Data-Efficient Robot Learning

Active Website dataefficiency

We are developing a theory and framework for data-efficient robot learning that unifies efficient representation learning with provably reliable supervision. Our goal is to enable agents to generalize from limited, imperfect, or synthetic data by grounding both what they learn, through compact, task-aligned representations, and how they learn, through corrective labels that are mathematically consistent with the underlying dynamics. This perspective treats learning as an interplay between structure discovery and label synthesis, yielding algorithms that can extrapolate safely beyond expert demonstrations. Ultimately, we aim to build robotic systems that learn robustly and efficiently from sparse, weak, or self-generated experience.

Publications (3)
Y. Zhang, S. Mittal, Z. Zhang, L. Ke, S. Srinivasa, and A. Gupta — Conference on Robot Learning, 2025
A. Deshpande, K. Liyiming, Q. Pfeifer, A. Gupta, and S. Srinivasa — IEEE/RSJ International Conference on Intelligent Robots and Systems, 2024
L. Ke*, Y. Zhang*, A. Deshpande, A. Gupta, and S. Srinivasa — International Conference on Learning Representations, 2024

Robot-Assisted Feeding

Active Website robotfeeding

Our work in robot-assisted feeding focuses on enabling autonomous, safe, and comfortable bite acquisition and delivery for individuals with motor impairments. Our system ADA (Assistive Dexterous Arm) integrates compliant control, multimodal perception, and learned food interaction policies to handle the diversity of everyday meals. We study the fundamental problems of manipulation under uncertainty while advancing assistive robotics for real-world impact.

Publications (14)
A. Nanavati, E. K. Gordon, T. A. Kessler Faulkner, Y. Song, J. Ko, T. Schrenk, V. Nguyen, B. H. Zhu, H. Bolotski, A. Kashyap, S. Kutty, R. Karim, L. Rainbolt, R. Scalise, H. Song, R. Qu, M. Cakmak, and S. S. Srinivasa — ACM/IEEE International Conference on Human-Robot Interaction, 2025
Website, Best Systems Paper Award Finalist
E. Gordon*, R. Jenamani*, A. Nanavati*, Z. Liu, H. Bolotski, R. Karim, D. Stabile, A. Kashyap, B. H. Zhu, X. Dai, T. Schrenk, J. Ko, T. Faulkner, T. Bhattacharjee, and S. Srinivasa — ACM/IEEE International Conference on Human-Robot Interaction, 2024
Best Demo Award Winner
E. Gordon*, A. Nanavati*, R. Challa, B. H. Zhu, T. A. Kessler Faulkner, and S. S. Srinivasa — Conference on Robot Learning, 2023
A. Nanavati*, P. Alves-Oliveira*, T. Schrenk, E. Gordon, M. Cakmak, and S. S. Srinivasa — ACM/IEEE International Conference on Human-Robot Interaction, 2023
Best Design Paper Award Winner
A. Nanavati, P. Alves-Oliveira, T. Schrenk, E. Gordon, M. Cakmak, and S. Srinivasa — ACM/IEEE International Conference on Human-Robot Interaction, 2023
Video. PDF here
E. Gordon, S. Roychowdhury, T. Bhattacharjee, K. Jamieson, and S. Srinivasa — IEEE International Conference on Robotics and Automation, 2021
E. Gordon, X. Meng, T. Bhattacharjee, M. Barnes, and S. Srinivasa — IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020
T. Bhattacharjee, E. Gordon, R. Scalise, M. Cabrera, A. Caspi, M. Cakmak, and S. Srinivasa — ACM/IEEE International Conference on Human-Robot Interaction, 2020
T. Bhattacharjee, G. Lee, H. Song, and S. Srinivasa — IEEE Robotics and Automation Letters, 2019
R. Feng, Y. Kim, G. Lee, E. Gordon, M. Schmittle, S. Kumar, T. Bhattacharjee, and S. Srinivasa — International Symposium on Robotics Research, 2019
T. Bhattacharjee, M. Cabrera, A. Caspi, M. Cakmak, and S. Srinivasa — International ACM SIGACCESS Conference on Computers and Accessibility, 2019
D. Gallenberger, T. Bhattacharjee, Y. Kim, and S. Srinivasa — ACM/IEEE International Conference on Human-Robot Interaction, 2019
Best Paper Award Winner for Technical Advances in HRI
H. Song, T. Bhattacharjee, and S. Srinivasa — IEEE International Conference on Robotics and Automation, 2019
T. Bhattacharjee, D. Gallenberger, D. Dubois, L. L'Écuyer-Lapiere, Y. Kim, A. Mandalika, R. Scalise, R. Qu, H. Song, E. Gordon, and S. Srinivasa — Conference on Neural Information Processing Systems, 2018
Video. Best Demo Award Winner

Learning from Interventions

Active interventions

We study how human interventions, like resets, corrections, and implicit signals, among others, can serve as a principled source of structure for safe and efficient robot learning. By interpreting interventions as defining support sets of safe and high-value states, we design algorithms that provably accelerate convergence while bounding suboptimality. This framework extends to learning intervention models directly from observation, allowing agents to autonomously infer when to reset, request help, or modify their behavior. Our broader goal is to establish a unified foundation for learning under human guidance, where safety, efficiency, and adaptability emerge naturally from the dynamics of interaction.

Publications (3)
J. Spencer, S. Choudhury, M. Barnes, M. Schmittle, M. Chiang, P. Ramadge, and S. Srinivasa — Autonomous Robots, 46, 2022
J. Spencer, S. Choudhury, M. Barnes, M. Schmittle, M. Chiang, P. Ramadge, and S. Srinivasa — Robotics: Science and Systems, 2020
S. Ainsworth, M. Barnes, and S. Srinivasa — Advances in Neural Information Processing Systems, 2019