多智能体协作的3D对象检测方法

By setting up perception, prediction, and fusion modules in a multi-agent system, and utilizing information interaction at critical moments and historical information correction, the problem of communication bandwidth limitation is solved, and the accuracy and robustness of 3D object detection are improved.

CN116823939BActive Publication Date: 2026-07-17SHANGHAI ARTIFICIAL INTELLIGENCE INNOVATION CENT +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHANGHAI ARTIFICIAL INTELLIGENCE INNOVATION CENT
Filing Date
2023-04-12
Publication Date
2026-07-17

Smart Images

  • Figure CN116823939B_ABST
    Figure CN116823939B_ABST
Patent Text Reader

Abstract

本发明提供了一种多智能体协作的3D对象检测方法，包括：在第一智能体上设置感知模块、预测模块和融合模块，在第二智能体上设置感知模块；由第一智能体和第二智能体的感知模块基于传感器信息对周围物体的信息进行感知，分别得到第一感知信息和第二感知信息，其中第二感知信息作为第一智能体的交互信息；由第一智能体的预测模块基于周围物体的历史信息对周围物体的当前状态进行预测，得到预测结果；以及由第一智能体的融合模块与第二智能体进行信息交互，以使得第一感知信息与所述交互信息进行融合，以及使得第一感知信息与预测结果进行融合。
Need to check novelty before this filing date? Find Prior Art