Jacky Liang

Hello!

I’m a second year PhD student at Carnegie Mellon University’s Robotics Institute, and I’m co-advised by Prof. Oliver Kroemer and Prof. Maxim Likhachev.

My research interest lies in enabling robots to perform complex tasks in semi-structured environments by combining methods in model-based planning and model-free learning, leveraging both the performance guarantees of plans and the robustness to uncertainty of learned policies.

Before joining RI I interned at NVIDIA for the Isaac project and worked on using GPU-accelerated physics simulations for robot learning. Before that and during my time at UC Berkeley I did research in robot grasping and manipulation with Prof. Ken Goldberg.

I write for and co-run Skynet Today, a website dedicated to covering AI news and trends without hype. Check us out and subscribe if you like what you see :)

Updates

10/22/2019 - Our article covering the contributions of and the responses to OpenAI’s in-hand Rubik’s cube manipulation work.

OpenAI’s dexterous robotic hand — separating progress from PR

2/4/2019 - Check out this in-depth article I’ve co-written on the impact of AI and automation on jobs! We’ve done a thorough review on recent studies and tried to give a balanced take on the subject:

Job loss due to AI - How bad is it going to be?

Research

Preprints

DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System

Ankur Handa, Karl Van Wyk, Wei Yang, Jacky Liang, Yu-Wei Chao, Qian Wan, Stan Birchfield, Nathan Ratliff, Dieter Fox. October 2019. [arXiv] [PDF] [Website]

Publications

Homography-Based Deep Visual Servoing Methods for Planar Grasps

Austin S. Wang, Wuming Zhang, Daniel Troniak, Jacky Liang, Oliver Kroemer. International Conference on Intelligent Robots and Systems (IROS), Macau, China, November 2019. [Paper]

Towards Precise Robotic Grasping by Probabilistic Post-grasp Displacement Estimation

Jialiang Zhao, Jacky Liang, Oliver Kroemer. Field and Service Robotics (FSR), Tokyo, Japan, August 2019. [arXiv] [Paper]

GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning

Jacky Liang*, Viktor Makoviychuk*, Ankur Handa*, Nuttapong Chentanez, Miles Macklin, Dieter Fox. Conference on Robot Learning (CoRL), Zurich, Switzerland, October 2018. [arXiv] [PDF] [Website]

Using dVRK Teleoperation to Facilitate Deep Learning of Automation Tasks for an Industrial Robot

Jacky Liang, Jeffrey Mahler, Michael Laskey, Pusong Li, Ken Goldberg. IEEE Conference on Automation Science and Engineering (CASE), Xi’an, China, August 2017. Finalist, Best Student Paper Award. [PDF] [Website]

Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics

Jeffrey Mahler, Jacky Liang, Sherdil Niyaz, Michael Laskey, Richard Doan, Xinyu Liu, Juan Aparicio Ojea, Ken Goldberg. Robotics: Science and Systems (RSS). MIT Cambridge, MA. July 2017. [PDF] [Website]

Design of Parallel-Jaw Gripper Tip Surfaces for Robust Grasping

Menglong Guo, David V. Gealy, Jacky Liang, Jeffrey Mahler, Aimee Goncalves, Stephen McKinley, Ken Goldberg. 2017 IEEE International Conference on Robotics and Automation (ICRA). May 2017. [PDF]

* Equal Contribution.

Teaching

CS188 Introduction to Artificial Intelligence

Spring 2017 Discussion Teaching Assistant

EE16A Design of Information Devices and Systems

Fall 2016, 2017 Discussion Teaching Assistant