Learning-based Grasp Synthesis

Learning-Based Grasp Synthesis is a computational framework within multi-fingered grasping that employs machine learning models to generate feasible grasp configurations by learning mappings from object or scene representations to hand poses, distinguished from analytical methods by its reliance on data-driven generalization rather than explicit physical or geometric modeling.

51

Publications

3.2K

Citations

193

Authors

71

Institutions

Publications per year

2017–2026

35

Authors

193

  1. DK
    Danica Kragić

    KTH Royal Institute of Technology, Sweden

    4 publications · 183 citations

    4

    h-index

  2. HK
    Hamidreza Kasaei

    University of Groningen, Netherlands

    3 publications · 64 citations

    3

    h-index

  3. ST
    Siyu Tang

    Max Planck Institute for Intelligent Systems, Germany

    3 publications · 258 citations

    3

    h-index

  4. JL
    Jens Lundell

    Aalto University, Finland

    3 publications · 117 citations

    3

    h-index

  5. KK
    Korrawe Karunratanakul

    ETH Zurich, Switzerland

    3 publications · 258 citations

    3

    h-index

1–5 of 193

Venues

  1. IEEE Robotics and Automation Letters

    4 publications · 205 citations

    4

    h-index

  2. Robotics and Autonomous Systems

    4 publications · 562 citations

    4

    h-index

  3. arXiv (Cornell University)

    Repository · 3 publications · 88 citations

    3

    h-index

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

    Conference · 2 publications · 47 citations

    2

    h-index

  5. Autonomous Robots

    1 publications · 14 citations

    1

    h-index

1–5