Michal P. Podolinsky

PhD Student, Electrical & Computer Engineering (Robotics) · UT Austin

Michal Podolinsky

Austin, Texas

michal.podolinsky@utexas.edu

University of Texas at Austin

I am a graduate research assistant at the Autonomous Systems Group at the University of Texas at Austin, pursuing a PhD in Electrical and Computer Engineering (ECE) focusing on robotics. I completed my BSc in Aerospace Engineering at the Technical University of Delft.

My research interests are the safe deployment of Vision-Language-Action (VLA) and Vision-Language Models (VLMs).

I completed my BSc in Aerospace Engineering at TU Delft and a minor in Technology Entrepreneurship at UIUC.

Outside the lab I enjoy hiking, playing tennis, and volunteering at YMCA summer camps.

publications

[2026 Pre-print] Failure Prediction and Classification in Vision-Language-Action Models via Calibrated Latent Probing
Michal P. Podolinsky, Yunhao Yang, Daniel Little, Hong Lu, Rohan Siva, Olin Goudey, Neel P. Bhatt, Matthias Scheutz, Ufuk Topcu
arXiv Website Code Dataset (2.5k+ downloads)
[IROS 2026 LAFR Workshop] ASPIRE: Decoupling Perception and Reasoning in Vision-Language Models with Answer Set Programming
Michal P. Podolinsky, Yunhao Yang, Neel P. Bhatt, Alvaro Velasquez, Ufuk Topcu
Workshop Website
[2026 Pre-print] Co-GLANCE: Uncertainty-Aware Active Perception for Heterogeneous Robot Teaming
Michal P. Podolinsky, Neel P. Bhatt, Pranay Samineni, Rohan Siva, Christian Ellis, Ufuk Topcu
arXiv Website Dataset (8.5k+ downloads)

news

Nov 2025 Started volunteering at Del Valle High School as instructor for the Autonomous Car Project.
Aug 2025 Started graduate studies at UT Austin, Autonomous Systems Group.
Jun 2025 Started as Associate Consultant Intern at Bain & Company.
Feb 2025 Awarded the Belgian American Educational Foundation Fellowship supporting graduate studies in the United States.
Dec 2024 LiDAR altitude estimation algorithm commercially deployed in ABZ Innovation autonomous agricultural UAVs via Perciv AI.
Sep 2024 Selected among top 40 students from leading European technical universities by the IDEA League network.
Aug 2024 Started internship at Perciv AI (TU Delft spinoff) on UAV perception and LiDAR-based altitude estimation.
Dec 2023 Started undergraduate research at UIUC LEADS Laboratory on high-fidelity CFD modelling of airfoil heat-exchanger integration in electric aircraft.

projects

Spot payload Spot alternate view Spot deployment
Boston Dynamics Spot

Custom payload integration (LiDAR, RGB-D) and reinforcement-learning gait policies trained in NVIDIA Isaac Lab, validated on hardware.

Isaac Lab RL ROS 2 Active
LiDAR altitude estimation
LiDAR Altitude Estimation

Real-time, LiDAR-only altitude estimation for autonomous agricultural UAVs. Commercially deployed in ABZ Innovation drones via Perciv AI.

LiDAR UAV Deployed
SLA map with geostrophic velocities Eddy points Okubo-Weiss parameter Partial SLA map
Ocean Eddy Tracking

Spatiotemporal tracking of dynamic ocean structures from satellite altimetry using the Okubo-Weiss parameter. Undergrad research at TU Delft.

Satellite Data Geophysics Completed

outreach

Del Valle High School — Autonomous Car Project

Instructor · Austin, TX · Nov 2025 – present

As a graduate research assistant at the Autonomous Systems Group, I volunteer at Del Valle High School teaching students the basics of servos and sensors, electrical circuits, Python programming, and GPIO-based hardware control. Students apply these skills to build a functioning autonomous RC car over the course of the program. Learn more →

Feel free to reach out for research collaborations or opportunities.