Learning-based autonomy for robots in the physical world.
I build and study learning-based autonomous systems, with current work spanning embodied navigation, cross-embodiment manipulation, simulation, and real robotic systems.
Questions, experiments, and evidence
Three research efforts are foregrounded here. Each case study separates the research question, personal contribution, upstream systems, completed results, failures, and limitations.
Three connected questions
The methods will change. These are the longer-lived questions that organize the work.
01
Generalization & Adaptation
How can a robot remain capable when its environment, task, viewpoint, or embodiment differs from training?
I am interested in identifying which parts of a learned system fail under distribution shift, then designing representations, data, and evaluations that make adaptation measurable.
02
Robot Learning & Learning-Based Control
How can robots acquire robust physical skills from demonstrations, interaction, and closed-loop feedback?
My current work uses behavior cloning and reinforcement-learning tools, while treating policy class, action representation, and native competence as experimental variables rather than fixed identities.
03
Embodied Autonomy
How should perception, language, planning, learning, and control be integrated into one autonomous physical system?
I care about complete-system behavior: what the robot observes, how decisions become motion, and what deployment evidence can actually establish.
Robots have to work below the model layer
These projects show field integration, mathematical modeling, robot recovery, embedded timing, and hardware interfaces without presenting engineering breadth as a skill meter.
Reports, methods, and evidence ledgers
No publication status is implied. These are the real technical artifacts currently available.
Ownership across studies and systems
Roles are described at the level personally designed, implemented, evaluated, debugged, or coordinated.
May 2026 – present
Research Assistant — Humanoid Robotics
Fort Lewis College · Advisor: Dr. Yiyan Li
2026 · active
Independent Research — xembench
Language-grounded manipulation in ManiSkill3
Oct 2025 – Apr 2026
Research Assistant — Field Robotics
NASA Colorado Robotics Challenge · four-person team
A computer engineer moving deeper into robot learning
Computer engineering student at Fort Lewis College focused on robot learning and autonomy, with experience spanning benchmark design, simulation, controls, perception, and embedded systems.
Help build general-purpose autonomous robots that can adapt to new tasks, bodies, and environments — and continue learning after deployment. My background spans mathematical modeling, simulation, ROS, perception, embedded systems, and field integration; current work uses that range to ask narrower and more rigorous learning questions.
- Student representative, Strategic Implementation Committee — one of four students serving with the FLC president, trustees, deans, and campus leaders on the 2025–2030 strategic plan
- President & co-founder, Entrepreneurial Ventures Association — led an 8-person executive team, organized pitch competitions allocating $1,500 in micro-grants, and brought the NASA Venture Program to campus
- Team lead, NASA Colorado Robotics Challenge — coordinated a four-person team building and fielding an autonomous 18-DoF hexapod
Interested in robot learning, embodied autonomy, or real-system evaluation?
I am always glad to compare notes on research questions, systems, and experiments.