Sim-to-real Transfer

Sim-To-Real Transfer is a research problem in robot learning that concerns enabling models or control policies trained in simulation to achieve reliable performance when deployed on the corresponding physical robotic systems by mitigating discrepancies between simulated and real-world environments, dynamics, and perception.

911

Publications

58K

Citations

3.4K

Authors

918

Institutions

Publications per year

2017–2026

594

Authors

3.4K

  1. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    14 publications · 3.9K citations

    13

    h-index

  2. SL
    Sergey Levine

    University of California, Berkeley, United States

    14 publications · 1.1K citations

    12

    h-index

  3. NH
    Nicolas Heess

    Google (United States), United States

    11 publications · 975 citations

    11

    h-index

  4. YB
    Yunfei Bai

    Google (United States), United States

    11 publications · 1.2K citations

    10

    h-index

  5. DB
    Dhruv Batra

    Georgia Institute of Technology, United States

    8 publications · 615 citations

    8

    h-index

1–5 of 3.4K

Venues

  1. arXiv (Cornell University)

    Repository · 113 publications · 5.5K citations

    36

    h-index

  2. IEEE Robotics and Automation Letters

    41 publications · 2.3K citations

    29

    h-index

  3. Nurse Education Today

    13 publications · 686 citations

    13

    h-index

  4. 2022 International Conference on Robotics and Automation (ICRA)

    Conference · 12 publications · 425 citations

    12

    h-index

  5. IEEE Transactions on Robotics

    11 publications · 879 citations

    11

    h-index

1–5