Danfei Xu

[New] I will start as an Assistant Professor at the School of Interactive Computing at Georgia Tech in Fall 2022 and will be hiring Ph.D. students in the upcoming 2021/2022 cycle. If you are interested in pushing the frontier of Robotics and Machine Learning research with me at GaTech, please apply through the official application portal and list me as a faculty of interest.

I recently graduated with a Ph.D. in CS from Stanford (2021) and started as a Research Scientist at NVIDIA AI Research. I was fortunate to be advised by Fei-Fei Li and Silvio Savarese who co-lead the Stanford Vision and Learning Lab. I work in the intersection of Robotics and Machine Learning.

Prior to joining Stanford, I received my B.S. from Columbia University (SEAS'15). I've spent time at DeepMind UK (2019), ZOOX (2017), Autodesk Research (2016), CMU RI (2014), and Columbia Robotics Lab (2013-2015).

Email / Google Scholar / CV (May 2021) / Github / Twitter

Research

My research goal is to enable physical autonomy in everyday human environments with minimum expert intervention. Towards this goal, my works draw equally from Robotics, Machine Learning, and Computer Vision, including topics such as imitation & reinforcement learning, representation learning, manipulation, and human-robot interaction. My current research focuses on visuomotor skill learning, structured representations for long-horizon planning, and data-driven approaches to human-robot collaboration.

Thesis: Compositional Reasoning in Robot Learning (talk recording, slides)

News

[Sep 2021] Our RoboMimic work will appear as an oral presentation at CoRL 2021 (top 6% submissions).
[Sep 2021] Our new work on training robot collaborators from demonstrations is accepted at CoRL 2021.
[Aug 2021] We released a large-scale study on learning skills from human demos (code+dataset).
[Aug 2021] New work on learning human-robot collaboration policies from demonstrations.
[July 2021] Generalization Through Hand-Eye Coordination accepted to IROS 2021.
[April 2021] We are organizing an ICCV workshop on Structural and Compositional Learning on 3D Data.
[April 2021] I will be co-instructing the Stanford CS231n course in Spring 2021.
[Mar 2021] Deep Affordance Foresight accepted at ICRA 2021.
[Feb 2021] Invited talk at MIT Vision Seminar.
[Dec 2020] Invited talk at DeepMind.
[Dec 2020] Invited talk at Cornell Robotics Seminar.

Demos

Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations (2020)

6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints (2020)

Preprints

Human-in-the-Loop Imitation Learning using Remote Teleoperation
Ajay Mandlekar, Danfei Xu, Roberto Martin-Martin, Yuke Zhu, Li Fei-Fei, Silvio Savarese
In Submission

Human-in-the-loop learning for complex manipulation tasks.

Publications

What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
Ajay Mandlekar, Danfei Xu, Josiah Wong, Soroush Nasiriany, Chen Wang, Rohun Kulkarni, Li Fei-Fei, Silvio Savarese, Yuke Zhu, Roberto Martin-Martin
CoRL 2021 (oral, to appear)

[code+dataset][website][blogpost]

A large-scale study on learning manipulation skills from human demonstrations.

Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration
Chen Wang, Claudia D'Arpino, Danfei Xu, Li Fei-Fei, Karen Liu, Silvio Savarese
CoRL 2021 (to appear)

Learning human-robot collaboration policies from human-human collaboration demonstrations.

Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control
Chen Wang*, Rui Wang*, Ajay Mandlekar, Li Fei-Fei, Silvio Savarese, Danfei Xu
IROS 2021

An learnable action space for recovering human's hand-eye coordination behaviors by learning from human demonstrations.

Deep Affordance Foresight: Planning Through What Can Be Done in the Future
Danfei Xu, Ajay Mandlekar, Roberto Martin-Martin, Yuke Zhu, Silvio Savarese, Li Fei-Fei
(Long version) ICRA 2021
(Short version) Oral Presentation, NeurIPS Workshop on Object Representations for Learning and Reasoning, 2020

We extend the classical definition of affordance to enable generalizable long-horizon planning.

Positive-Unlabeled Reward Learning
Danfei Xu, Misha Denil
(Long version) CoRL 2020
(Short version) Late-Breaking Paper, NeurIPS Deep Reinforcement Learning Workshop 2019

[Video]

An algorithm framework that simultaneously addresses the reward delusion problem in supervised reward learning and the overfitting discriminator problem in adversarial imitation learning.

	Procedure Planning in Instructional Videos Chien-Yi Chang, De-An Huang, Danfei Xu, Ehsan Adeli, Li Fei-Fei Juan Carlos Niebles ECCV, 2020 Learning to plan from instructional videos.
	Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations Ajay Mandlekar, Danfei Xu, Roberto Martin-Martin, Silvio Savarese, Li Fei-Fei RSS, 2020 [website] [video] [blog post] Learning visuomotor policies that can generalize across long-horizon tasks by modeling latent compositional structures.
	6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints Chen Wang, Roberto Martin-Martin, Danfei Xu, Jun Lv, Cewu Lu, Li Fei-Fei, Silvio Savarese, Yuke Zhu ICRA, 2020 [website] [video] [code] Real-time category-level 6D object tracking from RGB-D data.
	Regression Planning Networks Danfei Xu, Roberto Martin-Martin, De-An Huang, Yuke Zhu, Silvio Savarese, Li Fei-Fei NeurIPS, 2019 [code] [poster] A flexible neural network architecture for learning to plan from video demonstrations.
	Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning De-An Huang, Danfei Xu, Yuke Zhu, Silvio Savarese, Li Fei-Fei, Juan Carlos Niebles IROS, 2019 [blog post] One-shot imitation learning via hybrid neural-symbolic planning.
	Situational Fusion of Visual Representation for Visual Navigation William B. Shen, Danfei Xu, Yuke Zhu, Leonidas Guibas, Li Fei-Fei, Silvio Savarese ICCV, 2019 Learning generalizable navigation policy from mid-level visual representations.
	DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion Chen Wang, Danfei Xu, Yuke Zhu, Roberto Martin-Martin, Cewu Lu, Li Fei-Fei, Silvio Savarese CVPR, 2019 [website] [video] [code] Dense RGB-depth sensor fusion for 6D object pose estimation.
	Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration De-An Huang, Suraj Nair, Danfei Xu, Yuke Zhu, Animesh Garg, Li Fei-Fei, Silvio Savarese, Juan Carlos Niebles CVPR*, 2019 (Oral) [blog post] Generate executable task graphs from video demonstrations.
	Neural Task Programming: Learning to Generalize Across Hierarchical Tasks Danfei Xu, Suraj Nair, Yuke Zhu, Julian Gao, Animesh Garg, Li Fei-Fei, Silvio Savarese ICRA, 2018 [website] [video] [Two Minute Papers] [blog post] Neural Task Programming (NTP) is a meta-learning framework that learns to generate robot-executable neural programs from task demonstration video.
	PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation Danfei Xu, Ashesh Jain, Dragomir Anguelov CVPR, 2018 End-to-end 3D Bounding Box Estimation via sensor fusion.
	Scene Graph Generation by Iterative Message Passing Danfei Xu, Yuke Zhu, Christopher B. Choy, Li Fei-Fei CVPR, 2017 [website] [code] We propose an end-to-end model that jointly infers object category, location, and relationships. The model learns to iteratively improve its prediction by passing messages on a scene graph.
	3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction Christopher B. Choy, Danfei Xu, JunYoung Gwak, Silvio Savarese ECCV, 2016 [website] [code] We propose an end-to-end 3D reconstruction model that unifies single- and multi-view reconstruction.
	Model-Driven Feed-Forward Prediction for Manipulation of Deformable Objects Yinxiao Li , Yan Wang , Yonghao Yue , Danfei Xu, Michael Case , Shih-Fu Chang , Eitan Grinspun , Peter K. Allen IEEE TASE, 2016 [website] Deformable object manipulation with an application of personal assitive robot. This is the journal paper of our "laundry robot" series: ICRA 2015 IROS 2015 ICRA 2016
	Topometric localization on a road network Danfei Xu, Hernan Badino, Daniel Huber IROS, 2015 Vision-based localization on a probabilistic road network.
	Tactile identification of objects using Bayesian exploration Danfei Xu, Gerald E. Loeb, Jeremy Fishel ICRA, 2013 Object classification using multi-modal tactile sensing.