Building the future of large autonomous electric fixed-wing aircraft, solving critical agricultural and logistics challenges around the world.

As part of NIST’s Automated Vehicle (AV) team, I support the research, development, and testing of AV systems to inform and enable the development of industry standards. Building on my work in the APRS project, my focus is on enhancing operational capabilities, system integration, and interdisciplinary collaboration.

Integrated Autoware with a Ford Fusion Hybrid drive-by-wire AV, enabling standardized testing of perception, planning, and control modules.

Developed HD Lanelet maps of the NIST campus for localization, navigation, and reproducible test benchmarking.

Implemented obstacle collision-avoidance behaviors, improving AV safety and reliability in complex traffic scenarios.

Built a Neo4j-based GUI to visualize AV system interactions and data flow, accelerating debugging and supporting standards research.

Collaborated across AI, perception, and V2X teams, ensuring seamless software-hardware integration and advancing interoperable AV systems.

Presented technical briefings to SAE committees, FHWA, NHTSA, and NIST leadership, shaping discussions on AV safety, standardization, and system performance.

As a Researcher in the Agility Performance of Robotic Systems (APRS) project within the Measurement Science for Manufacturing Robots Program, I spearhead initiatives to optimize robotic system performance and safety.

Overhauled the APRS robotics demo (Fanuc, Motoman, UR5e, Franka), developing custom ROS drivers for legacy systems to expand functionality.

Pioneered adaptive task planning with PlanSys2 + behavior trees, enabling failure recovery and reducing downtime.

Contributed to IEEE P2940 standards, defining agility and reconfigurability metrics for next-gen robotics.

Developed ROS2 computer vision pipelines, improving detection accuracy by 25% for Sim-to-Real transfers.

Designed ARIAC 2024 simulation that increased AGV efficiency by 20% and stability by 15%.

Optimized Neo4j performance, cutting query times by 50% and accelerating robotics data workflows.

Built a pipeline for vision-based bolt classification in manufacturing systems.

Developed proof-of-concept simulations with UR3 robot in ROS & Gazebo, validating autonomous workflows.

Applied C++ and Python algorithms to support perception and control for industrial robotics applications.

Reduced production costs by 15% by optimizing layouts and resource planning.

Developed a Python/Qt cost tool that automated material ordering and improved financial tracking.

Facilitated UL & CSA certification, unlocking US export market entry.

Collaborated cross-functionally with marketing and suppliers to ensure high-quality, reliable products.