Nodoka Shibasaki

About Me

I am a third-year Electrical and Computer Engineering student at Northeastern University with a strong intent to pursue robotics. I am currently a research assistant in the RiVER Lab under the supervision of Professor Taskin Padir, where I research on manipulation, perception, and control systems.

My interest in robotics has solidified thanks to many guidances. I had the opportunity to develop autonomous multi-modal locomotion robots at the Silicon Synapses Lab under Professor Ramezani Alireza, and uncertainty-aware exoskeletons at the Shepherd’s Lab under Professor Max Shepherd.

I also gained valuable industry research experience as a full-time intern for six months at OMRON SINIC X in Tokyo. My work is motivated by the goal of enabling humans to seamlessly and safely work together with robots in their daily lives.

Extra: My early work in athletic training and at Stanford Sports Medicine Lab initially drew me toward biomechanics and pre-med. But as I began working on assistive robotics in college, I found myself more captivated by the engineering challenge of creating adaptive systems that work with human capabilities. I’m interested in developing safe, adaptive and replicable robotic systems that enable intuitive human-robot collaboration.

Research Projects

Active vs. Passive Control with FT feedback

Jul 2025 – Dec 2025

I compared passive compliance (soft wrist, position control) versus active compliance (Forward Dynamics Compliance Controller, rigid wrist) on a UR5e using SAC reinforcement learning with force-torque feedback only.

Tactile Memory with Soft Robots

Jul 2025 – Dec 2025

TaMeSo-bot uses transformer-based learning to process tactile, force-torque, and proprioceptive signals for retrieval-based manipulation. Achieved 88.5% and 62% success rates under seen and unseen peg-in-hole conditions (varying shapes, sizes, textures, orientations).

Multi-Modal Locomotion Robot

Jan 2025 – July 2025

Sim-to-real transfer is a bottleneck for multi-modal robots due to unpredictable real-world dynamics. To address this, I built a reproducible pipeline for the M4 platform using ROS 2, ArduPilot, and Docker. This system reduced deployment time by 40% and improved energy efficiency by 18%, enabling reliable field testing.

Ankle Exoskeleton

Sep 2024 – Jun 2025

Designing customizable, robust exoskeletons is challenging due to complex biomechanics. I developed a modular ankle exoskeleton platform with a flexible CAD system and sensor pipelines. This accelerated hardware and control iteration, laying the groundwork for future ML-driven gait assistance.

Hip Exoskeleton

Jun 2024 – Feb 2025

Balancing power efficiency and adaptive control in wearable robotics is difficult under variable human movement. I optimized the hip exoskeleton's power system and implemented an RL-based control policy. These upgrades improved stability and energy efficiency, enabling longer, more robust human-in-the-loop trials.

Hobby

Powered by Jekyll and Minimal Light theme.