IP Library Granted Patent US 12,440,911
Granted Patent B2
US 12,440,911 · App. 17/070,652 · Granted Oct 14, 2025

Robotic welding systems

Inventors: Haruhiko Harry Asada (Lincoln, MA); Haruhiko Eto (Yokosuka, JP)
Assignees: Massachusetts Institute of Technology; SUMITOMO HEAVY INDUSTRIES, LTD.
B23K9/0953B23K9/0956B23K37/0247
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 12,440,911
App. No.
17/070,652
Granted
Oct 14, 2025
Kind
B2
Abstract

A robotic welding systems and related methods are described. In some embodiments, a robotic welding system may generate a target trajectory based at least partly on a trajectory of a welding torch during manual operation of the welding torch; and operate one or more actuators of the system to control movement of the welding torch based at least partly on the target trajectory.

Claims (18)

1. A robotic welding system comprising:

a welding torch;

a support configured to support the welding torch during a welding operation; one or more actuators operatively coupled to the support, wherein the one or more actuators are configured to control a movement of the welding torch in one or more directions;

an input device configured to receive operator input related to manual operation of the welding torch, wherein the operator input includes manual operation of repeatedly moving the welding torch along a commanded trajectory by an operator; and

a processor operatively coupled to the one or more actuators and the input device, wherein the processor is configured to perform the steps of:

automatically estimating a repetitive trajectory based at least partially on the commanded trajectory, and approximating the repetitive trajectory as a target trajectory during the manual operation of moving the welding torch along the commanded trajectory; and

operating the one or more actuators to control movement of the welding torch based at least partly on the target trajectory upon approximating the repetitive trajectory as the target trajectory.

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

operate the one or more actuators based at least partly on the target trajectory in response to an estimation of the repetitive trajectory converging with the commanded trajectory of the welding torch.

3. The robotic welding system of claim 2 , wherein the processor is configured to operate the one or more actuators based on the commanded trajectory prior to the repetitive trajectory converging with the commanded trajectory, and wherein the processor is configured to not use the commanded trajectory to operate the one or more actuators after the repetitive trajectory converges with the commanded trajectory.

4. The robotic welding system of claim 2 , wherein the processor is configured to output an indication to a user when the robotic welding system transitions from the manual operation based on the commanded trajectory to autonomous operation based on the target trajectory.

5. The robotic welding system of claim 2 , wherein the processor is configured to determine an error between the repetitive trajectory and the commanded trajectory of the welding torch, and wherein the processor is configured to transition to operating the one or more actuators based at least partly on the target trajectory when the error between the repetitive trajectory and the commanded trajectory is below a predetermined threshold error.

6. The robotic welding system of claim 1 , wherein the processor is configured to estimate a frequency of the repetitive trajectory based at least partly on the operator input related to the manual operation of the welding torch, and wherein the processor is configured to generate the target trajectory based at least partly on the estimated frequency.

7. The robotic welding system of claim 6 , wherein the processor is configured to generate an initial estimate of the target trajectory based at least partly on a set of movements of the welding torch, and wherein the processor is configured to generate the target trajectory based at least partly on the initial estimate in real-time.

8. The robotic welding system of claim 1 , wherein the support is disposed on a self-propelled carriage.

9. The robotic welding system of claim 1 , wherein approximating the repetitive trajectory as the target trajectory comprises:

generating an initial target trajectory based at least partly on the commanded trajectory of the welding torch during manually operating the welding torch along the commanded trajectory; and

updating the initial target trajectory, upon generating the initial target trajectory, to generate an updated target trajectory by manually operating the welding torch along the commanded trajectory for at least one more time.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 24, 2022
From: ASADA, HARUHIKO HARRY
To: MASSACHUSETTS INSTITUTE OF TECHNOLOGY
Reel/Frame 059387/0947 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 17, 2021
From: ETO, HARUHIKO
To: MASSACHUSETTS INSTITUTE OF TECHNOLOGY; SUMITOMO HEAVY INDUSTRIES LIMITED
Reel/Frame 057510/0209 →
Continuity (2)
Provisional Application 63067973 · Aug 20, 2020
Related Publication 20220055138A1 · Feb 24, 2022
References Cited (14)
US 6212443B1 · Nagata et al. · 2001 [cited by applicant]
US 10564635B2 · Sato · 2020 [cited by examiner]
US 10888996B2 · Tabandeh · 2021 [cited by examiner]
US 11345019B2 · Hane · 2022 [cited by examiner]
US 20060069466A1 · Kato et al. · 2006 [cited by applicant]
US 20150217449A1 · Meier et al. · 2015 [cited by applicant]
US 20180095640A1 · Albright · 2018 [cited by examiner]
US 20180348744A1 · Cortsen · 2018 [cited by examiner]
US 20200384563A1 · Jo · 2020 [cited by examiner]
US 20210086285A1 · Nadler · 2021 [cited by examiner]
JP 200151712 · 2001 [cited by applicant]
JP 2008302386A · 2008 [cited by examiner]
International Search Report for PCT/US 20/55582 mailed on Jan. 22, 2021. [cited by applicant]
Eto et al., Seamless Manual-to-Autopilot Transition: An Intuitive Programming Approach to Robotic Welding. 2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), New Delhi, India,… [cited by applicant]