Ziyan Gao

Ziyan Gao

Research Assistant Professor at Japan Advanced Institute of Science and Technology (JAIST).

Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Pages

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

implementations

portfolio

publications

A few-shot learning framework for planar pushing of unknown objects

Published in Intelligent Service Robotics, 2022

Presents a few-shot learning framework for robot planar pushing with a new large dataset and novel representation for pushing primitives, including computation efficient planning method.

Recommended citation: Gao, Z., Elibol, A., & Chong, N. Y. (2022). A few-shot learning framework for planar pushing of unknown objects. Intelligent Service Robotics, 15(3), 335-350.
Download Paper

Zero moment two edge pushing of novel objects with center of mass estimation

Published in IEEE Transactions on Automation Science and Engineering, 2022

Pushing is one of the fundamental nonprehensile manipulation skills. This work estimates the center of mass of an object and proposes the Zero Moment Two Edge Pushing method to translate a novel object without rotation to a goal pose.

Recommended citation: Gao, Z., Elibol, A., & Chong, N. Y. (2022). Zero moment two edge pushing of novel objects with center of mass estimation. IEEE Transactions on Automation Science and Engineering, 20(3), 1487-1499.
Download Paper

On the generality and application of mason’s voting theorem to center of mass estimation for pure translational motion

Published in IEEE Transactions on Robotics, 2024

Extends Mason Voting Theorem to object center of mass estimation in the absence of accurate information on friction and object shape using a position-controlled robot arm and vision sensor.

Recommended citation: Gao, Z., Elibol, A., & Chong, N. Y. (2024). On the generality and application of mason's voting theorem to center of mass estimation for pure translational motion. IEEE Transactions on Robotics, 40, 2656-2671.
Download Paper

Hierarchical Motion Field Alignment for Robust Optical Flow Estimation

Published in Sensors, 2025

Proposes a learning-based model with Hierarchical Motion Field Alignment module and Correlation Self-Attention module for improved optical flow estimation, particularly for small and fast-moving objects.

Recommended citation: Ma, D., Imamura, K., Gao, Z., Wang, X., & Yamane, S. (2025). Hierarchical Motion Field Alignment for Robust Optical Flow Estimation. Sensors, 25(9), 2653.
Download Paper

Predicting hemodynamic parameters based on arterial blood pressure waveform using self-supervised learning and fine-tuning

Published in Applied Intelligence, 2025

Proposes SSHemo, a self-supervised generative learning model for hemodynamic parameter prediction from arterial blood pressure waveforms, addressing data scarcity through self-supervised learning.

Recommended citation: Liao, K., Elibol, A., Gao, Z., Meng, L., & Chong, N. Y. (2025). Predicting hemodynamic parameters based on arterial blood pressure waveform using self-supervised learning and fine-tuning. Applied Intelligence, 55(7), 481.
Download Paper

Berp: A blind estimator of room parameters for single-channel noisy speech signals

Published in IEEE Transactions on Audio, Speech and Language Processing, 2025

Proposes BERP, a universal approach to blindly estimate room acoustical parameters, room geometrical parameters, and occupancy levels from noisy single-channel speech signals using attention mechanisms.

Recommended citation: Wang, L., Lu, Y., Gao, Z., Li, K., Huang, J., Kong, Y., & Okada, S. (2025). Berp: A blind estimator of room parameters for single-channel noisy speech signals. IEEE Transactions on Audio, Speech and Language Processing.
Download Paper

Online 3D Bin Packing with Fast Stability Validation and Stable Rearrangement Planning

Published in Robotics and Computer-Integrated Manufacturing (Under Review - Second Round), 2025

Proposes a novel framework that integrates packing policy with structural stability validation and heuristic planning, introducing Load Bearable Convex Polygon for computationally efficient stable loading positions.

Recommended citation: Gao, Z., Wang, L., Kong, Y., & Chong, N. Y. (2025). Online 3D Bin Packing with Fast Stability Validation and Stable Rearrangement Planning. Robotics and Computer-Integrated Manufacturing (Under Review).
Download Paper

Shortcut-enhanced Multimodal Backdoor Attack in Vision-guided Robot Grasping

Published in IEEE Transactions on Automation Science and Engineering, 2025

Proposes SEMBA, a novel backdoor attack method on multimodal vision-guided robot grasping in high-clutter scenarios, using Multimodal Shortcut Searching Algorithm and Multimodal Trigger Generation.

Recommended citation: Li, C., Gao, Z., & Chong, N. Y. (2025). Shortcut-enhanced Multimodal Backdoor Attack in Vision-guided Robot Grasping. IEEE Transactions on Automation Science and Engineering.
Download Paper

Visual Prompt Guided Unified Pushing Policy

Published in arXiv preprint, 2026

Proposes a unified pushing policy that incorporates a lightweight prompting mechanism into a flow matching policy to guide reactive, multimodal pushing actions for object rearrangement and table-cleaning tasks.

Recommended citation: Bui, H.*, Gao, Z.*, Hosoda, Y., & Lee, J. (2026). Visual Prompt Guided Unified Pushing Policy. arXiv preprint arXiv:2602.19193. (* Equal contribution, co-corresponding authors)
Download Paper

talks

teaching