Pulkit Agrawal

ORCID: 0000-0002-9569-6690
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Domain Adaptation and Few-Shot Learning
  • Robot Manipulation and Learning
  • Reinforcement Learning in Robotics
  • Sepsis Diagnosis and Treatment
  • Acute Kidney Injury Research
  • Water Quality Monitoring Technologies
  • Hemodynamic Monitoring and Therapy
  • Teleoperation and Haptic Systems

Massachusetts Institute of Technology
2025

IIT@MIT
2024

University of California, Berkeley
2023

To act in the world, robots rely on a representation of salient task aspects: for example, to carry coffee mug, robot may consider movement efficiency or mug orientation its behavior. However, if we want and with people, their representations must not be just functional but also reflective what humans care about, i.e. they aligned. We observe that current learning approaches suffer from misalignment, where robot's learned does capture human's representation. suggest because are ultimate...

10.1145/3610977.3634987 article EN cc-by 2024-03-10

ABSTRACT Background Major Adverse Kidney Events within 30 days (MAKE30) is an important patient-centered outcome for assessing the impact of acute kidney injury (AKI). The existing prediction models MAKE30 are static and overlook dynamic changes in clinical status. In this study, we introduce ORAKLE, a novel deep-learning model that utilizes evolving time-series data to predict MAKE30, enabling personalized, approaches AKI management improvement. Methods We conducted retrospective study...

10.1101/2025.01.18.25320769 preprint EN medRxiv (Cold Spring Harbor Laboratory) 2025-01-19

To act in the world, robots rely on a representation of salient task aspects: for example, to carry coffee mug, robot may consider movement efficiency or mug orientation its behavior. However, if we want and with people, their representations must not be just functional but also reflective what humans care about, i.e. they aligned. We observe that current learning approaches suffer from misalignment, where robot's learned does capture human's representation. suggest because are ultimate...

10.48550/arxiv.2302.01928 preprint EN other-oa arXiv (Cornell University) 2023-01-01

We introduce a teleoperation system that integrates 5 DOF actuated neck, designed to replicate natural human head movements and perception. By enabling behaviors like peeking or tilting, the provides operators with more intuitive comprehensive view of environment, improving task performance, reducing cognitive load, facilitating complex whole-body manipulation. demonstrate benefits perception across seven challenging tasks, showing how neck enhances scope efficiency remote operation....

10.48550/arxiv.2411.00704 preprint EN arXiv (Cornell University) 2024-11-01
Coming Soon ...