Marko Bjelonic
Chief Executive Officer Co-Founder at RIVR
Zurich, Zurich, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolMarko Bjelonic is a robotics entrepreneur and researcher with nine years of experience, currently CEO and co-founder of RIVR where he leads commercialization of General Physical AI for last-mile delivery with backers including Jeff Bezos. He earned a PhD at ETH Zurich as one of the first students in Prof. Marco Hutter’s legged robotics lab and pioneered a patented wheel‑and‑leg hybrid for quadrupeds as well as the first application of an artificial neural network on a legged robot. His research-to-product focus spans postdoctoral and NCCR roles where he translated perception and ML into deployable systems, contributing to projects like YOLO ROS object detection and GPU-accelerated elevation mapping. A member of the winning team in the DARPA Robotics Challenge—called the "Super Bowl of Robotics" by The Washington Post—he pairs deep technical rigor with startup execution and a personal resilience shaped by emigrating from the former Yugoslavia as a child.
9 years of coding experience
8 years of employment as a software developer
ETH Zürich
German, English, Serbian, French, Norwegian
Github Skills (12)
object-detection10
computer-vision10
darknet10
c-language10
deep-learning10
ros10
deep-learning-ai10
c-programming-language10
robotics9
geometric-algorithms8
visualizations7
visualization7
Programming languages (6)
Github contributions (5)
leggedrobotics/darknet_ros
Dec 2016 - Jun 2021
YOLO ROS: Real-Time Object Detection for ROS
Role in this project:
ML Engineer
ML EngineerContributions:1 release, 4 reviews, 253 commits in 4 years 7 months
Contributions summary:Marko primarily contributed to the YOLO object detection system for ROS. Their commits focused on enhancing the system's capabilities, including adding probability scores to bounding box titles for improved object classification confidence. They also made changes to the core object detection logic, and added launch file capabilities to streamline the deployment and configuration of the system. The user appears to be focused on improving the core functionality and usability of the object detection pipeline.
human-detectiondeep-learningcomputer-visionobject-detectionreal-time-object-detection
leggedrobotics/elevation_mapping_cupy
Sep 2019 - Nov 2020
Elevation Mapping on GPU.
Role in this project:Back-end Developer
Back-end DeveloperContributions:14 commits in 1 year 2 months
Contributions summary:Marko primarily worked on the `loco_perception_ros` package within the repository. Their contributions include adding and modifying ROS-related code, specifically focusing on visualizing convex sets and refining vertex iterators. They also integrated changes from a related branch, renaming the `convex_plane_extraction` package to `convex_plane_decomposition` and updating the associated ROS code. These changes suggest a focus on processing and visualizing geometric data within a robotic perception context.
gpumappingelevationoccupancy-grid-mapdepth-camera
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.