Chuer Pan

Hi there! I am a first-year Electrical Engineering PhD student at Stanford University, advised by Prof. Shuran Song. I am a member of Robotics and Embodied AI Lab @ Stanford.

I am interested in developing robust, compliant and generalizable robot systems that can efficiently acquire high-precision, contact-rich manipulation skills from human and transfer to new scenarios with minimal adapation.

Privously, I worked on few-shot 6D object pose estimation for robot manipulation with David Held at CMU Robotics Institute. There I defended my MS in Robotics. Before that, I obtained my BASc from Engineering Science at the University of Toronto, specializing in Robotics. There, I worked on deep natural language processing with Frank Rudzicz at Vector Institute. During my early exposure at research, I worked on microfabrication for microfluidics with Eugenia Kumacheva at the University of Toronto.

During undergrad, I worked on motion planning for AV at aUToronto.

Email: chuerpan at stanford dot edu

Google Scholar  /  Twitter

Research

I'm interested in robotics, machine learning and computer vision.

Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robot

We propose a portable data collection and policy learning framework that allows direct skill transfer from in-the-wild human demonstrations to deployable robot policies, allowing zero-shot generalizable dynamic, bimanual, precise, and long-horizon robot policies.

Open X-Embodiment: Robotic Learning Datasets and RT-X Models

We introduce the largest robot learning dataset to date with 1M+ real robot trajectories, spanning 22 robot embodiments. We train large, transformer-based policies on the dataset and show that co-training with our diverse dataset substantially improves performance.

TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation

We propose a vision-based system that learns to estimate the task specific pose relationship (cross-pose) between pairs of interacting object using learned cross-object correspondences. We demonstrate that our method is able to learn from just 10 real point cloud demonstration with no pose annotations needed and generalize to novel instances within the trained object category.

Deep Projective Rotation Estimation through Relative Supervision

We propose a new algorithm for self-supervised orientation estimation which utilizes Modified Rodrigues Parameters to stereographically project the closed manifold of SO(3) to the open manifold of 3D Euclidean space, which avoids the local optima common when naively applying relative self-supervision for object orientation estimation, allowing for faster convergence and lower rotational error on relative rotation estimation.

Examining the rhetorical capacities of neural language models

We propose a method that quantitatively evaluates the rhetorical capacities of neural language models (LMs) by evaluating their abilities to encode a set of linguistic features derived from Rhetorical Structure Theory (RST). Our experiments show that BERT-based LMs outperform other Transformer LMs such as GPT-2 and XLNet, revealing richer discourse knowledge in their intermediate layer representations.

An exploration of the reflow technique for the fabrication of an in vitro microvascular system to study occlusive clots

We introduce a reflow technique for fabrication of multi-level microchannel network with circular cross-section to systematically study the dissolution effects of thrombolytic drug on occlusive embolic clots in microvascular system.

Design and source code from Jon Barron's website