Workplace monitoring and semantic entity identification for safe machine operation

US12049014B2 · kind B2 · utility

Assignee

• VEO ROBOTICS, INC. · US

Inventors

• Clara Vu · Cambridge, US
• Scott Denenberg · Boston, US
• Marek WARTENBERG · Chelsea, US
• Paul Jakob Schroeder · Brookline, US
• Ilya A. Kriveshko · Littleton, US
• Alberto Moel · Cambridge, US

Key dates

• Filing date: Nov 30, 2021
• Grant date: Jul 30, 2024
• Expiry date: Jan 6, 2043

Classification

• Technology area (CPC Y): Emerging Cross-Sectional Technologies
• CPC primary: Y10S901/49
• WIPO field: Measurement
• WIPO sector: Instruments

Abstract

An integrated system and method for monitoring a workspace, classifying regions therein, dynamically identifying safe states, and identifying and tracking workpieces utilizes semantic analysis of a robot in the workspace and identification of the workpieces with which it interacts, as well as a semantic understanding of entity properties both governing and arising from interaction with other entities for control purposes. These properties may be stored in a profile corresponding to the entity; depending on the implementation, the profile and methods associated with the entity may be stored in a data structure corresponding to the entity “class.” Volumetric regions (e.g., voxels) corresponding to each entity may be tracked and used to implement object methods and/or control methods. For example, machinery may be controlled in accordance with the attributes specified by the objects corresponding to identified entities in a monitored workspace.