motion sequence of the robot.
Need to check novelty before this filing date? Find Prior Art