Vamsi Kalagaturu

Vamsi Kalagaturu

Robotics researcher, SECORO — University of Bremen

I build composable, reusable models for contact-rich mobile manipulation: building blocks that generate a robot's skill code for tasks where geometry, contact, and uncertainty all matter at once.

GitHub Scholar ORCID LinkedIn

Research

Contact-rich manipulation
Controllers and skills for tasks where the robot must push, slide, and stay in contact, reasoning about forces rather than positions.
Composable robot models
Models that snap together and get reused across tasks and platforms, generating the code for a skill instead of leaving it to be hand-written every time.
VLMs & VLAs
Using vision-language and vision-language-action models to generate semantics and models rather than trajectories: the model says what a task means, and the robot's own models work out how to move.

Publications

  1. 2024

    Composable and reusable models for contact-rich robotic mobile-manipulation tasks

    V. Kalagaturu et al. · IEEE Robotics and Automation Letters

  2. 2022

    Viewpoint planning for mapping of unknown confined spaces

    Autonomous perception & mapping

  3. 2020

    Perception & manipulation for the RoboCup@Work league (b-it-bots)

    Team contribution · Mobile manipulation in industrial settings

Tools

Mujoco KDL Wrapper
A C++ library bridging MuJoCo physics simulation with KDL for robot kinematics and dynamics. Builds KDL chains straight from the compiled MuJoCo model, handles multi-robot scenes, and ships Python bindings.

Awards

About

I build the software and control that make robot manipulation dependable. Most manipulation stacks are bespoke: a controller written for one task on one platform, which breaks the moment the robot actually touches something. My work replaces that with composable models that transfer across tasks and platforms, generate the skill code themselves, and hold up under real geometry, real contact, and real uncertainty.

I do this with the SECORO group at the University of Bremen, after an M.Sc. in Autonomous Systems at Bonn-Rhein-Sieg University and competition robotics with b-it-bots at RoboCup@Work. I care about robotics that is reusable and honest about the physical world, and I write the code that earns that claim on real hardware.

Now
PhD student and Research Engineer, SECORO — University of Bremen
Education
M.Sc. Autonomous Systems, Bonn-Rhein-Sieg University
Based in
Bremen, Germany
Works with
C++ · C · Python · ROS · JavaScript
Focus
Robotics manipulation · Integration · Perception · Software modelling · RDF

Contact

Collaborations, questions, or a chat about manipulation and control: my inbox is open.