I am a 4th year PhD candidate in computer science (robotics & AI) at the Interactive and Collaborative Autonomous Robotic Systems (ICAROS) Lab advised by Prof. Stefanos Nikolaidis at the University of Southern California (USC). I got my bachelor's degree from Zhejiang University (ZJU).
Research Interests
Robotics - Science: I'm interested in learning and planning for multi-robot and human-robot systems.
Robotics - Systems: I'm interested in developing robotic systems for real-world problems.
- domestic robotics: cooking, hair brushing robots.
- field robotics: mining robots.
Press
- Our work on learning robot collaborative manipulation plans from YouTube videos was selected as Paper of the Month by Kinova Robotics.
- Our work on robotic hair brushing was highlighted at the Fortune.
Demos
Presentations
- A MIP-based Approach for Multi-Robot Geometric Task-and-Motion Planning, IEEE International Conference on Automation Science and Engineering, August 2022. [slides]
- Robot Learning Collaborative Manipulation Plans from YouTube Cooking Videos, R:SS Workshop on Emergent Behaviors in Human Robot Systems, July 2020. [slides] [video]
- Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robot Skills, Southern California Robotics Symposium, April 27 2019. [slides] [poster]
Publications
Journal Papers- Ryan Julian, Eric Heiden, Zhanpeng He, Hejia Zhang, Stefan Schaal, Joseph J. Lim, Gaurav S. Sukhatme, Karol Hausman. Scaling Simulation-to-Real Transfer by Learning a Latent Space of Robot Skills. International Journal of Robotics Research (IJRR), 2020. [paper]
- Chaoyang Zhu, Kejie Huang, Shuyuan Yang, Ziqi Zhu, Hejia Zhang, Haibin Shen. An Efficient Hardware Accelerator for Structured Sparse Convolutional Neural Networks on FPGA. IEEE Transactions on Very Large Scale Integration Systems (TVLSI), 2020. [paper]
- Shivin Dass*, Karl Pertsch*, Hejia Zhang, Youngwoon Lee, Joseph J. Lim, Stefanos Nikolaidis. Assisted Teleoperation for Scalable Robot Data Collection. In Robotics: Science and Systems (R:SS), 2023. [arXiv] [project page] [code]
- Hejia Zhang, Shao-Hung Chan, Jie Zhong, Jiaoyang Li, Sven Koenig, Stefanos Nikolaidis. A MIP-Based Approach for Multi-Robot Geometric Task-and-Motion Planning. In The 18th IEEE International Conference on Automation Science and Engineering (CASE), 2022. [pdf]
- Hejia Zhang*, Matthew Fontaine*, Amy Hoover, Julian Togelius, Bistra Dilkina, Stefanos Nikolaidis. Video Game Level Repair via Mixed Integer Linear Programming. In The 16th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-20), 2020 (Oral Presentation; 25% acceptance rate). [pdf] [paper] [bibtex] [code]
- Hejia Zhang, Po-Jen Lai, Sayan Paul, Suraj Kothawade and Stefanos Nikolaidis. Learning Collaborative Action Plans from Unlabeled YouTube Videos. International Symposium on Robotics Research (ISRR), 2019. [pdf] [bibtex]
- Ryan Julian*, Eric Heiden*, Zhanpeng He, Hejia Zhang, Stefan Schaal, Joseph J. Lim, Gaurav S. Sukhatme, Karol Hausman. Scaling simulation-to-real transfer by learning composable robot skills. In International Symposium on Experimental Robotics (ISER), 2018. [pdf] [bibtex]
- Shivin Dass, Karl Pertsch, Hejia Zhang, Youngwoon Lee, Joseph J. Lim, Stefanos Nikolaidis. Assisted Teleoperation for Scalable Robot Data Collection. In Conference on Robot Learning (CoRL) Workshop on Pre-training Robot Learning, 2022.
- Hejia Zhang, Shao-Hung Chan, Jie Zhong, Jiaoyang Li, Sven Koenig, Stefanos Nikolaidis. A MIP-Based Approach for Multi-Robot Geometric Task-and-Motion Planning. In Southern California Robotics Symposium (SCR), 2022. [pdf] [bibtex]
- Hejia Zhang, Stefanos Nikolaidis. Robot Learning Collaborative Manipulation Plans from YouTube Cooking Videos. In R:SS Workshop on Emergent Behaviors in Human-Robot Systems, 2020. [pdf] [bibtex] [talk] [slides]
- Hejia Zhang, Eric Heiden, Stefanos Nikolaidis, Joseph J. Lim, Gaurav S. Sukhatme. Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robotic Manipulation Skills. In Southern California Robotics Symposium (SCR), 2019. [pdf] [bibtex]
- Zhanpeng He*, Ryan Julian*, Eric Heiden, Hejia Zhang, Stefan Schaal, Joseph J. Lim, Gaurav S. Sukhatme, Karol Hausman. Simulator Predictive Control: Using Learned Task Representations and MPC for Zero-Shot Generalization and Sequencing. In Conference on Neural Information Processing Systems (NeurIPS) 2018 Deep Reinforcement Learning Workshop. [pdf] [video] [bibtex]
- Hejia Zhang, Jie Zhong, Stefanos Nikolaidis. Zero-Shot Imitating Collaborative Manipulation Plans from YouTube Cooking Videos. In arXiv [arXiv]
- Eric Heiden*, David Millard*, Hejia Zhang and Gaurav S. Sukhatme. Interactive Differentiable Simulation. In arXiv. [arXiv] [bibtex]
- Hejia Zhang, Eric Heiden, Stefanos Nikolaidis, Joseph J. Lim and Gaurav S. Sukhatme. Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robot Skills. In arXiv. [pdf] [video] [poster] [arXiv] [bibtex]