Kaiyuan (Eric) Chen

kaiych.com · kych@berkeley.edu · Google Scholar · github.com/KeplerC

Research Interests

Robot Learning, Agentic Robotics and Simulation, Robot Data and Network Systems, Distributed Robot Systems, Vision-Language Models

Education

Professional Experience

Honors & Awards

• ICRA 2025 Best Robot Learning Paper Award as first author (1 of 4,250)
• IROS 2024 Best Paper Finalist & Best Student Paper Finalist as first author (4 of 3,344)
• CoRL 2026 Spotlight as first author (72 of 2,094 submissions, top 3.4%)
• NeurIPS 2025 Datasets & Benchmarks Spotlight as first author (56 of 1,995)
• Winner, Undergraduate Student Research Award at IEEE ICRA Art in Robotics 2025
• Winner, Google–BAIR Commons Research Proposals 2023, 2024, 2025 (top ~10%, three consecutive years)
• CVPR 2026 Outstanding Reviewer
• Summa cum laude (highest Latin honor, top 1%), UCLA Computer Science · Dean's List

Preprints & Under Review

• Kaiyuan Chen*, Shuangyu Xie*, Uksang Yoo, Xinyue Zhu, Cael Magner, Alvin Zhu, Daehwa Kim, Eric Heiden, Erwin Coumans, Miles Macklin, Spencer Huang, Ken Goldberg. "RoboSimStudio: An Interactive Toolkit for Human and Agent Rapid Real2Sim of Robot Manipulation Tasks." Preprint, 2026. arXiv:2610.18835 · robosimstudio.github.io
• Kaiyuan Chen, Xinyue Zhu, Shuangyu Xie, Uksang Yoo, Thi Thu Phuong Luong, Marcus Gualtieri, Christian Juette, Liu Ren, Spencer Huang, Ken Goldberg. "Comparing Models, Skills, Feedback and Curriculum Design for Agentic Robotics." Under review at the International Conference on Learning Representations (ICLR), 2027.
• Shuangyu Xie, Kaiyuan Chen, Muhammad Zubair Irshad, Richard Cheng, Sergey Zakharov, Ken Goldberg. "KiRoSe: Using Kinematic Data for Efficient Segmentation of Robot Demonstrations." Under review at the International Conference on Learning Representations (ICLR), 2027.
• Shuangyu Xie, Kaiyuan Chen, Uksang Yoo, Xinyue Zhu, Meadow Shen, Jaimyn Drake, Eugen Solowjow, Lionel Gulich, Alexander Millane, Rafael Cathomen, Tuur Stuyck, Sangeeta Subramanian, Yichao Pan, Bruce McGowan, Michael Benedict, Linxi Fan, Yuke Zhu, Spencer Huang, Ken Goldberg. "VABAR: A Variational Automation Benchmark for Agentic Robotics." Under review at IEEE Int. Conf. on Robotics and Automation (ICRA), 2027.
• Daehwa Kim, Xinyue Zhu, Shuangyu Xie, Uksang Yoo, Justin Kerr, Kaiyuan Chen, Ken Goldberg. "Acoustic-Video Perception for Robot Manipulation with Occluded Contact Dynamics." Under review at IEEE Int. Conf. on Robotics and Automation (ICRA), 2027.
• Andrew Lee, Marcus Gualtieri, Thi Thu Phuong Luong, Williard Joshua Jose, Ghayoor Shah, Kaiyuan Chen, Ken Goldberg, Christian Juette, Liu Ren. "Benchmarking Runtime Memory in Agentic Robotics." Under review at IEEE Int. Conf. on Robotics and Automation (ICRA), 2027.
• Shuo Xing, Zezhou Sun, Shuangyu Xie, Kaiyuan Chen, Yanjia Huang, Yuping Wang, Jiachen Li, Dezhen Song, Zhengzhong Tu. "Can Large Vision Language Models Read Maps Like a Human?" Preprint, 2025. arXiv:2503.14607

Peer-Reviewed Publications

• Kaiyuan Chen*, Shuangyu Xie*, Letian Fu, Justin Yu, William Pacini, Sandeep Bajamahal, Hudson Kim, Jaimyn Drake, Daehwa Kim, Haoru Xue, Jonathan Francis, Christian Juette, Peter Schaldenbrand, Muhammet Yunus Seker, Ruwan Wickramarachchi, Uksang Yoo, Guanzhi Wang, Adithyavairavan Murali, Balakumar Sundaralingam, S. Shankar Sastry, Yuke Zhu, Linxi "Jim" Fan, Spencer Huang, Ken Goldberg. "GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness for Variational Automation Tasks." Conference on Robot Learning (CoRL), 2026. Spotlight (72 of 2,094 submissions, top 3.4%) arXiv:2607.05369
• Shuangyu Xie, Di Wang, Joe Johnson, Chengsong Hu, Kaiyuan Chen, Muthukumar Bagavathiannan, Ken Goldberg, Dezhen Song. "Energy-Efficient Precision Weed Elimination Using a Quadruped Robot." The International Journal of Robotics Research (IJRR), 2026. doi:10.1177/02783649261487695
• Shuangyu Xie, Kaiyuan Chen, Ziyang Chen, Simeon Adebola, Yixuan Huang, Zehan Ma, Tianshuang Qiu, Wentao Yuan, Dhruv Shah, Pannag R. Sanketi, Ken Goldberg. "RoboVista: Evaluating Vision Language Models for Diverse Robot Applications." Robotics: Science and Systems (RSS), 2026. arXiv:2607.04610
• Kaiyuan Chen*, Shuangyu Xie*, Kush Hari, Andrew Goldberg, Kavish Kondap, Ken Goldberg. "RoboSQ: Semantic Queries for Task-Aligned Robot Training Data." IEEE Int. Conf. on Robotics and Automation (ICRA), 2026.
• Kaiyuan Chen*, Shuangyu Xie*, Andrew Goldberg, Ken Goldberg. "Learning Multi-Task Robot Trajectory Segmentation from Visual and Kinematic Streams." IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Findings, 2026.
• Shubham Mishra, Alexander Thomas, Nurzhan Abdrassilov, Kaiyuan Chen, Natacha Crooks, John Kubiatowicz. "HarborMaster: Rollback Detection for Trusted Distributed Computing." Proceedings of the VLDB Endowment (PVLDB) 19(9), 2026. doi:10.14778/3819518.3819539
• Kaiyuan Chen*, Shuangyu Xie*, Zehan Ma, Pannag Sanketi, Ken Goldberg. "Robo2VLM: Improving Visual Question Answering using Large-Scale Robot Manipulation Data." NeurIPS Datasets & Benchmarks Track, 2025. Spotlight (56 of 1,995)
• Kaiyuan Chen, Letian Fu, David Huang, Josh Zhang, Lawrence Yunliang Chen, Huang Huang, Kush Hari, Ashwin Balakrishna, Pannag R. Sanketi, John Kubiatowicz, Ken Goldberg. "Robo-DM: Efficient Robot Big Data Management." IEEE Int. Conf. on Robotics and Automation (ICRA), 2025. Best Robot Learning Paper Award (1 of 4,250)
• Kaiyuan Chen, Nan Tian, Christian Juette, Tianshuang Qiu, Liu Ren, John Kubiatowicz, Ken Goldberg. "FogROS2-PLR: Probabilistic Latency-Reliability for Cloud Robotics." IEEE Int. Conf. on Robotics and Automation (ICRA), 2025.
• Andrew Goldberg, Kavish Kondap, Tianshuang Qiu, Zehan Ma, Letian Fu, Justin Kerr, Huang Huang, Kaiyuan Chen, Kuan Fang, Ken Goldberg. "Blox-Net: Generative Design-for-Robot-Assembly Using VLM Supervision, Physics Simulation, and a Robot with Reset." IEEE Int. Conf. on Robotics and Automation (ICRA), 2025.
• Kaiyuan Chen, Kush Hari, Trinity Chung, Michael Wang, Nan Tian, Jeffrey Ichnowski, Christian Juette, Ren Liu, John Kubiatowicz, Ion Stoica, Ken Goldberg. "FogROS2-FT: Fault Tolerant Cloud Robotics." IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2024. Best Paper Finalist & Best Student Paper Finalist (4 of 3,344)
• Kaiyuan Chen, Kush Hari, Rohil Khare, Charlotte Le, Trinity Chung, Jaimyn Drake, Jeffrey Ichnowski, John Kubiatowicz, Ken Goldberg. "FogROS2-Config: A Toolkit for Choosing Server Configurations for Cloud Robotics." IEEE Int. Conf. on Robotics and Automation (ICRA), 2024.
• Kaiyuan Chen, Michael Wang, Marcus Gualtieri, Nan Tian, Christian Juette, Liu Ren, Jeffrey Ichnowski, John Kubiatowicz, Ken Goldberg. "FogROS2-LS: A Location-Independent Fog Robotics Framework for Latency-Sensitive ROS 2 Applications." IEEE Int. Conf. on Robotics and Automation (ICRA), 2024.
• Adam Rashid*, Chung Min Kim*, Justin Kerr*, Letian Fu, Kush Hari, Ayah Ahmad, Kaiyuan Chen, Huang Huang, Marcus Gualtieri, Michael Wang, Christian Juette, Nan Tian, Liu Ren, Ken Goldberg. "Lifelong LERF: Local 3D Semantic Inventory Monitoring Using FogROS2." IEEE Int. Conf. on Robotics and Automation (ICRA), 2024.
• Kaiyuan Chen, Ryan Hoque, Karthik Dharmarajan, Edith LLontop, Simeon Adebola, Jeffrey Ichnowski, John Kubiatowicz, Ken Goldberg. "FogROS2-SGC: A ROS 2 Cloud Robotics Platform for Secure Global Connectivity." IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2023.
• Jeffrey Ichnowski*, Kaiyuan Chen*, Karthik Dharmarajan, Simeon Adebola, Michael Danielczuk, Víctor Mayoral-Vilches, Nikhil Jha, Hugo Zhan, Edith LLontop, Derek Xu, John Kubiatowicz, Ion Stoica, Joseph Gonzalez, Ken Goldberg. "FogROS 2: An Adaptive and Extensible Platform for Cloud and Fog Robotics Using ROS 2." IEEE Int. Conf. on Robotics and Automation (ICRA), 2023.
• Kaiyuan Chen, Yafei Liang, Nikhil Jha, Jeffrey Ichnowski, Michael Danielczuk, Joseph Gonzalez, John Kubiatowicz, Ken Goldberg. "FogROS: An Adaptive Framework for Automating Fog Robotics Deployment." IEEE Int. Conf. on Automation Science and Engineering (CASE), 2021.
• Yunqi Guo, Zhaowei Tan, Kaiyuan Chen, Songwu Lu, Ying-Nian Wu. "A Model Obfuscation Approach to IoT Security." IEEE Conf. on Communications and Network Security (CNS), 2021.
• Kaiyuan Chen, Jinghao Zhao. "Skip the Question You Don't Know: An Embedding Space Approach." Int. Joint Conf. on Neural Networks (IJCNN), 2019.
• Kaiyuan Chen, Jingyue Shen, Fabien Scalzo. "Skull Stripping Using Confidence Segmentation Convolution Neural Network." Int. Symposium on Visual Computing (ISVC), 2019.
• Wenchao Wu, Yixian Zheng, Kaiyuan Chen, Xiangyu Wang, Nan Cao. "A Visual Analytics Approach for Equipment Condition Monitoring in Smart Factories of Process Industry." IEEE Pacific Visualization Symposium (PacificVis), 2018.

Peer-Reviewed Workshop Papers

• Kaiyuan Chen*, Shuangyu Xie*, Zehan Ma, Pannag Sanketi, Ken Goldberg. "Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets." RSS Workshop on Learned Robot Representations (RoboReps), 2025.
• Kavish Kondap, Andy Bass, Elle O. Hill, Paloma Raffle, Andrew Goldberg, Tianshuang Qiu, Zehan Ma, Letian Fu, Justin Kerr, Huang Huang, Kaiyuan Chen, Kuan Fang, Ken Goldberg. "Generative AI and Minimalist Sculpture." ICRA Art in Robotics Special Session, 2025. Winner, Undergraduate Student Research Award
• Kaiyuan Chen, Letian Fu, Siyuan Fu, Lawrence Yunliang Chen, Huang Huang, Kush Hari, Ashwin Balakrishna, Pannag R. Sanketi, John Kubiatowicz, Ken Goldberg. "Robo-DM: Efficient Robot Big Data Management." CoRL Open X-Embodiment Workshop, 2024.
• Andrew Goldberg, Kavish Kondap, Tianshuang Qiu, Zehan Ma, Letian Fu, Justin Kerr, Huang Huang, Kaiyuan Chen, Kuan Fang, Ken Goldberg. "Blox-Net: Generative Design-for-Robot-Assembly Using VLM Supervision, Physics Simulation, and a Robot with Reset." CoRL Workshop on Learning Robotic Assembly of Industrial and Everyday Objects, 2024.
• Kaiyuan Chen, Kush Hari, Lawrence Yunliang Chen, Ken Goldberg. "RoboDM: Cloud-Based Large-Scale Data Collection." IROS Workshop on Collecting, Managing and Utilizing Data Through Embodied Robots, 2024.
• Kaiyuan Chen. "Fog-RT-X: Cloud-Based Large-Scale Collection and Management Framework." ICRA Open X-Embodiment Workshop, 2024.
• Alex Thomas, Shubham Mishra, Kaiyuan Chen, John Kubiatowicz. "Paranoid Stateful Lambdas." SOSP, 2023.
• Jinghao Zhao, Kaiyuan Chen, Zengwen Yuan, Songwu Lu. "Intelligent Wi-Fi Multicast for NDN AR." ICN WEN Workshop, 2019.
• Kaiyuan Chen, Rong Huang, Diyi Liu, Catherine Wahlenmayer, Jiewen Wang, Deanna Needell. "Classification of Large-Scale Lyme Disease Data." Joint Mathematics Meeting (JMM), 2019.

Research Experience

On agentic robotics: self-learning policies and Real2Sim (sponsor: NVIDIA)

• Co-led GaP, a multi-agent self-learning harness in which LLM agents author, verify, and self-improve executable behavior graphs as robot policies, reaching 0.93–0.99 success under pose variation across 8 variational automation tasks on UR5e and Franka robots (CoRL '26 Spotlight)
• Built RoboSimStudio, an interactive toolkit on NVIDIA Newton for human- and coding-agent-driven Real2Sim of manipulation tasks from smartphone video, with multi-physics coupling and agentic Real2Sim2Real (arXiv '26)

On the infrastructure for large robot data (sponsor: Google DeepMind)

• Spearheaded Robo-DM, a scalable data-management system that compresses, retrieves, and queries multimodal robot demonstrations (ICRA '25 Best Robot Learning Paper, ICRA '26)
• Built a large-scale data-mining pipeline generating 670k visual-question-answering pairs from robot demonstrations to improve the spatial capabilities of vision-language models (NeurIPS '25 D&B Spotlight)
• Built RoboVista, an expert-annotated Robot Question Answering benchmark spanning 6 robot application domains and 39 tasks for evaluating vision-language models (RSS '26)
• Developed RoboSegNet, multi-task robot trajectory segmentation from visual and kinematic streams for automatic labeling of large robot datasets (CVPR '26 Findings)

On the infrastructure for cloud robotics (sponsor: NSF Award #1838833, ECDI: Secure Fog Robotics Using the Global Data Plane, ~$2M)

• Led the development of FogROS2, an open-source cloud-robotics platform now integrated into the official ROS 2 release (CASE '21, ICRA '23)
• Extended FogROS2 with a multi-cloud brokerage system for cost efficiency and fault tolerance (ICRA '24, IROS '24 Best Paper Finalist)
• Integrated 12+ real-world cloud-offloading applications for resource-constrained mobile robots (ICRA '24)

On the infrastructure for latency-sensitive networked robots (sponsor: Bosch Research, ~$1.5M)

• Designed the Secure Global Connectivity (SGC) routing protocol for cross-network robot communication (IROS '23)
• Replicated compute and network resources to mitigate long-tail latency for latency-sensitive robots and autonomous vehicles (ICRA '24, ICRA '25)

Academic Service

• Session Chair — Multi-Robot Systems Session, ICRA 2025
• Journal reviewer — IEEE Transactions on Robotics (T-RO) · IEEE Robotics and Automation Letters (RA-L) · IEEE Transactions on Robot Learning (T-RL) · IEEE Robotics & Automation Magazine (RAM) · IEEE Journal on Selected Areas in Communications · IEEE Internet of Things Journal
• Conference reviewer — ICRA 2023–2027 · IROS 2022, 2024–2026 · CASE 2024, 2025 · CoRL 2026 · RSS 2026 · NeurIPS 2026 · CVPR 2026 (Outstanding Reviewer) · ECCV 2026 · ICCV 2025

Teaching

• Lead organizer — ICRA 2024 tutorial "Cloud and Fog Robotics: A Hands-On Tutorial with ROS 2 and FogROS2"
• Graduate Student Instructor — IEOR 115: Industrial and Commercial Data Systems (Fall 2024)
• Mentor — CS 262: Advanced Operating Systems (Fall 2020, Fall 2025)
• Master's capstone advisor — CMU Master of Computational Data Science (Fall 2023, co-advised with Prof. Jeffrey Ichnowski) · Berkeley Master of Engineering (Spring 2022)

Mentoring

Students who co-authored two or more conference papers with me:

• Kavish Kondap — undergraduate, UC Berkeley (2023–) · Best Undergraduate Student Research Award, ICRA 2025 Art in Robotics
• Andrew Goldberg — undergraduate, UC Berkeley (2023–) · Best Undergraduate Student Research Award, ICRA 2025 Art in Robotics
• Kush Hari — Ph.D. student, UC Berkeley (2023–2025)
• Tianshuang Qiu — Robotics Engineer, General Robotics (2024–2025)
• Zehan Ma — Robotics Engineer, Amazon (2024–2025)
• Simeon Adebola — Ph.D. student, UC Berkeley (2022–2023)
• Trinity Chung — graduate student, CMU, with Aran Nayebi (2021–2023)
• Rohil Khare — co-founder, Y Combinator-backed V1 (2022–2024)
• Karthik Dharmarajan — graduate student, Stanford, with Fei-Fei Li (2021–2023)
• Edith LLontop — Robotics Solutions Architect, NVIDIA (2021–2022)
• Nikhil Jha — Member of Technical Staff, Cognition (2021–2022)
• Yafei (Debbie) Liang — Ph.D. student, UC Berkeley (2020–2021)

Invited Talks & Interviews

• "Towards Scalable Data Infrastructure for Humanoid Intelligence" — Berkeley Humanoid Intelligence Center, Sep 2025
• Interviewee, "Mastering Research — Part 1/3: Choose Smart, Read Smarter!" — IEEE Robotics & Automation Magazine, Sep 2025
• "Augmenting Open X-Embodiment Datasets" — Google DeepMind–BAIR Commons, Jun 2025
• "FogROS: A Cloud Robotics System" — General Robotics, May 2025
• "Cloud Robotics for Automation and Driving" — Bosch Research, Feb 2025
• "Cloud Robotics: Past, Present and Future" — Berkeley Sky Seminar, Jun 2024
• "FogROS2-SGC: Secure Global Connectivity" — Berkeley Sky Retreat, May 2024
• "Fog-RT-X: Cloud-Based Large-Scale Collection and Management Framework" — Google DeepMind, Jan 2024
• "FogROS2: A Cloud Robotics Framework" — Autodesk, Aug 2023
• "Cloud Robotics and FogROS2" — ROS-by-the-Bay, Open Robotics, Aug 2023