Franziska Meier

About

Franziska Meier is a prominent robotics researcher whose work spans robot learning, motion planning, and embodied AI. Her research has significantly advanced how robots perceive, learn, and interact with dynamic, unstructured environments — challenges central to deploying intelligent systems in the real world. Meier's early contributions focused on movement primitives and skill learning, with foundational papers on movement segmentation and Dynamic Movement Primitives (DMPs) that have each garnered over 70 citations. These works established principled frameworks for decomposing and reusing complex robot behaviors. She extended this line of research into obstacle avoidance and contact-rich manipulation, including more recent work adapting DMPs through learning from demonstration. Her 2020 paper on simulation in robotics (157 citations) is among her most influential, offering a comprehensive roadmap for how virtual environments can accelerate robot development. Her 2018 work on real-time perception and reactive motion generation (107 citations) demonstrated the critical role of tight sensorimotor integration in robust grasping under uncertainty. More recently, Meier has pushed into embodied AI with OpenEQA (2024), exploring how foundation models can enable agents to answer natural language questions about their environments. Across her career, Meier has consistently bridged classical robot learning with modern deep learning approaches, making her a key figure shaping contemporary robotics research.

Research Focus

Key Achievements

Top Papers

1. 1
   On the use of simulation in robotics: Opportunities, challenges, and suggestions for moving forward

   157 citations · 2020
2. 2
   Real-Time Perception Meets Reactive Motion Generation

   107 citations · 2018
3. 3
   From dynamic movement primitives to associative skill memories

   71 citations · 2012
4. 4
   Movement segmentation using a primitive library

   71 citations · 2011
5. 5
   Residual Learning From Demonstration: Adapting DMPs for Contact-Rich Manipulation

   48 citations · 2022
6. 6
   Learning coupling terms for obstacle avoidance

   47 citations · 2014
7. 7
   OpenEQA: Embodied Question Answering in the Era of Foundation Models

   46 citations · 2024
8. 8
   SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Control

   44 citations · 2018
9. 9
   Learning Generalizable Locomotion Skills with Hierarchical Reinforcement Learning

   42 citations · 2020
10. 10
    Incremental Local Gaussian Regression

    38 citations · 2014

Key Collaborators

Contact & Links