profile photo

Baichuan Huang

I am a 4th year PhD student in Computer Science at Rutgers University, advised by Jingjin Yu, also worked with Abdeslam Boularias.

Previously I was a Master student in Prof. Stefanie Tellex's H2R lab at Brown University. Mostly worked on Drone and Mixed Reality.

Google Scholar  •  Github  •  CV
Email: baichuan.huang at rutgers dot edu


I'm interested in Robotics. Currently, I am working on robot manipulation, learning and planning, I am also touching other research topics.

Parallel Monte Carlo Tree Search with Batched Rigid-body Simulations for Speeding up Long-Horizon Episodic Robot Planning

Baichuan Huang, Abdeslam Boularias, Jingjin Yu
IEEE International Conference on Intelligent Robots and Systems (IROS) 2022
PDF  •  Code  •  Video

We propose a novel Parallel Monte Carlo tree search with Batched Simulations (PMBS) algorithm for accelerating long-horizon, episodic robotic planning tasks. Leveraging a GPU-based large-scale simulator, PMBS introduces massive parallelism into MCTS for solving planning tasks through the batched execution of a large number of concurrent simulations, which allows for more efficient and accurate evaluations of the expected cost-to-go over large action spaces.

Interleaving Monte Carlo Tree Search and Self-Supervised Learning for Object Retrieval in Clutter

Baichuan Huang, Teng Guo, Abdeslam Boularias, Jingjin Yu
International Conference on Robotics and Automation (ICRA) 2022
PDF  •   •  Code  •  Video

In this study, working with the task of object retrieval in clutter, we have developed a robot learning framework in which Monte Carlo Tree Search (MCTS) is first applied to enable a Deep Neural Network (DNN) to learn the intricate interactions between a robot arm and a complex scene containing many objects, allowing the DNN to partially clone the behavior of MCTS. In turn, the trained DNN is integrated into MCTS to help guide its search effort. We call this approach learning-guided Monte Carlo tree search for Object REtrieval (MORE), which delivers significant computational efficiency gains and added solution optimality.

Visual Foresight Trees for Object Retrieval from Clutter with Nonprehensile Rearrangement

Baichuan Huang, Shuai D. Han, Jingjin Yu, Abdeslam Boularias
IEEE Robotics and Automation Letters (RA-L) 2022
PDF  •  Code  •  Video

Object retrieval in dense clutter is an important skill for robots to operate in households and everyday environments effectively. The proposed solution, Visual Foresight Trees (VFT), intelligently rearranges the clutter surrounding a target object so that it can be grasped easily. The predictive network provides visual foresight and is used in a tree search as a state transition function in the space of scene images. The tree search returns a sequence of consecutive push actions yielding the best arrangement of the clutter for grasping the target object.

Toward Fully Automated Metal Recycling using Computer Vision and Non-Prehensile Manipulation

Shuai D Han, Baichuan Huang, Sijie Ding, Changkyu Song, Si Wei Feng, Ming Xu, Hao Lin, Qingze Zou, Abdeslam Boularias, Jingjin Yu
International Conference on Automation Science and Engineering (CASE) 2021
PDF  •  Video

Due to inherent irregularities in recyclable materials, sorting valuable metals (e.g., aluminum and copper) via mechanical means is a difficult task resisting full automation. In this work, leveraging the latest development in machine learning and robot learning, we develop an image-based sorting system for tackling this challenging task. In addition to delivering a highly accurate deep learning model for reliably distinguishing pure scrap pieces from pieces containing impurities with over 95% precision/recall, we further automate the process of sample preparation, data acquisition/labeling/analysis, and machine learning model training.

DIPN: Deep Interaction Prediction Network with Application to Clutter Removal

Baichuan Huang, Shuai D. Han, Abdeslam Boularias, Jingjin Yu
International Conference on Robotics and Automation (ICRA) 2021
PDF  •  Code  •  Video

We propose a Deep Interaction Prediction Network (DIPN) for learning to predict complex interactions that ensue as a robot end-effector pushes multiple objects. DIPN “imagines” the effect of a push action and generates an accurate synthetic image of the predicted outcome. DIPN is shown to be sample efficient when trained in simulation or with a real robotic system. The high accuracy of DIPN allows direct integration with a grasp network, yielding a robotic manipulation system capable of executing challenging clutter removal tasks while being trained in a fully self-supervised manner.

Advanced Autonomy on a Low-Cost Educational Drone Platform

Luke Eller*, Théo Guérin*, Baichuan Huang*, Garrett Warren*, Sophie Yang*, Josh Roy, Stefanie Tellex
IEEE International Conference on Intelligent Robots and Systems (IROS) 2019
PDF  •  Code  •  Video

PiDrone is a quadrotor platform created to accompany an introductory robotics course. We present a hardware and software framework for an autonomous aerial robot, in which all software for autonomy can run onboard the drone, implemented in Python. We present an Unscented Kalman Filter (UKF) for accurate state estimation. Next, we present an implementation of Monte Carlo (MC) Localization and FastSLAM for Simultaneous Localization and Mapping (SLAM).

Planning with State Abstractions for Non-Markovian Task Specifications

Yoonseon Oh, Roma Patel, Thao Nguyen, Baichuan Huang, Ellie Pavlick, Stefanie Tellex
Robotics: Science and Systems (RSS) 2019
PDF  •  Code  •  Video

We introduce the Abstract Product Markov Decision Process (AP-MDP), a novel approach capable of representing non-Markovian reward functions at different levels of abstractions. The AP-MDP framework translates LTL into its corresponding automata, creates a product Markov Decision Process (MDP) of the LTL specification and the environment MDP, and decomposes the problem into subproblems to enable efficient planning with abstractions. We present a neural sequence-to-sequence model trained to translate language commands into LTL expression.

Flight, camera, action! using natural language and mixed reality to control a drone

Baichuan Huang, Deniz Bayazit, Daniel Ullman, Nakul Gopalan, Stefanie Tellex
International Conference on Robotics and Automation (ICRA) 2019
PDF  •  Code  •  Video

With increasing autonomy, robots like drones are increasingly accessible to untrained users. For a wider adoption of these technologies by the public, a much higher-level interface, such as natural language or mixed reality (MR), allows the automation of the control of the agent in a goal-oriented setting. We present an interface that uses natural language grounding within an MR environment to solve high-level task and navigational instructions given to an autonomous drone.

Model checking quantum key distribution protocols

Baichuan Huang, Yan Huang, Jiaming Kong, Xin Huang
International Conference on Information Technology in Medicine and Education (ITME) 2016

Quantum key distribution protocols use quantum information theories to guarantee the security of key exchange procedure, and model checking is a verification technique which could be used to test the security of it. In this paper, a new group quantum key distribution protocol is designed based on BB84 protocol, which is a possible solution to handle the security issue in communication between multi-users.

A study on the reliability of software defined wireless sensor network

Yulin Lu, Xin Huang, Baichuan Huang, Weiwen Xu, Qian Zhang, Ruiyang Xu, Dawei Liu
IEEE International Conference on Smart City/SocialCom/SustainCom (SmartCity) 2015

Software defined wireless sensor network is an network defined for dynamic and secure control of smart devices. It decouples the data plane and the control plane, allowing administrators to reprogram the smart devices in the network and backbone network devices based on users' varying demands. In this paper, a typical architecture of software defined wireless sensor network is proposed.

Layout from Jon Barron. © Baichuan Huang