Akhil Sathuluri

I am a PhD student at TU Munich, thinking about ways to represent and co-optimise morphology and controllers of robotic systems and their implications on realising physical robots. I work as a research assistant at the Robot Systems Forschungsgruppe at LPL.

I completed a short stint at the Multi-robot Systems Lab at Stanford , where we explored the ideas of diffusion policies and their combination with Gaussian splatting representation, serving as a simulatable digital twin-based surrogate for real-world data.

I spent some time at the Artificial and Mechanical Intelligence Research Line at the Italian Institute of Technology, where I worked on methods to improve the robustness of humanoid walking by looking at the combined locomotion controller and joint actuation space.

I previously worked as an electrical engineer in the Robotics and Automation team of Bajaj Auto Ltd, the largest three-wheeler and the third largest two-wheeler manufacturer in the world. We developed edge-based vision systems for low-cost robotic special-purpose machines.

Earlier, I graduated from IIT Madras and was a member of the Robotics Lab, advised by Prof. Sandipan Bandyopadhyay, where I worked on the design, analysis and control of parallel robots.

Email  /  Github  /  Google Scholar  /  LinkedIn  /  CV

In progress

In progress

In progress

Co-design optimisation of a family of robots with shared components

Maximising Tolerance to Disturbances via Combined Control-Actuation Optimisation for Robust Humanoid Robot Walking

Modeling and control of a teleoperation system for a small-scale In-Vessel Articulated Robot (IVAR)

A Multidisciplinary Optimization Approach for Resolving the Vicious Cycle between Morphology and Control of Robots

Computational Systems Design of Low-Cost Lightweight Robots

Robust co-design of robots via cascaded optimisation

A systems design approach for the co-design of a humanoid robot arm

Extended-configuration-space modelling: mapping to reduced order models and real-time simulation of Lagrangian dynamics and control of parallel manipulators

A Study on the Lagrangian Formulation of Dynamics with Applications to Control of Parallel Manipulators

Root-tracking methods and their applications in simulations

MaMiC: Macro and Micro Curriculum for Robotic Reinforcement Learning

Sim-to-real transfer of RL policies with industrial robots

MagNex — Expendable robotic surgical tooltip