Ian Utnehmer
Rover Project
I'm a Software Engineer specializing in computer vision / ML for Robotics in my free time. My current project has finished its first iteration.
Autonomous Scout is my thesis project: a low-cost robotics navigation system that closes the gap between 2D LiDAR-based obstacle avoidance and real-world terrain awareness. I built the system around a Jetson Nano/JetRacer platform using Python, PyTorch, ROS, and TensorRT, combining LiDAR SLAM, camera-based perception, and autonomous path planning.
The project detects hazards that standard 2D LiDAR often misses, including ground-level paper and terrain such as grass. I developed a camera segmentation stack for constrained edge compute, including swap-space mitigation, tooling for CSI camera hangs, and a labeled-image pipeline for training and deployment. I first deployed a ResNet-18 model for paper detection, then reused the same segmentation pipeline with a Cityscapes SegNet-18 model to extend the system toward terrain detection. Utilized Monodepth2 for depth estimation from RGB imagery.
I fused camera detections with LiDAR-based navigation by separating live obstacle handling from persistent mapping logic, exposing results in RViz and feeding them into move_base for autonomous path planning. The full stack successfully avoided paper in initial tests, then avoided grass after plugging the Cityscapes SegNet-18 model into the same pipeline.
I also built the supporting infrastructure for reliable deployment, including rosbridge-based host control, teleoperation and move-to-point scripts, static-IP networking through a NetworkManager dispatcher script, and localization debugging around AMCL drift and base_footprint-to-laser_frame transforms. Overall, the project demonstrates a practical perception-and-planning system that improves navigation safety, consistency, and readiness for indoor and outdoor terrain navigation.
Timeline
Software Engineer Intern
Software Engineer Intern
University of California, Los Angeles
Miracosta College
El Camino High School
Skills
Programming Languages: Java/TypeScript, C++, C, Python, JavaScript, Golang
Software Engineering: Agile development, software lifecycle, requirements analysis, object-oriented design, debugging, testing, software integration, Git
Frameworks / Platforms / Tools: Robot Operating System, OpenCV, TensorRT, OpenSSL, Codex, Claude Code, Linux, React, Next.js, VS Code, Visual Studio
Link to github: https://github.com/ian-utnehmer
Note: Username was changed from avian187 to ian-utnehmer on 9/29/2025
Work History
Software Engineer Intern
Rapidly developing autonomy software that enables underwater vehicles to carry out missions independently.
Software Engineer Intern
2 Months- Active DoD Secret Security Clearance.
- Documented code changes and system updates for team reference and future development.
- Assisted in testing and validating new features, ensuring functionality meets specifications.
- Collaborated with cross-functional teams to troubleshoot and resolve technical issues.
- Participated in daily stand-up meetings to communicate progress and address challenges.
- Contributed to software design discussions, providing insights on user experience improvements.
- Utilized Agile methodologies to manage tasks effectively within project timelines.
Projects
Non-coursework related:
- Autonomous Rover (Jan 2026 - Current)
- Rover built on the Jetson Nano platform, JetRacer chassis. Autonomusly navigates sidewalks via self-trained segmentation networks utilizing LiDAR and RGB camera via Monodepth2 estimation and Cartographer SLAM.
- Proof-Of-Concept Fine-Tuned GPT-3 model (June - Aug 2023)
- Implemented functionalities including generating text with fine-tuned models, listing fine-tuning jobs, creating fine-tuning jobs, uploading files, and listing available models. Utilized libraries such as Jsoup for HTTP requests and file handling. Demonstrated proficiency in Java programming, API integration, and problem-solving skills. Gained knowledge with handling JSON files.
- Basic Discord Account Scraper (Aug - Dec 2022)
- JavaFX application which extracts user data from Discord servers using authentication tokens. Implemented a user-friendly interface to input tokens and displayed the user's friends list as output. Ensured secure data retrieval while providing a seamless user experience. Utilized the JSoup library for HTTP requests- Autonomous Rover (Jan 2026 - Current)
Education
Bachelor of Science - Computer Science
Three Notable Projects completed at UCLA:
SchedUCLA (React, Node.js, Firebase, Tailwind CSS)
- Worked with a team to develop a full-stack event scheduling web application with interactive UCLA campus mapping, integrating Firebase for authentication and data storage.
- Built responsive UI with React and TailwindCSS; implemented modular component structure, sidebar navigation, and event creation form.
- Designed backend API in Node.js to handle event routing and server logic.
Line-Following Robot Development (Arduino)
- Programmed a robot using Arduino IDE to navigate a complex race track with IR sensors and encoders. Completed the track in both forward and reverse directions continually.
- Implemented PID control and sensor fusion for accurate navigation and sharp turn management.
- Optimized control algorithms, enabling reliable and efficient track completion.
Secure Encrypted Transport Protocol
- Designed and implemented a secure transport protocol with structured parsing, explicit protocol stages, and a state machine to enforce correct sequencing across handshake and protected data exchange.
- Protected communication against impersonation, tampering, and unsafe state transitions in a low-level networking environment.
- Integrated certificate validation, ephemeral ECDH key exchange, and authenticated encryption using OpenSSL EVP APIs.
- Tested and debugged non-blocking socket I/O flows, transition edge cases, and regressions using Git-based workflows for repeatable development.
Associate in Science For Transfer (AS-T) - Computer Science
GPA: 4.0/4.0
Transferred to UCLA Fall 2024.
High School Diploma
Graduated top 1% of class.