Our mission is to enable robots to improve the quality of life of people with mobility limitations by assisting them with activities of daily living (ADLs). In our lab, we seek solutions to the fundamental research question on how to leverage robot-world physical and social interactions in unstructured human environments to perform relevant ADLs.
EmPRISE lab is a part of the Department of Computer Science in the Computing and Information Science at Cornell University. We are a full-stack robotics lab leveraging tools from sensing, perception, planning, learning, and control to provide intelligent autonomy. Our projects delve deep into human-robot interaction, haptic perception, robot manipulation, and tactile sensing. We are not only passionate about developing algorithms that solve fundamental problems in these domains but also strongly believe in developing real robotic systems, deploying them in the real world, and evaluating them with real users.
Recent News
June 2025
"FEAST" won the 🏆 Outstanding Paper Award at RSS'25! Congrats to Rajat and his team for their amazing work.
June 2025
Congrats to Rajat and his team for being nominated for both the 🏆 Outstanding Paper Award and the 🏆 Outstanding Systems Paper Award at RSS'25 for their paper "FEAST: A Flexible Mealtime Assistance System Towards In-the-Wild Personalization".
June 2025
Our paper, "OpenRoboCare: A Multi-Modal Multi-Task Expert Demonstration Dataset for Robot Caregiving" has been accepted to IROS'25!
April 2025
Congrats to Rohan and his team for being nominated for the 🏆 Best Paper Award at ICRA'25 for their paper "To Ask or Not To Ask: Human-in-the-loop Contextual Bandits with Applications in Robot-Assisted Feeding".
April 2025
Congrats to Rajat and team for their paper "FEAST: A Flexible Mealtime-Assistance System Towards In-the-Wild Personalization" accepted at RSS'25!
Feburary 2025
Phase 2 of the PhyRC challenge is now live! Check out the website for more details.
January 2025
Congrats Rohan on getting his paper accepted to ICRA'25! The paper presents a human-in-the-loop contextual bandit approach for robot-assisted feeding.