应用于半结构化环境的机器人自主运动规划方法及系统
CN117621049BActive Publication Date: 2026-07-17EAST CHINA UNIV OF SCI & TECH
View PDF 2 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- EAST CHINA UNIV OF SCI & TECH
- Filing Date
- 2023-10-18
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing robotic arms suffer from high complexity in motion planning algorithms in semi-structured environments, lack flexibility and safety, and struggle to cope with environmental changes and new obstacles.
Method used
By combining neural networks and artificial potential field methods, collision-free paths are generated through scene encoding, motion planning, fusion sampling, and Gaussian resampling, and repaired when necessary using an artificial potential field method enhanced by an ambient potential field.
Benefits of technology
It reduces the complexity of the planning algorithm, improves the flexibility and safety of the robotic arm in semi-structured environments, reduces deployment costs, and enables rapid trajectory planning when the environment changes.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN117621049B_ABST
Abstract
本发明提供了一种应用于半结构化环境的机器人自主运动规划方法及系统，包括：采集机器人工作环境的多视图矩阵；通过场景编码器对多视图矩阵进行编码处理，得到对应的环境编码和机器人状态矩阵，并重构成对应的状态列表进行运动规划，得到多个关于下一个机器人状态的高斯权重、均值和方差；再进行融合处理，生成新的机器人状态矩阵；检查新生成的机器人状态矩阵和上一个机器人状态矩阵是否发送碰撞，若是，则记录碰撞点并进行修复；若否，则更新状态点直至当前机器人状态矩阵达到目标状态矩阵后结束规划。本发明在半结构化的工业场景下，使从事分拣、紧固工作的机械臂具有高效的自主运动规划能力，提高产线柔性、安全性，降低部署成本。
Need to check novelty before this filing date? Find Prior Art