IP Library › Granted Patent US 12,194,507
Granted Patent B2
US 12,194,507 · App. 18/126,309 · Granted Jan 14, 2025

Detection of heavy objects using computer vision

Inventors: Darshan Hegde (Foster City, CA); Harry Zhe Su (Union City, CA); Talbot Morris-Downing (Redwood City, CA)
Assignee: Dexterity, Inc.
B07C5/3422B07C1/04B07C5/10B07C5/28G06V20/60B07C2501/0063G06V2201/06
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 12,194,507
App. No.
18/126,309
Filed
Mar 24, 2023
Granted
Jan 14, 2025
Kind
B2
Art Unit
3653
USPC
209/577
Abstract

The present application discloses a system, a method, and a computer system for detecting objects that require special handling. The method includes (i) receiving image data from one or more cameras associated with a source conveyor configured to convey items to a pick location, (ii) determining, based at least in part on the image data, that an item requiring special handling has entered the source conveyor, and (iii) providing an output indicating that the item requiring special handling has been detected.

Claims (46)

1. A robotic system, comprising:

a communication interface configured to receive image data from one or more cameras associated with a source conveyor; and

one or more processors coupled to the communication interface and configured to:

determine, based at least in part on the image data, that an item requiring special handling has entered the source conveyor configured to convey the item to a singulation pick location; and

in response to determining that the item requiring special handling has entered the source conveyor, cause a plan for singulating the item to be updated to change a manner in which the item is handled, wherein:

the item requiring special handling corresponds to an item that is too heavy to be lifted by a robotic arm controlled by the one or more processors; and

causing the plan for singulating the item to be updated to change a manner in which the item is handled comprises determining an updated plan according to which the robotic arm is controlled to partially lift the item and push/pull the item to a destination location.

2. The robotic system of claim 1 , wherein the item requiring special handling corresponds to an item having a weight that exceeds a predefined weight threshold.

3. The robotic system of claim 1 , wherein:

the one or more processors are further configured to determine that the item is too heavy based on one or more of a perceived size or perceived shape.

4. The robotic system of claim 3 , wherein the one or more processors are further configured to:

determine the perceived size or the perceived shape based at least in part on the image data.

5. The robotic system of claim 3 , wherein:

the one or more processors are further configured to:

obtain sensor data from one or more other sensors in a workspace associated with the pick location; and

the perceived size or the perceived shape is further determined based at least in part on the sensor data.

6. The robotic system of claim 3 , wherein:

the one or more processors are further configured to:

obtain sensor data from one or more sensors in a workspace associated with the pick location; and

determine a weight of the item based at least in part on the sensor data.

7. The robotic system of claim 1 , wherein the one or more processors are further configured to:

identify the item based at least in part on the image data; and

determine a weight of the item based at least in part on the identifying of the item.

8. The robotic system of claim 7 , wherein determining the weight of the item based at least in part on the identifying of the item comprises:

obtaining an item identifier for the item; and

querying a mapping of item identifiers to weights to obtain the weight of the item.

9. The robotic system of claim 1 , wherein the one or more processors are further configured to:

obtain information on a label of the item based at least in part on the image data; and

determine a weight of the item based at least in part on the information on the label.

10. The robotic system of claim 1 , wherein the one or more processors are further configured to:

obtain information on a label of the item based at least in part on the image data; and

determine that the item is to be subject to special handling based at least in part on the information on the label.

11. The robotic system of claim 1 , wherein an updated plan for special handling the item comprises moving the item to a rejection path for manual handling.

12. The robotic system of claim 1 , wherein an updated plan for special handling the item comprises pushing the item onto a destination conveyor.

13. A method, comprising:

receiving, by one or more processors, image data from one or more cameras associated with a source conveyor configured to convey items to a pick location;

determining, based at least in part on the image data, that an item requiring special handling has entered the source conveyor; and

in response to determining that the item requiring special handling has entered the source conveyor, causing a plan for singulating the item to be updated to change a manner in which the item is handled, wherein:

the item requiring special handling corresponds to an item that is too heavy to be lifted by a robotic arm controlled by the one or more processors; and

causing the plan for singulating the item to be updated to change a manner in which the item is handled comprises determining an updated plan according to which the robotic arm is controlled to partially lift the item and push/pull the item to a destination location.

14. A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:

receiving, by one or more processors, sensor data from one or more sensors associated with a source conveyor configured to convey items to a pick location;

determining, based at least in part on the sensor data, that an item that is too heavy to be lifted by a robotic arm controlled by the one or more processors has entered the source conveyor; and

in response to determining that the item requiring special handling has entered the source conveyor, causing a plan for singulating the item to be updated to change a manner in which the item is handled, wherein:

the item requiring special handling corresponds to an item that is too heavy to be lifted by a robotic arm controlled by the one or more processors; and

causing the plan for singulating the item to be updated to change a manner in which the item is handled comprises determining an updated plan according to which the robotic arm is controlled to partially lift the item and push/pull the item to a destination location.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 25, 2023
From: HEGDE, DARSHAN; SU, HARRY ZHE; MORRIS-DOWNING, TALBOT
To: DEXTERITY, INC.
Reel/Frame 063761/0099 →
Continuity (2)
Provisional Application 63323822 · Mar 25, 2022
Related Publication 20230321694A1 · Oct 12, 2023
References Cited (7)
US 11205059B2 · Wagner · 2021 [cited by examiner]
US 20120308343A1 · Habisreitinger · 2012 [cited by applicant]
US 20210122586A1 · Sun · 2021 [cited by applicant]
US 20230150777A1 · Skyum · 2023 [cited by examiner]
US 20230271791A1 · Graston · 2023 [cited by examiner]
CN 209697521 · 2019 [cited by applicant]
CN 110976317 · 2020 [cited by applicant]
Cited By (1)
US 12,558,712