arXiv subjects

Jonathan Kao

Publications and source records attributed to Jonathan Kao.

3 recordsLinked to original sources

arXiv2026

Intent at a Glance: Gaze-Guided Robotic Manipulation via Foundation Models

Designing intuitive interfaces for robotic control remains a central challenge in enabling effective human-robot interaction, particularly in assistive care settings. Eye gaze offers a fast, non-intrusive, and intent-rich input modality, making it an attractive channel for conveying user goals. In this work, we present GAMMA (Gaze Assisted Manipulation for Modular Autonomy), a system that leverages ego-centric gaze tracking and a vision-language model to infer user intent and autonomously execute robotic manipulation tasks. By contextualizing gaze fixations within the scene, the system maps visual attention to high-level semantic understanding, enabling skill selection and parameterization without task-specific training. We evaluate GAMMA on a range of table-top manipulation tasks and compare it against baseline gaze-based control without reasoning. Results demonstrate that GAMMA provides robust, intuitive, and generalizable control, highlighting the potential of combining foundation models and gaze for natural and scalable robot autonomy. Project website: https://gamma0.vercel.app/

cs.RO↗

arXiv2022

Gacs-Korner Common Information Variational Autoencoder

We propose a notion of common information that allows one to quantify and separate the information that is shared between two random variables from the information that is unique to each. Our notion of common information is defined by an optimization problem over a family of functions and recovers the G\'acs-K\"orner common information as a special case. Importantly, our notion can be approximated empirically using samples from the underlying data distribution. We then provide a method to partition and quantify the common and unique information using a simple modification of a traditional variational auto-encoder. Empirically, we demonstrate that our formulation allows us to learn semantically meaningful common and unique factors of variation even on high-dimensional data such as images and videos. Moreover, on datasets where ground-truth latent factors are known, we show that we can accurately quantify the common information between the random variables.

cs.LG↗

arXiv2009

A bubble-powered micro-rotor: conception, manufacturing, assembly, and characterization

A steady fluid flow, called microstreaming, can be generated in the vicinity of a micro-bubble excited by ultrasound. In this article, we use this phenomenon to assemble and power a microfabricated rotor at rotation speeds as high as 625 rpm. The extractible power is estimated to be on the order of a few femtowatts. A first series of experiments with uncontrolled rotor shapes is presented, demonstrating the possibility of this novel actuation scheme. A second series of experiments with 65 micron rotors micromanufactured in SU-8 resin are presented. Variables controlling the rotation speed and rotor stability are investigated, such as the bubble diameter, the acoustic excitation frequency and amplitude, and the rotor geometry. Finally, an outlook is provided on developing this micro-rotor into a MEMS-based motor capable of delivering tunable, infinitesimal rotary power at the microscale.

physics.flu-dyn↗