G05B 2219/40499
Reinforcement learning algorithm
G05B2219/40499 (Reinforcement learning algorithm) appears on 109 US grants and 161 published applications in this corpus.
Search patents in G05B- Granted patents
- 109
- Published applications
- 161
- Assignees
- 76
- Inventors
- 416
- Latest grant
- 18 Aug 2026
Filings by year
| Year | Granted patents | Published applications |
|---|---|---|
| 2014 | 0 | 1 |
| 2015 | 0 | 3 |
| 2016 | 1 | 1 |
| 2017 | 4 | 4 |
| 2018 | 1 | 8 |
| 2019 | 5 | 17 |
| 2020 | 12 | 13 |
| 2021 | 6 | 31 |
| 2022 | 14 | 28 |
| 2023 | 15 | 16 |
| 2024 | 20 | 17 |
| 2025 | 19 | 14 |
| 2026 | 12 | 8 |
By publication year. 2026 runs to 8 Oct.
Recent patents
- Device and method for training a machine-learning model for determining a grasp of a multi-finger gripper for manipulating an object18 Aug 2026US 12,709,002 B2Robert Bosch GmbH
- Viewpoint invariant visual servoing of robot end effector using recurrent neural network28 Apr 2026US 12,611,768 B2Google Inc.
- Category-level manipulation from visual demonstration28 Apr 2026US 12,611,770 B2Intrinsic Innovation LLC
- Method of inserting an electronic components in through-hole technology, THT, into a printed circuit board, PCB, by an industrial robot7 Apr 2026US 12,598,706 B2Fitech Sp. z o.o.
- Performance recreation system31 Mar 2026US 12,591,229 B2Aivot, LLC
- System and method to determine operational workarounds for anomalies during operation of a robotic system1 Oct 2026US 2026/0295822 A1
- Using reinforcement learning to determine optimal alignment for an optical system24 Sep 2026US 2026/0288126 A1ASML Netherlands B. V.
- Viewpoint invariant visual servoing of robot end effector using recurrent neural network6 Aug 2026US 2026/0225237 A1Google Inc.
- System and Method Suitable for Tuning a Pre-Trained Diffusion Policy of a Robot9 Jul 2026US 2026/0192446 A1Mitsubishi Electric Research Laboratories, Inc.
- Performance recreation system25 Jun 2026US 2026/0178022 A1Aivot, LLC
Most cited
By later US patents
- Artificial intelligence system for modeling and evaluating robotic success at task performance113US 10,766,137 B1Amazon Technologies, Inc. · 2020
- Artificial intelligence system for efficiently learning robotic control policies43US 10,926,408 B1Amazon Technologies, Inc. · 2021
- Artificial intelligence system for modeling and evaluating robotic success at task performance33US 10,766,136 B1Amazon Technologies, Inc. · 2020
- Controller and machine learning device13US 10,668,619 B2Fanuc Corporation · 2020
- Machine learning device, robot controller, robot system, and machine learning method for learning action pattern of human11US 10,807,235 B2Fanuc Corporation · 2020