Just Be Exemplary

Ph.D. Researcher in Robotics
Department of Computer Science
Clarkson University
Potsdam, New York, United States
Email: contact (at)

Photo of Xinchao Song
About Me  Education  Experience  Publications  Certifications


About Me

I am currently a Ph.D. Student in Computer Science at Clarkson University, Potsdam, New York. My advisers are Prof. Sean Banerjee and Prof. Natasha Banerjee. Before joining Clarkson, I received my master’s degree in computer science at Northeastern University, Boston, Massachusetts, where I was advised by Prof. Robert Platt. I also worked in the mechanical engineering field for many years with a master of science in mechanical engineering.

My research interest is robotics and deep learning with a focus on multimodal perception, planning, control, and manipulation, especially from an interdisciplinary perspective of software and hardware.


Ph.D. Student in Computer Science

Clarkson University, Potsdam, New York, 2021 - Present

Master of Science in Computer Science

Northeastern University, Boston, Massachusetts, 2020

Master of Science in Mechanical Engineering

Northeastern University, Boston, Massachusetts, 2014

Bachelor of Engineering in Mechatronics Engineering

Tianjin University of Science and Technology, Tianjin, China, 2011


Ph.D. Research Assistant in Robotics

Terascale All-sensing Research Studio (TARS) at Clarkson University, Potsdam, New York, 2021 - Present

Graduate Teaching Assistant in Computer Sciences

Clarkson University, Potsdam, New York, 2021 - Present

Graduate Research Assistant in Robotics

Helping Hands Lab at Northeastern University, Boston, Massachusetts, 2019 - 2021

Lead Graduate Teaching Assistant in Computer Sciences

Northeastern University Khoury College of Computer Sciences, Boston, Massachusetts, 2018 - 2021

Mechatronics Engineer

Perfetch, Malden, Massachusetts, 2015 - 2017

R&D Engineer

Biomille Technologies, Boston, Massachusetts, 2014 - 2015

Undergraduate Research Assistant in Robotics

Tianjin University of Science and Technology, Tianjin, China, 2010 - 2011


Reinforcement-Learning Based Robotic Assembly of Fractured Objects Using Visual and Tactile Information

Xinchao Song*, Nikolas Lamb*, Sean Banerjee, Natasha Kholgade Banerjee. 2023 International Conference on Automation, Robotics and Applications (ICARA). [Paper]

We present a reinforcement learning approach that combines visual and tactile information to automatically assemble repair parts to fractured objects. We propose two novel visual metrics, which we term pixel offset error and assembly error, to provide estimation of assembly state. Our approach does not place constraints on object geometry and estimates the assembly state of the constituent objects in real time. We show tightly assembled fractured and restored pairs in simulation and on real robots.


Internet of Robotic Things: Current Technologies, Applications, Challenges and Future Directions

Davide Villa, Xinchao Song, Matthew Heim, Liangshe Li. arXiv preprint:2101.06256. [Paper]

The concept of the Internet of Things (IoT) is becoming increasingly popular, with the number of connected devices reaching billions. This paper focuses on the fusion of IoT and robotics, called the Internet of Robotic Things (IoRT), and discusses IoRT concepts, architectures, use case examples, key challenges, ethical issues, regulations, and future vision. This paper aims to provide a better understanding of the emerging concept of IoRT, its benefits and limitations, as well as guidelines and directions for future research and studies.


Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability

Hai Nguyen*, Brett Daley*, Xinchao Song, Chistopher Amato, Robert Platt. 2020 Conference on Robot Learning (CoRL). [website]

We propose a method for policy learning under partial observability called the Belief-Grounded Network (BGN) in which an auxiliary belief-reconstruction loss incentivizes a neural network to concisely summarize its input history. Since the resulting policy is a function of the history rather than the belief, it can be executed easily at runtime. We compare BGN against several baselines on classic benchmark tasks as well as three novel robotic touch-sensing tasks. BGN outperforms all other tested methods and its learned policies work well when transferred onto a physical robot.


Certified SOLIDWORKS Professional (CSWP) - Mechanical Design

The CSWP exam is a comprehensive, non-proctored online exam that tests an individual’s ability to design and analyze parametric parts and movable assemblies using a variety of complex features in SOLIDWORKS, including design validation tools. A Certified SOLIDWORKS Professional is an individual that has successfully passed this exam.


FCC Amateur Radio Service License - Technician

The FCC Amateur Radio Service Technician class license is the entry-level license that gives access to all Amateur Radio frequencies above 30 megahertz, allowing these licensees the ability to communicate locally and most often within North America. It also allows for some limited privileges on the HF bands used for international communications.