PeopleofSuperintelligence

Researcher

Hartmut Geyer

Hartmut Geyer is a robotics researcher whose work connects models of human locomotion with control for bipedal robots and powered prostheses. He earned degrees in physics and biomechanics at Friedrich-Schiller-University of Jena, held postdoctoral roles at MIT and ETH Zurich, and joined Carnegie Mellon’s Robotics Institute in 2010. His work spans compliant-leg and muscle-reflex models, deep reinforcement learning for the ATRIAS biped, and prosthesis control that adapts to terrain and obstacles. As of October 2026, he is a professor in Carnegie Mellon’s Robotics Institute and directs the Legged Systems Group.

Timeline

  1. 2001–2005

    Physics and biomechanics at Jena

    At Friedrich-Schiller-University of Jena, he earns a diploma in physics in 2001 and a Ph.D. in biomechanics in 2005.

  2. 2006–2010

    Postdoctoral work and gait models

    He receives an EU Marie Curie Fellowship in 2006 and works as a postdoctoral researcher at MIT’s Biomechatronics Group and ETH Zurich’s Institute for Automatic Control. With André Seyfarth and Reinhard Blickhan, he publishes a bipedal spring-mass model in 2006 showing how compliant legs reproduce the basic mechanics of walking and running. He joins Carnegie Mellon’s Robotics Institute in 2010.

  3. 2010

    A muscle-reflex walking model

    He and Hugh Herr publish a model in 2010 that uses muscle reflexes to encode legged mechanics. The model stabilizes into a walking gait, tolerates ground disturbances, and adapts to slopes.

  4. 2015

    Reflex control for prostheses

    His team evaluates a reflex-based control strategy for a powered prosthetic leg in simulation and laboratory tests in 2015. The strategy produces stable walking over uneven terrain and better recovery from trips and shoves.

  5. 2018

    Deep reinforcement learning on ATRIAS

    In 2018, he coauthors a preprint submitted to the 2019 IEEE International Conference on Robotics and Automation. The work uses deep reinforcement learning with structured control to learn bipedal policies and transfer them from simulation to the ATRIAS robot.

  6. August 2019

    Neuromuscular models for robot control

    He coauthors a chapter with André Seyfarth that reviews neuromuscular models of human locomotion and their use in the control of robotic limbs and humanoids in August 2019.

  7. July 2025

    Obstacle-aware prosthesis control

    In July 2025, he coauthors a human-cooperative control strategy for powered lower-limb prostheses. An onboard depth camera detects obstacles and prompts an elevated early-swing trajectory, while late-swing control follows the user’s biomechanical cues.

  8. As of October 2026

    Professor and group director

    As of October 2026, he is a professor in Carnegie Mellon’s Robotics Institute and directs its Legged Systems Group. The group uses physics, biomechanics, neuroscience, control theory and machine learning to develop lower-limb assistive robots.

Career

  1. Since 2010Carnegie Mellon UniversityProfessor
  2. 2006–2010Massachusetts Institute of TechnologyPostdoctoral researcher
  3. 2006–2010ETH ZurichPostdoctoral researcher

Education

  1. 2005Friedrich Schiller University JenaPh.D. in biomechanics
  2. 2001Friedrich Schiller University JenaDiploma in physics

From the biography.

  1. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Carnegie Mellon University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Carnegie Mellon University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  3. Google has the highest combined h-index among AI organizationsIncludes Carnegie Mellon University. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  4. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Carnegie Mellon University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Hartmut Geyer yet. Send us a free-licensed photo.

  1. Hartmut Geyer - Biomedical Engineering - College of Engineering - Carnegie Mellon University cmu.edu. Checked 21 October 2026.
  2. ECC13 - European Control Conference ecc13.ethz.ch. Checked 21 October 2026.
  3. Compliant leg behaviour explains basic dynamics of walking and running - Robotics Institute Carnegie Mellon University publications.ri.cmu.edu. Checked 21 October 2026.
  4. A muscle-reflex model that encodes principles of legged mechanics produces human walking dynamics and muscle activities - Robotics Institute Carnegie Mellon University publications.ri.cmu.edu. Checked 21 October 2026.
  5. Strategy Based on Human Reflexes May Keep Legged Robots, Prosthetic Legs From Tripping - News - Carnegie Mellon University cmu.edu. Checked 21 October 2026.
  6. [1809.10811] Using Deep Reinforcement Learning to Learn High-Level Policies on the ATRIAS Biped arxiv.org. Checked 21 October 2026.
  7. Neuromuscular Control Models of Human Locomotion - Robotics Institute Carnegie Mellon University publications.ri.cmu.edu. Checked 21 October 2026.
  8. Environment-Aware and Human-Cooperative Swing Control for Lower-Limb Prostheses in Diverse Obstacle Scenarios arxiv.org. Checked 21 October 2026.
  9. Legged Systems Group sites.google.com. Checked 21 October 2026.
  10. Hartmut Geyer - The Robotics Institute - CMU ri.cmu.edu. Checked 21 October 2026.