Building the Next Generation of Intelligent Machines


What we do

We perform fundamental and applied research in robotics, machine learning, and artificial intelligence to design and develop intelligent systems. Our work touches on various problems, including dextrous manipulation and control, mobile navigation, human-robot collaboration, autonomous driving, and healthcare. Read more

Soft-Rigid Body Manipulation

Soft-Rigid Body Manipulation

Structural Concept Learning

Human-aware Grasping

Multi-agent Planning & Control

Active Sensing

Constrained Manipulation

Visual Navigation

Neural Motion Planning

Neural Rearrangment Planning

Deep Reinforcement Learning

Latest News


Nine papers accepted at ICRA'24!


CoRAL Lab hosted a visit for undergraduate students! [link]


Three papers were accepted: [1] [2] in RA-L and [3] at CoRL'23!!


Three papers accepted at IROS'23!


Paper on Physics-Informed Motion Planning accepted in RSS'23!


Ruiqi Ni received the Best Paper at ICLR Workshop on Neural Fields across Fields!


Paper on Active Neural Sensing accepted in TRO'23!


Paper on Physics-Informed Robot Motion Planning accepted for SPOTLIGHT at ICLR'23!


Paper on Grasp Generation for Human-Robot Collaboration accepted at ICRA'23!


Paper on Neural Lyapunov-based Safe Control accepted at IROS'22!

Research Highlights

Progressive Learning for Physics-informed Neural Motion Planning

Abstract— A new semi-linear Eikonal PDE formulation and progressive speed scheduling strategy to solve high-DOF motion planning problems.

NTFields: Neural Time Fields for Physics-Informed Robot Motion Planning

Abstract— Unlike most neural motion planners, NTFields require no expert trajectories for training and instead directly learn to solve Eikonal PDE.

CoGrasp: 6-DoF Grasp Generation for Human-Robot Collaboration

Abstract— Robot grasp generation contextualizes human social preferences of interacting with daily-life objects for human-robot collaboration.

Robot Active Neural Sensing and Planning

Abstract— A framework that actively collects the RGBD observations of an unknown confined environment with an in-hand camera and transforms them into interpretable scene representation.

NeRP: Neural Rearrangement Planning for Unknown Objects

Abstract— NeRP is a learning-based approach for multi-step neural object rearrangement planning with never-before-seen objects in the real world.

Constrained Motion Planning Networks X

Abstract— CoMPNetX is a neural planning approach with a fast projection operator for solving constrained manipulation tasks.

All Publications >

Research Videos

Neural Rearragment Planning - RSS 2021
Motion Planning Networks
Dynamically Constrained Motion

Follow our YouTube Channel >

"Meet our research team"

See People >