IP Library Granted Patent US 12,643,237
Granted Patent B2
US 12,643,237 · App. 18/740,522 · Granted Jun 2, 2026

Workplace monitoring and semantic entity identification for safe machine operation

Inventors: Clara Vu (Cambridge, MA); Scott Denenberg (Newton, MA); Marek Wartenberg (Westbrook, ME); Paul Jakob Schroeder (Chapel Hill, NC); Ilya A. Kriveshko (Boxborough, MA); Alberto Moel (Cambridge, MA)
Assignee: Symbotic LLC
B25J9/1694B25J9/1666B25J9/1676B25J9/1697G01S7/4808G01S17/04G01S17/87G01S17/89G06T17/10G01V8/20G05B2219/40202G06T17/05Y10S901/47Y10S901/49
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,643,237
App. No.
18/740,522
Granted
Jun 2, 2026
Kind
B2
Abstract

A system includes sensors, memory, and a processor. The sensors are configured to capture images of a workspace, and the memory is configured to store the images and a model of machinery located within the workspace. The processor is configured to generate a spatial representation of the workspace based on the captured images. The processor is also configured to identify non-machinery entities within the workspace and, for each of the identified entities, generate an object that specifies a spatial extent of the respective entity and a protective separation distance for the entity. Further, the processor is configured to recognize an interaction between the entities and merge the corresponding objects into a merged object specifying a protective separation distance therefor. Moreover, the processor is configured to control operation of the machinery in accordance with a safety protocol and the protective separation distance for the merged object.

Claims (70)

1 . A system for monitoring a workspace, the system comprising:

sensors configured to capture images of a workspace;

memory configured to store (i) captured images from the sensors and (ii) a model of machinery located within the workspace, wherein the model comprises movement capabilities of the machinery; and

a processor configured to:

generate a spatial representation of the workspace based on the captured images;

identify first and second non-machinery entities within the workspace;

generate a first object that specifies attributes of the first non-machinery entity comprising (i) a spatial extent of the first non-machinery entity and (ii) a protective separation distance for the first non-machinery entity;

generate a second object that specifies attributes of the second non-machinery entity comprising (i) a spatial extent of the second non-machinery entity and (ii) a protective separation distance for the second non-machinery entity;

recognize an interaction between the first and second non-machinery entities in the workspace;

responsive to recognizing the interaction, merge the first and second objects into a merged object that specifies a protective separation distance for the merged object; and

control operation of the machinery in accordance with (i) a safety protocol and (ii) the protective separation distance for the merged object.

2 . The system of claim 1 , wherein the processor is further configured to:

recognize dissociation between the first and second non-machinery entities; and

generate and store separate objects corresponding to the first and second non-machinery entities and specifying at least some different attributes thereof.

3 . The system of claim 1 , wherein:

the first object further specifies a first associated computer-executable method; and

the second object further specifies a second associated computer-executable method.

4 . The system of claim 3 , wherein:

the first associated computer-executable method comprises a first method for generating a hierarchically superior object that comprises the first object; or

the second associated computer-executable method comprises a second method for generating a hierarchically superior object that comprises the second object.

5 . The system of claim 1 , wherein at least one of the first and second non- machinery entities is a non-human entity.

6 . The system of claim 1 , wherein:

the protective separation distance for the first non-machinery entity is different from the protective separation distance for the second non-machinery entity; and

the protective separation distance for the merged object is greater than each of (i) the protective separation distance for the first non-machinery entity and (ii) the protective separation distance for the second non-machinery entity.

7 . The system of claim 1 , wherein the interaction between the first and second non-machinery entities corresponds to contact between the entities.

8 . The system of claim 1 , wherein the interaction between the first and second non-machinery entities corresponds to proximity of the entities.

9 . The system of claim 1 , wherein:

the processor is further configured to generate and store a zone object that specifies a zone within the workspace to be treated as empty; and

controlling operation of the machinery is further in accordance with the zone object.

10 . The system of claim 1 , the processor is further configured to:

generate a display of at least a portion of the workspace;

receive a command indicating entities in the workspace to be merged; and

merge objects associated with the entities indicated by the command into a single object.

11 . The system of claim 10 , wherein the processor is further configured to receive commands to change at least one attribute associated with the single object.

12 . The system of claim 1 wherein the processor is further configured to:

generate a display of at least a portion of the workspace;

receive commands indicating entities in the workspace associated with a merged object; and

generate and store separate objects corresponding to the indicated entities; and

delete the merged object.

13 . The system of claim 1 , wherein:

the processor is responsive to an external tracking system; and

the processor is further configured to identify at least the first or second non-machinery entity based on data from the external tracking system.

14 . The system of claim 13 , wherein the external tracking system includes at least one of (i) proximity sensors, (ii) IR break-beam sensors, or (iii) a 2D or 3D vision system.

15 . The system of claim 13 , wherein at least some of the first and second non-machinery entities include a feature to permit object and position tracking by the external tracking system.

16 . The system of claim 15 , wherein the feature is at least one of (i) an ultra-wideband transponder, (ii) an RFID tag, (iii) a barcode, or (iv) a QR code.

17 . The system of claim 13 , wherein the processor is further configured to make data available to a controller of the first or second non-machinery entity based on identifying the first or second non-machinery entity.

18 . A method of monitoring a workspace, the method comprising:

providing sensors configured to capture images of a workspace;

storing (i) captured images from the sensors and (ii) a model of machinery located within the workspace, wherein the model comprises movement capabilities of the machinery;

generating a spatial representation of the workspace based on the captured images;

identifying first and second non-machinery entities within the workspace;

generating a first object that specifies attributes of the first non-machinery entity comprising (i) a spatial extent of the first non-machinery entity and (ii) a protective separation distance for the first non-machinery entity;

generating a second object that specifies attributes of the second non-machinery entity comprising (i) a spatial extent of the second non-machinery entity and (ii) a protective separation distance for the second non-machinery entity;

recognizing an interaction between the first and second non-machinery entities in the workspace;

responsive to recognizing the interaction, merging the first and second objects into a merged object that specifies a protective separation distance for the merged object; and

controlling operation of the machinery in accordance with (i) a safety protocol and (ii) the protective separation distance for the merged object.

19 . The method claim 18 , further comprising:

recognizing dissociation between the first and second non-machinery entities;

generating and storing separate object data structures corresponding to the first and second non-machinery entities and specifying at least some different attributes.

20 . A system for monitoring a workspace, the system comprising:

sensors configured to capture images of a workspace;

memory configured to store (i) captured images from the sensors and (ii) a model of machinery located within the workspace, wherein the model comprises movement capabilities of the machinery; and

a processor configured to:

generate a spatial representation of the workspace based on the captured images;

identify first and second non-machinery entities within the workspace;

generate a first object that specifies attributes of the first non-machinery entity comprising (i) a spatial extent of the first non-machinery entity and (ii) a protective separation distance for the first non-machinery entity;

generate a second object that specifies attributes of the second non-machinery entity comprising (i) a spatial extent of the second non-machinery entity and (ii) a protective separation distance for the second non-machinery entity;

monitor a distance between the first and second non-machinery entities; and

control operation of the machinery in accordance with (i) the monitored distance,

(ii) the attributes of the first non-machinery entity, and (iii) the attributes of the second non-machinery entity.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 4, 2024
From: VEO ROBOTICS, INC.
To: SYMBOTIC LLC
Reel/Frame 068839/0710 →
Continuity (5)
Continuation 17538501 · Nov 30, 2021
Continuation In Part 17101792 · Nov 23, 2020
Continuation 15889767 · Feb 6, 2018
Provisional Application 63152113 · Feb 22, 2021
Related Publication 20240424678A1 · Dec 26, 2024
References Cited (76)
US 6212444B1 · Kato et al. · 2001 [cited by applicant]
US 6297844B1 · Schatz et al. · 2001 [cited by applicant]
US 6816755B2 · Habibi et al. · 2004 [cited by applicant]
US 7336814B2 · Boca et al. · 2008 [cited by applicant]
US 8154590B2 · Kressel et al. · 2012 [cited by applicant]
US 8253792B2 · Wells et al. · 2012 [cited by applicant]
US 8437535B2 · Boca et al. · 2013 [cited by applicant]
US 8559699B2 · Boca · 2013 [cited by applicant]
US 8700197B2 · Plociennik et al. · 2014 [cited by applicant]
US 9043025B2 · Brooks et al. · 2015 [cited by applicant]
US 9122266B2 · Franke · 2015 [cited by examiner]
US 9240070B2 · Anderson-Sprecher et al. · 2016 [cited by applicant]
US 9283678B2 · Kuffner, Jr. et al. · 2016 [cited by applicant]
US 9452531B2 · Kikkeri et al. · 2016 [cited by applicant]
US 9691151B1 · Anderson-Sprecher et al. · 2017 [cited by applicant]
US 9734401B2 · Hunt · 2017 [cited by applicant]
US 9740193B2 · Hunt · 2017 [cited by applicant]
US 9827681B2 · Naitou et al. · 2017 [cited by applicant]
US 10445944B2 · Galera et al. · 2019 [cited by applicant]
US 20050055134A1 · Okuda · 2005 [cited by examiner]
US 20050207618A1 · Wohler et al. · 2005 [cited by applicant]
US 20080021597A1 · Merte et al. · 2008 [cited by applicant]
US 20080152192A1 · Zhu et al. · 2008 [cited by applicant]
US 20090015663A1 · Doettling et al. · 2009 [cited by applicant]
US 20100092032A1 · Boca · 2010 [cited by examiner]
US 20110264266A1 · Kock · 2011 [cited by applicant]
US 20120022688A1 · Wong et al. · 2012 [cited by applicant]
US 20120022689A1 · Kapoor · 2012 [cited by examiner]
US 20130201292A1 · Walter et al. · 2013 [cited by applicant]
US 20140093130A1 · Dasu et al. · 2014 [cited by applicant]
US 20150049911A1 · Doettling et al. · 2015 [cited by applicant]
US 20150131896A1 · Hu · 2015 [cited by examiner]
US 20150269427A1 · Kim et al. · 2015 [cited by applicant]
US 20150293600A1 · Sears · 2015 [cited by examiner]
US 20160016315A1 · Kuffner, Jr. · 2016 [cited by examiner]
US 20160167231A1 · Nakayama · 2016 [cited by examiner]
US 20160282126A1 · Watts et al. · 2016 [cited by applicant]
US 20160354927A1 · Kikkeri · 2016 [cited by examiner]
US 20170057095A1 · Oestergaard et al. · 2017 [cited by applicant]
US 20170151676A1 · Atherton et al. · 2017 [cited by applicant]
US 20170197311A1 · Garcia · 2017 [cited by examiner]
US 20170210017A1 · Yamamoto · 2017 [cited by examiner]
US 20170302905A1 · Shteinfeld et al. · 2017 [cited by applicant]
US 20170334063A1 · Komatsuzaki et al. · 2017 [cited by applicant]
US 20170334066A1 · Levine et al. · 2017 [cited by applicant]
US 20170334076A1 · Bordegnoni et al. · 2017 [cited by applicant]
US 20170341231A1 · Tan et al. · 2017 [cited by applicant]
US 20170355079A1 · Takahashi · 2017 [cited by applicant]
EP 3248740A1 · 2017 [cited by applicant]
WO 2016122840A1 · 2016 [cited by applicant]
WO 2017199261A1 · 2017 [cited by applicant]
WO 2017203937A1 · 2017 [cited by applicant]
WO 2017207436A1 · 2017 [cited by applicant]
International Search Report for International Application No. PCT/US2018/016991 dated May 16, 2018, 12 pages. [cited by applicant]
Anandan, Tanya M. “The Shrinking Footprint of Robot Safety,” Robotics Online, Oct. 6, 2014, 9 pages. [cited by applicant]
Anandan, Tanya M. “The End of Separation: Man and Robot as Collaborative Coworkers on the Factory Floor,” Robotics Online, Jun. 6, 2013, 8 pages. [cited by applicant]
Cui, et al. “Robotics Safety: An Engineering Teaching Module,” University of Ontario, Institute of Technology, Minerva Canada, Mar. 2014, 39 pages. [cited by applicant]
Felzner, et al. “Obstacle Detection and Tracking for Safe Human-Robot Interaction Based on Multi-Sensory Point Clouds.” [cited by applicant]
Flacco, et al. “A Depth Space Approach to Human-Robot Collision Avoidance,” 2012 IEEE International Conference on Robotics and Automation, May 14-18, 2012, 8 pages. [cited by applicant]
Frank, Rudiger, Dr. “Modular Sensor System for Safe Robots,” https://www.automation.com/automation-news/article/modular-sensor-system-for-safe-robots, Nov. 25, 2017, 14 pages. [cited by applicant]
Frese, et al. “Multi-Sensor Obstacle Tracking for Safe Human-Robot Interation,” Fraunhofer Institute of Optics, System Technologies and Image Explitation IOSB, 2014, 8 pages. [cited by applicant]
Graham, et al. “A Sensory-Based Robotic Safety System,” IEE Proceedings, vol. 132, Pt D, No. 4, Jul. 1985, 7 pages. [cited by applicant]
Graham, et al. “A Safety and Collision Avoidance System for Industrial Robots,” IEEE Transactions on Industry Applications, vol. IA-22, No. 1, Jan./Feb. 1986, 9 pages. [cited by applicant]
Kock, et al. “Taming the robot,” Robotic Highlights, ABB Review, Apr. 2006, 4 pages. [cited by applicant]
Lacevic, et al. “Kinetostatic danger field—A novel safety assessment for human-robot interation,” ResearchGate, Jun. 9, 2016, 8 pages. [cited by applicant]
Lasota, et al. “A Survey of Methods for Safe Human-Robot Interation,” Foundations and Trends in Robotics, vol. 5, No. 4 (2014), 92 pages. [cited by applicant]
Lasota, et al. “Towards Safe Close-Proximity Human-Robot Interaction with Standard Industrial Robots,” IEEE, 2014, 7 pages. [cited by applicant]
Lenz, et al. “Fusing multiple Kinects to survey shared Human-Robot-Workspaces,” Robotics and Embedded Systems Department of Informatics Technische Universir-at Munchen, 6 pages. [cited by applicant]
Murray, et al. “Robot Motion Planning on a Chip,” Departments of Computer Science and Electrical & Computer Engineering, Duke University, 9 pages. [cited by applicant]
Pilz, GB. “Safe human-robot collaboration: from theory to practice,” https://www.pilz.com/en-GB/company/news/article/084837, Aug. 6, 2015, 4 pages. [cited by applicant]
Rybski, et al. “Sensor Fusion for Human Safety in Industrial Workcells,” Camegie Mellon University Research Showcase @ CMU, Oct. 2012, 9 pages. [cited by applicant]
ABB Robotics Produce Management, “SafeMove2,” Jul. 24, 2017, 25 pages. [cited by applicant]
ABB Robotics Produce Management, “SafeMove2 Protecting operators and enhancing robot safety,” abb.com/robotics, 2 pages. [cited by applicant]
Vogel, et al. “A Projection-based Sensor System for Safe Physical Human-Robot Collaboration,” 2013 IEEE/RSJ International Conference on Intelligent Robotcs and Systems (ROS), Nov. 3-7, 2013, 6 pages. [cited by applicant]
Zanchettin, et al. “Safety in Human-Robot Collaborative Manufacturing Environments: Metrics and Control,” IEEE Transactions on Automation Science and Engineering, vol. 13, No. 2, Apr. 2016, 12 pages. [cited by applicant]
Christiemin, et al. “Safety Critical Robot Programming and Testing for Operations in Industrial Co-production,” IEEE International Symposium on Software Reliability Engineering Workshops, 2014, 4 pages. [cited by applicant]