Deep Learning Framework for Early Detection of Pancreatic Cancer Using Multi-modal Medical Imaging Analysis
doi:10.1007/s10278-026-01998-wGreeting, I'm
Dennis Slobodzian.
Robotics Software · Controls · Perception · Embedded Systems
Electrical and computer engineer building real-time robotics software — C++ robot control, AprilTag/Kalman localization, LQR state-space feedback, GPU-accelerated vision, PCB design, and embedded firmware.
Projects
V-JEPA 2 Drake Simulation
Understand and use V-JEPA 2 using Drake simulation library for RL and ML tasks
Differential Swerve Drive Module
LQR state-space control of a differentially coupled swerve drive
Pose Estimator
Particle filter pose estimation with C++ and CUDA
4-Bar Crank Rocker Leg
Iterative mechanical leg design using a crank-rocker four-bar linkage
Vision System
Modular YOLO-based 3D vision pipeline for NVIDIA Jetson edge deployment
Embedded Hardware & Firmware
Motor-controller PCB and wireless 8 kHz mouse/dongle firmware
talOS
Mini ROS-inspired communication and control framework (Work in progress)
FRC — Team 5687 The Outliers
I joined Team 5687 in 2019 as a high school student with no prior robotics experience. Six weeks to design, build, and program a competition robot from scratch that urgency taught me more about engineering under constraint than anything else before or since.
After graduating I came back as a software and controls mentor. What started as teaching students to write a basic PID loop grew into a full controls curriculum: feedforward modeling, motion profiling, Kalman-filter localization with AprilTags, and eventually full state-space representations with LQR feedback. Every year the robots get more capable; every year the students go further than the year before.
The robots below are the ones I helped build and control, each one a snapshot of where the team was technically that season.