David Ologan

Hi! I’m currently a second-year PhD student at Carnegie Mellon University studying Mechanical Engineering. My research focuses on leveraging reinforcement learning and optimization-based control methods for autonomous locomotion in complex, contact-rich natural environments.

I am currently advised by Prof. Aaron Johnson in the Robomechanics Lab, and am fortunate to be supported by the GEM PhD University Fellowship.

I also recently recieved my M.S. from CMU in Mechanical Engineering, and a B.S. from MIT in Mechanical Engineering and Electrical Engineering and Computer Science. I expect to graduate in May of 2028, and I’m currently looking for internship positions starting in the summer of 2026. Please take a look at some of the projects I’ve been working on!

news

No news so far...

selected publications

Proprioception and reaction for walking among entanglements

Justin K Yim, Jiming Ren, David Ologan, and 2 more authors

In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023

Abs PDF Video Code

Entanglements like vines and branches in natural settings or cords and pipes in human spaces prevent mobile robots from accessing many environments. Legged robots should be effective in these settings, and more so than wheeled or tracked platforms, but naive controllers quickly become entangled and stuck. In this paper we present a method for proprioception aimed specifically at the task of sensing entanglements of a robot’s legs as well as a reaction strategy to disentangle legs during their swing phase as they advance to their next foothold. We demonstrate our proprioception and reaction strategy enables traversal of entanglements of many stiffnesses and geometries succeeding in 14 out of 16 trials in laboratory tests, as well as a natural outdoor environment.
Quad-SDK Update: Estimation, Underbrush, and Other Improvements

David Ologan, Ardalan Tajbakhsh, Justin K Yim, and 5 more authors

2023

Abs PDF Code

This report presents extensions to Quad-SDK, a full-stack, open-source ROS based framework for control of quadrupedal locomotion. The modular software integrates motion planning, control, simulation, and estimation, while streamlining the development of novel robotics packages. With this update, Quad-SDK now incorporates an Extended Kalman Filter (EKF) for reliable onboard state estimation. Additionally, a specialized controller designed for walking through entanglements has been added, allowing the robot to disentangle itself from vine-like obstructions. Both serve to enable more reliable outdoor locomotion. Finally, several improvements have been made to the software architecture.