Ayano Hiranaka

I am a CS PhD student at University of Southern California (USC) co-advised by Professor Daniel Seita and Professor Erdem Biyik.

Prior to coming to USC, I completed my Master's degree at Stanford University, where I was a research assistant at Stanford Vision and Learning Lab (SVL) working with Prof. Fei-Fei Li , Prof. Jiajun Wu, and Dr. Ruohan Zhang. I received my undergraduate degree in mechanical engineering from the University of Illinois at Urbana-Champaign (UIUC).

My experiences are a unique blend of computer science and mechanical engineering, ranging from AI to robotics to mechanical design.

Email  /  CV  /  Google Scholar  /  Github

Publications

I am passionate about designing synthetic agents that can be incorporated into everyday life as human companions. My research interest lies in developing methods that enable agents to communicate effectively and collaborate seamlessly with humans in households or public spaces, increasing the quality of human lives , while evolving alongside humans by learning from them. Topics of interest include human-in-the-loop learning, interactive human-robot collaboration, reinforcement learning, and imitation learning, especially for robotics applications.

Finetuning text-to-image diffusion models for a variety of tasks in a human-feedback-efficient manner by combining feedback-aligned representation learning and feedback-guided image generation.

Brain-robot interface system for everyday activities using EEG signal decoding, primitive skills, and robot intelligence aided by foundation models.

Combining intuitive skill-based action space and human evaluative feedback, enabling a more safe and sample efficient long-horizon task learning in the real world.

A sample-efficient RLHF framework for low-level robot control policy leveraging a human-interpretable high-level state representation for active query.

Research Projects

Mechatronic system that detect, track, and collect spectral data from moving, light-emitting objects in the night sky.
Mentored and sponsored by Prof. Nick Glumac.

Real-time identification of a note played on a piano with a probabilistic approach using a feedback particle filtering algorithm.
Mentored by Prof. Amirhossein Taghvaei and Prof. Prashant Mehta.

Investigation of atomization-based cutting fluid spray condition to maximize tool life for deep micro-drilling. Automatic drill parameter measurements from microscope images using keypoint detection.
Mentored by Dr. Amy Lee and Prof. Shiv Kapoor.

Miscllaneous Projects

In progress retro-style simulaiton RPG in Unity.
Personal hobby project.

AR piano using real-time hand keypoint tracking from RGB webcam stream.
CS231A Computer Vision from 3D Reconstruction to Recognition course project.

Drum-player humanoid simulator that playes the beats speficied by a user.
CS225A Experimental Robotics course project.

A vegetable slicer operating from single crank input, quadruped walking robot, and steel ball transporter mechanism.