thias15
Machine Learning Engineer at Intel
Munich, Bavaria, Germany
Summary
🤩
RockstarMachine Learning Engineer based in Munich with 10 years of experience applying computer vision and robotics research to real-world systems, particularly in object tracking and autonomous navigation. Hands-on contributor to high-profile open-source projects like Microsoft AirSim, where they implemented Semi-Global Matching stereo vision and a data collection pipeline, and to OpenBot, developing Arduino Nano firmware for motor control, odometry and sensor integration. Combines embedded-systems fluency (PWM, sonar, battery estimation) with ML-focused image processing and disparity map generation, enabling end-to-end perception-to-control pipelines. Known for bridging simulator work and low-cost robotic platforms, making advanced autonomy accessible on resource-constrained hardware.
9 years of coding experience
Github Skills (15)
controls10
computer-vision10
embedded10
c-language10
robotics10
stereoscopy10
cprogramming-language10
stereo10
sys10
controller10
arduino10
image-processing10
pwm10
android9
deep-learning7
Programming languages (7)
Github contributions (5)
ob-f/OpenBot
Aug 2020 - Dec 2022
OpenBot leverages smartphones as brains for low-cost robots. We have designed a small electric vehicle that costs about $50 and serves as a robot body. Our software stack for Android smartphones supports advanced robotics workloads such as person following and real-time autonomous navigation.
Role in this project:
Embedded Systems Engineer
Embedded Systems EngineerContributions:16 releases, 169 reviews, 578 commits in 2 years 4 months
Contributions summary:thias15's commits primarily focus on developing the firmware for an Arduino Nano-based robot. This involved implementing functionalities for receiving control commands from an Android application, controlling PWM signals for motor control, managing indicator signals, implementing wheel odometry, estimating battery voltage, and incorporating sonar sensor readings. The user demonstrated expertise in embedded systems, hardware interfacing, and real-time sensor data processing.
serveslow-costrobotsnavigationreal-time
microsoft/AirSim
Jul 2018 - Sep 2018
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
Role in this project:ML Engineer
ML EngineerContributions:14 commits, 8 PRs, 7 pushes in 1 month
Contributions summary:thias15 contributed significantly to the project by adding and integrating SGM (Semi-Global Matching) stereo vision code. This involved implementing the SGM algorithm, adding code for image processing and disparity map generation. The user also integrated the SGM functionality into an example project, suggesting a focus on enabling or improving the stereo vision capabilities within the autonomous vehicle simulator. Moreover, the user added a data collection pipeline.
deep-reinforcement-learningsimulationsimulatorunitysimulator-source
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.