Sergey Levine

This inventor holds 35 USPTO granted patents and 12 published patent applications, plus 1 CIPO patent and 10 EPO patents, primarily in Robotic Control. Top assignees: Google Inc., University of California, X Development LLC. Active years: 2018-2026.

USPTO Granted Patents = 35 (Patent Applications = 12)

% Patents Active = 100.0

CIPO Patents = 1 (Patent Applications = 1)

EPO Patents = 10 (Patent Applications = 19)

Average Co-Inventor Count = 4.2

ph-index = 6

Forward Citations = 153(Granted Patents)

Location History:

Mountain View, CA (US) (2023)
Berkeley, CA (US) (2018 - 2024)

Company Filing History:

University of California

Toyota Research Institute, Inc.

patents

where one patent can have more than one assignee

Years Active: 2018-2026

Loading Chart...

Areas of Expertise:

Reinforcement Learning

Imitation Learning

Visual Servoing

Robotic Manipulation

Hierarchical Learning

Control Policies

Tactile Sensors

Simulation Training

Meta-Learning

Video Prediction

Semantic Grasping

Agent Navigation

35 patents (USPTO):Sort by Forward CitationsExplore Patents

1. 12686134 - Natural language control of a robot (2026-07-21),

2. 12675670 - Offline primitive discovery for accelerating data-driven reinforcement learning (2026-07-07),

3. 12611768 - Viewpoint invariant visual servoing of robot end effector using recurrent neural network (2026-04-28),

4. 12587675 - Pixel-level video prediction with improved performance and efficiency (2026-03-24),

5. 12585917 - Reinforcement learning using advantage estimates (2026-03-24),

6. 12498677 - Mitigating reality gap through training a simulation-to-real model using a vision-based robot task model (2025-12-16),

7. 12479093 - Data-efficient hierarchical reinforcement learning (2025-11-25),

8. 12430551 - Reinforcement learning algorithm search (2025-09-30),

9. 12240113 - Deep reinforcement learning for robotic manipulation (2025-03-04),

10. 12235179 - Multi-directional high-resolution optical tactile sensors (2025-02-25),

11. 12226920 - System(s) and method(s) of using imitation learning in training and refining robotic control policies (2025-02-18),

12. 12103564 - Planning-aware prediction for control-aware autonomous driving modules (2024-10-01),

13. 12083678 - Efficient adaption of robot control policy for new task using meta-learning based on meta-imitation learning and meta-reinforcement learning (2024-09-10),

14. 11992945 - System and methods for training robot policies in the real world (2024-05-28),

15. 11992944 - Data-efficient hierarchical reinforcement learning (2024-05-28),

Title: Sergey Levine - Innovator from Berkeley, CA

Introduction: Sergey Levine is a renowned inventor based in Berkeley, CA, known for his groundbreaking contributions to the field of robotics and artificial intelligence.

Latest Patents: Sergey Levine holds several patents related to machine learning algorithms for robotic control systems, enhancing efficiency and adaptability in various applications.

Career Highlights: With a background in computer science and engineering, Sergey Levine has made significant strides in developing autonomous systems that can learn and adapt to complex environments. His work has been instrumental in advancing the capabilities of robotic technologies.

Collaborations: Throughout his career, Sergey Levine has collaborated with leading research institutions and tech companies to further explore the intersection of AI and robotics. His partnerships have led to innovative solutions that are shaping the future of automation.

Conclusion: Sergey Levine's dedication to pushing the boundaries of AI and robotics has solidified his reputation as a visionary inventor in the field. His work continues to inspire new generations of innovators to explore the endless possibilities of intelligent machines.