Hi, I am a PhD graduate in Computer Science from the Robotics Lab at Columbia University. I am a software engineer at Palantir Technologies. Before Palantir, I worked at Amazon on Amazon Go. I also worked on robotics at Microsoft Research.
At Columbia, I worked with Professor Peter Allen. My research interest lies in robotic grasping and object manipulation - enabling robots to grasp objects in a robust and functionally appropriate way and dexterously manipulate them. I am interested in data-driven approaches and believe that learning based on large amount of data, either generated in simulation or collected in physical robotic tasks, would improve robots’ intelligence and capabilities.
Ph.D. Dissertation: “Stable and Semantic Robotic Grasping Using Tactile Feedback” [url]
Research Topics go to research page
Task Modeling and Learning by Demonstration [IROS14, video] [IROS10]
Building autonomous robots is a dream for most robotists, if not all. Understanding necessary logical components of a task is critical for modeling a task. An effective task model will allow 1) a user to easily synthesize such a task and 2) a robot to efficiently execute such a task. In order to grant more people access to programming robots, the technical bar, which currently requires the programmer to have a significant amount of robotics background, should be lowered. Learning by demonstration is one approach that can potentially overcome this hurdle and help us achieve the goal.
Tactile-based Grasp Control [AURO13] [IROS13] [ICRA12]
Merely executing a planned-to-be-stable grasp generated within a simulation environment will not likely end up with a stable grasp in the physical world. Uncertainties exist in almost every component in a robot system: camera calibration, kinematic chain modeling, angular sensor modeling, etc. Vision systems may be able to provide close-to-accurate object poses, yet it is faced with tremendous difficulties while the hand is close to the object of interest, among which occlusion and resolution are obvious. Tactile sensing provides real-time, local, and detailed information about hand-object interaction and can be used collaboratively to improve a grasping process and make it more robust than otherwise.
Semantic Grasping [AURO14] [IROS12]
Stable grasping may not be sufficient for specific tasks considering potential task related constraints, i.e. relative hand posture, functional parts to grasp, etc. A semantic grasping approach takes into consideration task-related constraints in a grasp planning process and generates stable robotic grasps that are suitable for specific tasks.
Previous Projects
ARM-S: DARPA’s Autonomous Robotic Manipulation, software track
partner with SRI International and Carnegie Mellon University
DRC: DARPA’s Robotics Challenge, track A
partner with Drexel University, KAIST, Georgia Tech, WPI, Ohio State, Indiana University, Purdue, Swarthmore College, University of Delaware
Journal Articles
Hao Dang and Peter K. Allen, Semantic Grasping: Planning Task-Specific Stable Robotic Grasps, Autonomous Robots, 2014. [url, bib]
Hao Dang and Peter K. Allen, Stable Grasping under Pose Uncertainty Using Tactile Feedback, Autonomous Robots, 2013. [url, bib]
Conference Papers
Ashley Feniello, Hao Dang, Stan Birchfield, Program Synthesis by Examples for Object Repositioning Tasks, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 14-18, 2014, Chicago, USA. [pdf, video, bib]
Hao Dang and Peter K. Allen, Grasp Adjustment on Novel Objects Using Tactile Experience from Similar Local Geometry, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), November 3-7, 2013, Tokyo, Japan. [pdf, bib]
Hao Dang, Youngbum Jun, Paul Oh, and Peter K. Allen, Planning Complex Physical Tasks for Disaster Response with a Humanoid Robot, IEEE International Conference on Technologies for Practical Robot Applications (TePRA), April 22-23, 2013, Woburn, USA. [pdf, bib]
Hao Dang and Peter K. Allen, Semantic Grasping: Planning Robotic Grasps Functionally Suitable for An Object Manipulation Task, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 7-11, 2012, Algarve, Portugal. [pdf, bib]
Hao Dang and Peter K. Allen, Learning Grasp Stability, IEEE Conference on Robotics and Automation (ICRA), May 14-18, 2012, St. Paul, USA. [pdf, bib]
Hao Dang, Jonathan Weisz, and Peter K. Allen, Blind Grasping: Stable Robotic Grasping Using Tactile Feedback and Hand Kinematics, IEEE Conference on Robotics and Automation (ICRA), May 9-13, 2011, Shanghai, China. [pdf, bib]
Hao Dang and Peter K. Allen, Robot Learning of Everyday Object Manipulations via Human Demonstration, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 18-22, 2010, Taipei, ROC. [pdf, bib]
Corey Goldfeder, Matei Ciocarlie, Jaime Peretzman, Hao Dang and Peter K. Allen, Data-Driven Grasping with Partial Sensor Data, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 11-15, 2009, St. Louis, USA. [pdf, bib]
Matei Ciocarlie, Hao Dang, Jamie Lukos, Marco Santello, Peter Allen, Functional Analysis of Finger Contact Locations during Grasping Third Joint EUROHAPTICS Conference and Symposium on Haptic Interfaces for Virtual Environment and Teleoperator Systems, March 18-20, 2009, Salt Lake City, USA. [pdf, bib]
Corey Goldfeder, Matei Ciocarlie, Hao Dang and Peter K. Allen, The Columbia Grasp Database, IEEE Conference on Robotics and Automation (ICRA), May 12-17, 2009, Kobe, Japan. [pdf, bib]
Workshops
Hao Dang and Peter K. Allen, Tactile Experience-based Robotic Grasping, Workshop on Advances in Tactile Sensing and Touch based Human-Robot Interaction, 7th ACM/IEEE International Conference on Human-Robot Interaction(HRI), March 5-9, 2012, Boston, USA. [pdf, bib]
Contact
Email: dang@cs.columbia.edu
Phone: (212) 939-7088
Address:
Department of Computer Science
Columbia University
500 W 120 Street, M.C. 0401
New York, NY, 10027
Personal
I am from Chongqing, China.
I love traveling the most. I also enjoy other activities such as cycling, hiking, table tennis, tennis, badminton, and photography.
