Connor Bossard

Robotics · ML · Controls

Connor Bossard

I'm a 2nd year Robotics student at Georgia Tech, with research focused on adversarial aerial path planning and the intersection of AI, ML, and controls.

Outside of robotics, I enjoy working out, playing guitar, watching sports, and playing on the Georgia Tech Club Baseball team.

Skills & Tech

Languages and tools I use in research and projects.

Python C++ MATLAB ROS Reinforcement Learning Machine Learning Control Theory SolidWorks Git Linux

Projects

F-16 dogfighting simulation
Adversarial PlanningMPPIModeling

Proposed Thesis: Real-Time Adversarial Planning Under Behavioral Uncertainty Using Belief-Space MPPI

  • First demonstration of MPPI on WVR aerial combat scenarios, with SOTA performance under real-time constraints.
  • Develop a belief-aware MPPI framework where uncertainty of opponent policy and state is represented as a large particle state.
  • Dynamic downselecting of particles to make computationally tractable.
  • Implementation of rejuvenation and resampling techniques for robustness to adversarial policy and reduced tracking error.
  • Validation in a high-fidelity, 6-DOF F-16 dogfighting environment with significant improvements over baselines.
Model-based diffusion planning
C++RRTMBD

C++ Planning Framework

  • Built Dubins car environment and FDM to test model-based planning algorithms.
  • Implemented CL-RRT and Model Based Diffusion (MBD) for waypoint-based navigation.
View on GitHub
Maze navigation RL
PythonRLTransfer Learning

Learning to Navigate: An Imitation Learning Framework for Path Planning in Adversarial Environments

  • Developed a transfer and curriculum learning framework to train a robust navigation policy for adversarial environments.
  • Pretrained an agent on expert demonstrations in a static maze using DAGGER and behavior cloning.
  • Fine-tuned the policy for dynamic adversarial scenarios using Proximal Policy Optimization (PPO).
  • Achieved significant performance improvements over a baseline PPO policy.
Read paper (PDF)
F-16 adaptive control
MATLABControl

Adaptive Control For F-16 Catastrophic Loss of Effectiveness

  • Implemented and compared nonlinear adaptive control methods: MRAC, sliding mode, and NN-based approaches.
  • Evaluated controller performance on an F-16 holding trim with loss of elevator effectiveness.
Read paper (PDF)
Retinal disease detection
PythonML

Fundus Image Classification for Retinal Disease Detection

  • Image classification on retinal images for automated disease detection.
  • Engineered features from preprocessed image data using Histogram of Oriented Gradients (HOG).
  • Implemented and benchmarked SVM, CNNs, and YOLOv8 on classification accuracy.
View report
TurtleBot path planning
ROSLinux

TurtleBot Path Planning

  • Fused TurtleBot sensor readings (LIDAR, camera, odometry) for state estimation in a maze environment.
  • Implemented navigation and control algorithms for autonomous maze traversal.
  • Fine-tuned a ResNet image classifier with few-shot learning on navigational signs to inform path decisions.
Ball balancing robot
C++Arduino

Ball Balancing Robot

  • Modeled and fabricated a robot consisting of 3D printed parts and heated inserts
  • Interfaced Arduino with three stepper motors and a resistive touch pad to determine ball’s location
  • Utilized inverse kinematics to determine how motor movement would impact platform orientation
  • Implemented a C++ based PID controller to balance a ball, using a resistive touch pad for orientation feedback and the motors for corrective action
Competition robot
IntegrationDesign

Competition Robot

  • Designed and modeled the robot in SolidWorks.
  • Fabricated using laser cutters, water jets, and 3D printers.
  • Wrote C++ scripts integrating sensors, pneumatics, solenoids, and motors.
  • Competed against 64 teams, placing in the top 5.
Electronics enclosure
CAD3D printing

Electronics Enclosure

  • Designed and modeled a compact electronics enclosure in CAD for a lower-body exoskeleton.
  • Fabricated the enclosure using 3D printers and heated inserts.
  • Tested for reliability against vibrations and environmental stresses.

Work Experience

GT Dynamic Adaptive Robotic Technologies (DART) Lab

  • Graduate Research Assistant
  • Path Planning / Trajectory Optimization
  • Reinforcement Learning
  • High Fidelity Adversarial Modeling
  • Aircraft Modeling and Simulation
  • Aug 2023 - Present

Sandia National Labs

  • Aerial Autonomy Intern
  • Multi-Agent, Adversarial Path Planning
  • Sequential Modeling using Transformer Encoder architecture
  • May 2025 - Present

Shield AI

  • Mechanical Engineering Intern
  • Redesigned and prototyped subsystem on a Group 5 UAS
  • Utilized FEA and safety factors to assist in material selection
  • Tested response to vibration, salt fog and cyclical loading
  • Automated the visualization of post flight controls data
  • May 2023 - Aug 2023

GT Exoskeleton and Prosthetic Intelligent Controls (EPIC) Lab

  • Undergraduate Research Assistant
  • Developed enclosure for electronics, accounting for vibrations and stresses
  • Integrated socket connection for sensor and input data to be transferred to the hip exoskeleton
  • Assisted in live visualization of outputs and important metrics
  • Aug 2021 - May 2023

Procter & Gamble

  • Research and Development Intern
  • Utilized PowerBI to visualize data, mockup enhancements and presented solutions for management
  • Developed a Python script to automate a key data processing pipeline, resulting in a saving of hundreds of man-hours annually
  • May 2022 - Aug 2022

Relevant Masters Coursework

  • Deep Reinforcement Learning
  • Deep Learning
  • Machine Learning
  • Linear Controls
  • Non-Linear Controls
  • Advanced Flight Dynamics

Get in touch

Open to opportunities in robotics and autonomy.

Email

cbossard3@gatech.edu

Phone

(240) 778-4272

LinkedIn

Connect

Resume

Download PDF