Kaiyuan Chen
Kaiyuan Eric Chen
I am a PhD student in the Department of Computer Sciences at UC Berkeley.
My adivsor is Prof. John Kubiatowicz. I work closely with Prof. Ken Goldberg and Prof. Jeffrey Ichnowski on cloud and fog robotics. Jeff and I have been leading FogROS2, state-of-the-art open source cloud robotics framework that offloads unmodified ROS2 applications to the cloud. I received my B.S. in Computer Science from UCLA in 2020, where I was advised by Prof. Songwu Lu on Wireless Networking.
My general research interest is Systems in Robotics, which include topics in Cloud and Fog Robotics, Computer Networks, and System Security.
GitHub: KeplerC. Google Scholar: Kaiyuan Chen. CV: PDF.
Email: kych [at] berkeley [dot] edu
Research
-
Secure and Low Latency Fog Robotics
Ensuring reliable latency for Cloud or Fog robotics applications is challenging in the presence of network congestion and failures. The ultimate goal of this project is to provide a real-time, reliable network connections for robots that can be deployed in dynamic and real-world scenarios. Our work surrounds FogROS2-SGC, a peer-to-peer communication framework that securely connects heterogenous robots without any hassle on network setup.
In follow-up work, we extend FogROS2-SGC and study its capability to control network routing to support latency sensitive applications, such as object tracking and collision avoidance with FogROS2-LS. We are looking for a unified approach that provides the time guarantee without any modifications to the robotics applications.
Figure: FogROS2-SGC facilitates distributed fleet learning with 4 robot arms at different geographic locations
Figure: FogROS2-LS enables resilient object following in the presence of network failures
-
Usable and Cost-Effective Cloud Robotics
Mobility, power, and price points often dictate that robots do not have sufficient computing power on board to run contemporary robot algorithms at desired rates. Cloud computing providers such as AWS, GCP, and Azure offer immense computing power and increasingly low latency on demand, but tapping into that power from a robot is non-trivial. We present FogROS2, An Adaptive and Extensible Platform for Cloud and Fog Robotics Using ROS 2. FogROS2 is officially released by ROS2 Humble.
Selected Publications
- FogROS2-SGC: A ROS2 Cloud Robotics Platform for Secure Global Connectivity (IROS 2023)
Kaiyuan Chen, Ryan Hoque, Karthik Dharmarajan, Edith LLontop, Simeon Adebola, Jeffrey Ichnowski, John Kubiatowicz, Ken Goldberg
[Paper] [code] [Video]
- FogROS2: An Adaptive Platform for Cloud and Fog Robotics Using ROS 2 (ICRA 2023)
Jeffrey Ichnowski*, Kaiyuan Chen*, Karthik Dharmarajan, Simeon Adebola, Michael Danielczuk, Victor Mayoral-Vilches, Nikhil Jha, Hugo Zhan, Edith LLontop, Derek Xu, Camilo Buscaron, John Kubiatowicz, Ion Stoica, Joseph Gonzalez, Ken Goldberg
[Paper] [code] [Video]
- FogROS: An Adaptive Framework for Automating Fog Robotics Deployment (CASE 2021)
Kaiyuan Chen, Yafei Liang, Nikhil Jha, Jeffrey Ichnowski, Michael Danielczuk, Joseph Gonzalez, John Kubiatowicz, Ken Goldberg
[Paper] [code] [Video]
- A model obfuscation approach to IoT security (CNS 2021)
Yunqi Guo, Zhaowei Tan, Kaiyuan Chen, Songwu Lu, Ying Nian Wu
[Paper]
- A visual analytics approach for equipment condition monitoring in smart factories of process industry (PacificVis 2018)
Wenchao Wu, Yixian Zheng, Kaiyuan Chen, Xiangyu Wang, Nan Cao
[Paper]