Jeannette Bohg
Max Planck Institute for Intelligent Systems, Stanford University, KTH Royal Institute of Technology, Intel (United States), Institute of Occupational Medicine, Corvallis Environmental Center, University of Southern California, Max Planck Society, Artificial Intelligence in Medicine (Canada)
Papers
103
Total Citations
6,337
H-Index
33
About
Jeannette Bohg is a prominent robotics and machine learning researcher whose work sits at the intersection of robot perception, manipulation, and deep learning. Best known for her foundational contributions to robotic grasping, her 2016 survey on data-driven grasp synthesis (554 citations) and its 2023 deep learning successor (215 citations) have become essential references for researchers entering the field. Her early work on learning grasping points with shape context (2009) helped establish data-driven approaches as a viable paradigm long before they became mainstream. Bohg's research has expanded ambitiously into dynamic 3D scene understanding, with MeteorNet (225 citations) offering novel architectures for processing point cloud sequences, and into manipulation of deformable objects through self-supervised state estimation. More recently, she has embraced the integration of large language models into robotics, contributing to TidyBot and Text2Motion, demonstrating how natural language can guide feasible robot task planning. Her involvement in landmark collaborative efforts—including the influential Foundation Models report (2,177 citations) and Open X-Embodiment (119 citations)—reflects her broad impact on AI and embodied intelligence. Her body of work consistently bridges theoretical innovation with practical robotic application.
Research Focus
Key Achievements
Top Papers
- 1On the Opportunities and Risks of Foundation Models2,177 citations · 2021
- 21Data-Driven Grasp Synthesis- A Survey554 citations · 2016
- 3MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences225 citations · 2019
- 4Deep Learning Approaches to Grasp Synthesis: A Review215 citations · 2023
- 5Text2Motion: from natural language instructions to feasible plans197 citations · 2023
- 6TidyBot: personalized robot assistance with large language models189 citations · 2023
- 7
- 8Learning grasping points with shape context142 citations · 2009
- 9OpenGRASP: A Toolkit for Robot Grasping Simulation121 citations · 2010
- 10