Claudia D'Arpino
Claudia D'Arpino
I'm a Research Scientist in Robotics-AI at
NVIDIA
, working on post-training steering methods for online controllability of robot policies (diffusion, VLAs), along with VR-based teleoperation systems for data collection and policy evaluation.
Previously, I was a Postdoctoral Scholar at the
Stanford Vision and Learning Lab
, working with Silvio Savarese on deep reinforcement learning for robot social navigation and
iGibson
, a large-scale simulation platform for robot learning. I collaborated with Fei-Fei Li, Karen Liu, and Dorsa Sadigh, and co-instructed CS331B: Interactive Simulation for Robot Learning at Stanford.
I earned my PhD in Computer Science from
MIT
, advised by
Julie Shah
. There, I developed a next-generation teleoperation system based on learning from demonstrations, built MIT's Optimus robot, participated in the
DARPA Robotics Challenge
working with the Atlas robot, and led 100+ live robot demos.
My research has been featured in the NYT, Science Magazine, Wired, MIT News, and CNN, and has received funding from ONR and DARPA.
Google Scholar
@cpdarobotics
GitHub
Updates
Jan 2026:
New ICRA 2026 paper on steering reasoning VLAs by parallel sampling and VLM-based verification.
[ActAlign]
[Libero-10-r]
[HuggingFace]
Dec 2025:
Updated VR + cuRobo MPC teleop codebase.
[GitHub]
June 2025:
Attend our RSS Workshop on Generative Models x HRI!
[Workshop]
ICRA 2025:
Check out our paper on steering diffusion policies
[Arxiv]
Also moderating a panel on the social navigation workshop
[Workshop]
Publications
Verifying alignment between reasoning and actions in vision-language-action models.
Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification.
Yilin Wu, Anqi Li, Tucker Hermans, Fabio Ramos, Andrea Bajcsy,
Claudia Pérez-D'Arpino
ICRA 2026
Steering generative robot policies through human interactions at inference time.
Inference-Time Policy Steering through Human Interactions.
Yanwei Wang, Lirui Wang, Yilun Du, Balakumar Sundaralingam, Xuning Yang, Yu-Wei Chao,
Claudia Pérez-D'Arpino
, Dieter Fox, Julie Shah.
2025 IEEE International Conference on Robotics and Automation (ICRA 2025)
Principles and guidelines for methods and benchmarking of social robot navigation.
Principles and Guidelines for Evaluating Social Robot Navigation Algorithms.
Anthony Francis*,
Claudia Pérez-D'Arpino*
, Chengshu Li, Fei Xia, Alexandre Alahi, Rachid Alami, Aniket Bera, Abhijat Biswas, Joydeep Biswas, Rohan Chandra, Hao-Tien Lewis Chiang, Michael Everett, Sehoon Ha, Justin Hart, Jonathan P. How, Haresh Karnan, Tsang-Wei Edward Lee, Luis J. Manso, Reuth Mirsky, Sören Pirk, Phani Teja Singamaneni, Peter Stone, Ada V. Taylor, Peter Trautman, Nathan Tsoi, Marynel Vázquez, Xuesu Xiao, Peng Xu, Naoki Yokoyama, Alexander Toshev, Roberto Martín-Martín.
ACM Transactions on Human-Robot Interaction (ACM THRI), Vol. 14(2), 2025. *Equal contribution.
Explicit-input assistance for robot teleoperation in cluttered environments.
Fast Explicit-Input Assistance for Teleoperation in Clutter.
Nick Walker, Xuning Yang, Animesh Garg, Maya Cakmak, Dieter Fox,
Claudia Pérez-D'Arpino
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)
Benchmarking teleoperation systems with expert operators (leader/follower teleop, teleautonomy interface, assisted planning, 2D, 3D perception).
Experimental Assessment of Human-Robot Teaming for Multi-Step Remote Manipulation with Expert Operators.
Claudia Pérez-D'Arpino
, Rebecca P. Khurshid, Julie A. Shah.
ACM Transactions on Human-Robot Interaction (ACM THRI), Vol. 13(3), 2024
Learning vision-based human-to-robot handovers from point clouds.
Learning Human-to-Robot Handovers from Point Clouds.
Sammy Christen, Wei Yang,
Claudia Pérez-D'Arpino
, Otmar Hilliges, Dieter Fox, Yu-Wei Chao.
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023)
Retrospective on challenges and progress in embodied AI research.
Retrospectives on the Embodied AI Workshop.
Matt Deitke, Dhruv Batra, Yonatan Bisk, Tommaso Campari, Angel X. Chang, Devendra Singh Chaplot, Changan Chen,
Claudia Pérez-D'Arpino
, Kiana Ehsani, Ali Farhadi, Li Fei-Fei, Anthony Francis, Chuang Gan, Kristen Grauman, David Hall, Winson Han, Unnat Jain, Aniruddha Kembhavi, Jacob Krantz, Stefan Lee, Chengshu Li, Sagnik Majumder, Oleksandr Maksymets, Roberto Martín-Martín, Roozbeh Mottaghi, Sonia Raychaudhuri, Mike Roberts, Silvio Savarese, Manolis Savva, Mohit Shridhar, Niko Sünderhauf, Andrew Szot, Ben Talbot, Joshua B. Tenenbaum, Jesse Thomason, Alexander Toshev, Joanne Truong, Luca Weihs, Jiajun Wu.
arXiv preprint, 2022
Learning+Planning for social navigation in constrained layouts.
Robot Navigation in Constrained Pedestrian Environments using Reinforcement Learning.
Claudia Pérez-D'Arpino
, Can Liu, Patrick Goebel, Roberto Martín-Martín, Silvio Savarese.
2021 IEEE International Conference on Robotics and Automation (ICRA 2021)
iGibson: a simulation environment for interactive tasks in large realistic scenes.
iGibson, a Simulation Environment for Interactive Tasks in Large Realistic Scenes.
Bokui Shen, Fei Xia, Chengshu Li, Roberto Martín-Martín, Linxi Fan, Guanzhi Wang,
Claudia Pérez-D'Arpino
, Shyamal Buch, Sanjana Srivastava, Lyne P. Tchapmi, Micael E. Tchapmi, Kent Vainio, Josiah Wong, Li Fei-Fei, Silvio Savarese.
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)
Learning diverse human-robot collaboration strategies via imitation.
Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration.
Chen Wang,
Claudia Pérez-D'Arpino
, Danfei Xu, Li Fei-Fei, C. Karen Liu, Silvio Savarese.
5th Conference on Robot Learning (CoRL 2021)
PhD Thesis
Hybrid Learning for Multi-Step Manipulation in Collaborative Robotics.
Claudia Pérez-D'Arpino
Doctor of Philosophy, Computer Science. Massachusetts Institute of Technology, 2019
Learn geometric constraints from demonstrations for multistep manipulation tasks in shared autonomy.
C-LEARN: Learning Geometric Constraints from Demonstrations for Multi-Step Manipulation in Shared Autonomy.
Claudia Pérez-D'Arpino
, Julie A. Shah.
2017 IEEE International Conference on Robotics and Automation (ICRA 2017)
Director: User interface for shared autonomy at DRC Finals.
Director: A User Interface Designed for Robot Operation with Shared Autonomy.
Pat Marion, Maurice Fallon, Robin Deits, Andrés Valenzuela,
Claudia Pérez D'Arpino
, Greg Izatt, Lucas Manuelli, Matt Antone, Hongkai Dai, Twan Koolen, John Carter, Scott Kuindersma, Russ Tedrake.
Journal of Field Robotics, vol. 34, no. 2, pp. 262--280, 2017
Optimus as Theatrical Robot in Shared Autonomy
A Theatrical Mobile-Dexterous Robot Directed through Shared Autonomy.
Claudia Pérez-D'Arpino
, Peter Agoos, Andrew Zamore, David Gammons, Evie Kyritsis, Julie Shah.
Proceedings of 2017 Conference on Human-Robot Interaction (HRI2017) Companion, Vienna, Austria, 2017
Prediction of the target of human reaching motion in real time.
Fast Target Prediction of Human Reaching Motion for Cooperative Human-Robot Manipulation Tasks Using Time Series Classification.
Claudia Pérez-D'Arpino
, Julie A. Shah.
2015 IEEE International Conference on Robotics and Automation (ICRA 2015)
MIT Team Approach to the DARPA Robotics Challenge.
An Architecture for Online Affordance-based Perception and Whole-body Planning.
Maurice Fallon, Scott Kuindersma, Sisir Karumanchi, Matthew Antone, Toby Schneider, Hongkai Dai,
Claudia Perez D'Arpino
, Robin Deits, Matt DiCicco, Dehann Fourie, Twan Koolen, Pat Marion, Michael Posa, Andres Valenzuela, Kuan-Ting Yu, Julie Shah, Karl Iagnemma, Russ Tedrake, Seth Teller.
Journal of Field Robotics, vol. 32, no. 2, pp. 229--254, 2015
Human-robot co-navigation using anticipatory indicators.
Human-Robot Co-Navigation Using Anticipatory Indicators of Human Walking Motion.
Vaibhav V. Unhelkar*,
Claudia Pérez-D'Arpino*
, Leia Stirling, Julie A. Shah. *Equal contribution.
2015 IEEE International Conference on Robotics and Automation (ICRA 2015)
Video Abstract of MIT's entry to the DARPA Virtual Challenge (VRC) in June 2013.
A summary of team MIT's approach to the virtual robotics challenge.
R Tedrake, M Fallon, S Karumanchi, S Kuindersma, M Antone, T Schneider, T Howard, M Walter, H Dai, R Deits, M Fleder, D Fourie, R Hammoud, S Hemachandra, P Ilardi,
C Perez-D'Arpino
, S Pillai, A Valenzuela, C Cantu, C Dolan, I Evans, S Jorgensen, J Kristeller, JA Shah, K Iagnemma, S Teller.
Video Abstract. 2014 IEEE International Conference on Robotics and Automation
Overview of the hardware and software of an IMU for UAVs.
Development of a Low Cost Inertial Measurement Unit for UAV Applications with Kalman Filter based Attitude Determination.
Claudia Pérez-D'Arpino
, Damian Vigouroux, Wilfredis Medina-Meléndez, Leonardo Fermín, Rafael. R. Torrealba, Juan C. Grieco, Gerardo Fernández-López.
2011 IEEE International Conference on Technologies for Practical Robot Applications
Bilateral Control for MIMO systems using the States Convergence technique. Applied to a 2-DOF Helicopter.
Generalized Bilateral MIMO Control by States Convergence with time delay and application for the teleoperation of a 2-DOF helicopter.
Claudia Pérez-D'Arpino
, Wilfredis Medina-Meléndez, Leonardo Fermín-León, Juan Manuel Bogado, Rafael R. Torrealba, Gerardo Fernández-López.
2010 IEEE International Conference on Robotics and Automation (ICRA 2010)
Designing, fabricating and testing a passive biomechatronic knee prosthesis.
Through the Development of a Biomechatronic Knee Prosthesis for Transfemoral Amputees: Mechanical Design and Manufacture, Human Gait Characterization, Intelligent Control Strategies and Tests.
Rafael R. Torrealba,
Claudia Pérez-D'Arpino
, José Cappelletto, Leonardo Fermín-León, Gerardo Fernández-López, Juan C. Grieco.
2010 IEEE International Conference on Robotics and Automation (ICRA 2010)
Using the Mahalanobis Distance to achieve luminosity independent color segmentation. Fast implementation in FPGA.
FPGA-Based Artificial Vision System for Robot and Obstacles Detection under Strong Luminosity Variability
Pérez-D'Arpino, Claudia
; Medina-Meléndez, W.; Ralev, D.; Guzmán, J.; Fermín, L.; Grieco, J.; Fernández, G.; Armada, Manuel.
International Conference on Climbing and Walking Robots (CLAWAR), 2009
Take a normalized velocity field for 2-D navigation and use a Fuzzy Inference System (FIS) to get human-inspired speeds for safe navigation around obstacles.
Fuzzy Logic Based Speed Planning for Autonomous Navigation Under Velocity Field Control
Pérez-D'Arpino, Claudia
; Medina, Wilfredis; Guzmán, José; Fermín, L.; Fernández, G.
IEEE International Conference on Mechatronics (ICM), 2009
Generate a velocity field for 2-D navigation. Avoid obstacles the same way fluids find their way around them.
Dynamic Velocity Field Angle Generation for Obstacle Avoidance in Mobile Robots Using Hydrodynamics
Pérez-D'Arpino, Claudia
; Medina, Wilfredis; Fermín, L.; Guzmán, J.; Fernández, G.; Grieco, J.C.
Ibero-American Conference on Artificial Intelligence (IBERAMIA), 2008
DC motor control combining fuzzy and sliding mode algorithms.
Speed Control of a DC Motor by Using Fuzzy Variable Structure Controller
Perez, Claudia
; Strefezza, Miguel.
Chinese Control Conference (CCC), 2008
Talks and Workshops
MIT Embodied Intelligence Seminar
Talk: Interactive Simulation for Robot Learning
February 2021
Invited talk at the
MIT Embodied Intelligence Seminar
presenting research on robot learning in simulation environments, including iGibson and social navigation.
Teaching
CS331B
Interactive Simulation for Robot Learning
Co-Instructor, Stanford University
Spring 2021
A research survey of advanced methods for robot learning in simulation, covering agent-environment interactions, imitation and reinforcement learning, sim2real techniques, and multi-agent/human-robot interaction domains. Project-based seminar leveraging iGibson simulation environment.
Advising
Research Interns at NVIDIA (t ≥ 2021)
Yilin Wu
(CMU):
Do What You Say: Steering VLA Models via Runtime Reasoning-Action Alignment Verification
Felix Wang
(MIT):
Inference-Time Policy Steering through Human Interactions
, ICRA 2025
Nick Walker
(UW):
Fast Explicit-Input Assistance for Teleoperation in Clutter
, IROS 2024
Sammy Christen
(ETH):
Learning Human-to-Robot Handovers from Point Clouds
, CVPR 2023
Postdoc at Stanford (2019 ≤ t ≤ 2021)
Can Liu
Social Robot Navigation
, ICRA 2021
Chen Wang
iGibson
, IROS 2021
Kent Vainio
: VR Teleoperation
UROPs at MIT (2012 ≤ t ≤ 2019)
Evie Kyritsis
Theatrical Robot, HRI 2017
Media Coverage
Featured in leading publications and research outlets
ICRA 2025: Steering Robot Policies
March 2025
MIT NEWS: Robotic helper making mistakes? Just nudge it in the right direction
Bloomberg Originals: The Rise of AI in Factories
Social Navigation Challenge in iGibson
CVPR 2021
Google Research Blog: Presenting the iGibson Challenge on Interactive and Social Navigation
C-LEARN: Teaching Robots to Teach
ICRA 2017
MIT NEWS: Teaching robots to teach other robots
Science: Robots could soon teach each other new tricks
Wired: The Little Robot That Taught the Big Robot
The Verge: Teach a robot simple tasks
Digital Trends: Robots That Can Learn and Pass On Skills
TechCrunch: MIT robot how to teach other robots
Sapiens: The Age of Cultured Machines
MIT2016 Pageant: Robot Performer
May 2016
MIT NEWS: MIT marks 100 years in Cambridge
MIT 2016 Pageant Video
Boston.com: MIT celebrates historic move to Cambridge
Prediction for Collaborative Robotics
2014
NSF: A day in the life of Robotina
JDN: Le robot collaboratif
CS Monitor: Meet Baxter, your new robotic co-worker
Optimus: Mobile Manipulator
2014-2015
Clearpath Robotics: Husky Mobilizes MIT Bomb Disposal Research
Robotiq: Why Did MIT Choose the 3-Finger Gripper?
DARPA Robotics Challenge Finals
June 2015
MIT News: MIT team places sixth at DARPA Robotics Challenge
MIT Tech Review: Why Robots and Humans Struggled
NYTimes: Relax, the Terminator Is Far Away
More at drc.mit.edu/media/
DARPA Robotics Challenge Trials
Dec 2013
Technology Review: Readying Robots for the Real World
MIT EECS Connector: Team MIT takes on the DRC
MIT News: Team MIT @ Virtual DRC (June 2013)
US