Research record

Publications

Peer-reviewed conference papers, preprints, and graduate thesis work in robot learning, locomotion, sensing, and human-robot interaction.

Google Scholar profile
Experimental setup showing a Neuromeka robot guided by a participant through a rectangular tactile calibration trajectory, with sensor and path diagrams.
PREPRINT Tactile interaction 2026

Journal (PREPRINT) · 2026

Real-Time Neuroadaptive Control with Tactile Calibration for Physical Human-Robot Interaction

Ashutosh Prakash, Mohamed A. Hanafy, Jordan Dowdy, Dan O. Popa

Preprints.org · Version 1

Paper

A dual-loop neuroadaptive tactile interface was evaluated across 28 participants and 112 personalized calibration models, enabling real-time human-guided robot-arm motion.

Multiple simulated ROBOTIS OP3 humanoids traverse tiled terrain while red 8-by-8 time-of-flight depth scans visualize local terrain sensing.
NAECON Terrain-aware humanoid locomotion 2026

Accepted conference paper · 2026

Loco-Loco-RL: Low-Cost Terrain Mapping for Humanoid Locomotion with Reinforcement Learning

Jordan Dowdy, Gryffin Reizian, Jean Chagas Vaz

IEEE National Aerospace and Electronics Conference (NAECON) · Accepted

A token-compressed temporal transformer fuses proprioception with a low-cost 64-point time-of-flight terrain scan and transfers to a physical ROBOTIS OP3 for terrain-aware locomotion.

A simulated custom five-degree-of-freedom robot arm positioned above red, blue, and green cubes in the cube-stacking task environment.
NAECON VR imitation learning 2026

Accepted conference paper · 2026

Learning to Stack: Cube-Stacking Imitation Learning from Virtual Reality Demonstrations

Gryffin Reizian†, Jordan Dowdy†, Jean Chagas Vaz

IEEE National Aerospace and Electronics Conference (NAECON) · Accepted · † Equal contribution

A virtual-reality teleoperation pipeline in Isaac Sim and Isaac Lab collects reusable cube-stacking demonstrations, retargets them to joint space, re-renders observations, and expands the dataset with Isaac Mimic.

Sequence of a simulated Unitree B1 quadruped descending stairs using a torque-driven reinforcement learning controller.
SII Torque-driven locomotion 2026

Conference paper · 2026

Towards Torque-Driven Reinforcement Learning for Quadruped Locomotion

Jordan Dowdy, Jean Chagas Vaz

2026 IEEE/SICE International Symposium on System Integration (SII) · pp. 1259–1264

Paper

A torque-control reinforcement-learning framework for the Unitree B1 traverses rough terrain, tracks commanded velocity, and climbs stairs in Isaac simulation without exteroceptive sensing.

Four-step sequence of a miniature humanoid walking to blocks, grasping a block, walking to a bin, and releasing it.
HUMANOIDS Tele-loco-manipulation 2025

Conference paper · 2025

Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning

Nicolas Kosanovic, Jordan Dowdy, Jean Chagas Vaz

2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids) · pp. 1233–1240

Paper

A full-body telepresence stack for the ROBOTIS OP3 combines virtual-reality upper-body control with reinforcement-learning locomotion for compliant tele-loco-manipulation.

Physical Unitree Go1 quadruped climbing an inclined wooden pallet during sim-to-real testing.
CASE Sim-to-real locomotion 2025

Conference paper · 2025

Isaac Sim-to-Real: Reinforcement Learning based Locomotion for Quadrupeds

Jordan Dowdy, Jean Chagas Vaz

2025 IEEE 21st International Conference on Automation Science and Engineering (CASE) · pp. 2194–2199

Paper

A reinforcement-learning locomotion pipeline trains in NVIDIA Isaac Sim and transfers to a physical Unitree Go1 for real-world evaluation.

A participant grasping the sensorized OctoCan end effector mounted on a RE2 robotic arm.
THESIS Human-robot collaboration 2024

M.S. thesis · 2024

Adaptive Robot Collaboration Using Robotic Skin and Motion Similarity

Jordan Dowdy

Electrical Engineering · University of Louisville

Thesis

OctoCan tactile sensing and neuroadaptive control support physical robot guidance, while online dynamic time-warping enables speed-adaptive imitation with the Zeno humanoid.