Understanding and manipulating articulated objects, such as doors and
dr...
Robot-assisted dressing could benefit the lives of many people such as o...
Manipulating objects without grasping them is an essential component of ...
Many fabric handling and 2D deformable material tasks in homes and indus...
Predicting how the world can evolve in the future is crucial for motion
...
To navigate in an environment safely and autonomously, robots must accur...
State estimation is one of the greatest challenges for cloth manipulatio...
Orientation estimation is the core to a variety of vision and robotics t...
How do we imbue robots with the ability to efficiently manipulate unseen...
Point clouds are a widely available and canonical data modality which co...
We formulate grasp learning as a neural field and present Neural Grasp
D...
A simple gripper can solve more complex manipulation tasks if it can uti...
Thin plastic bags are ubiquitous in retail stores, healthcare, food hand...
Effective planning of long-horizon deformable object manipulation requir...
Motion planning for safe autonomous driving requires learning how the
en...
We study the problem of learning graph dynamics of deformable objects wh...
Physical interaction with textiles, such as assistive dressing, relies o...
Robotic manipulation of highly deformable cloth presents a promising
opp...
Robotic manipulation of cloth has applications ranging from fabrics
manu...
Deformable object manipulation has many applications such as cooking and...
Self-occlusion is challenging for cloth manipulation, as it makes it
dif...
We explore a novel method to perceive and manipulate 3D articulated obje...
We consider the problem of sequential robotic manipulation of deformable...
Liquid state estimation is important for robotics tasks such as pouring;...
3D object detection plays an important role in autonomous driving and ot...
Real-time object pose estimation is necessary for many robot manipulatio...
When navigating in urban environments, many of the objects that need to ...
We address the problem of goal-directed cloth manipulation, a challengin...
To safely navigate unknown environments, robots must accurately perceive...
Robotic manipulation of cloth remains challenging for robotics due to th...
Pose estimation is a basic module in many robot manipulation pipelines.
...
Deploying Reinforcement Learning (RL) agents in the real-world require t...
Visual data in autonomous driving perception, such as camera image and L...
Manipulating deformable objects has long been a challenge in robotics du...
The goal of offline reinforcement learning is to learn a policy from a f...
Current image-based reinforcement learning (RL) algorithms typically ope...
Current state-of-the-art trackers often fail due to distractorsand large...
We propose Learning Off-Policy with Online Planning (LOOP), combining th...
3D object trackers usually require training on large amounts of annotate...
3D multi-object tracking (MOT) is essential to applications such as
auto...
Cloth detection and manipulation is a common task in domestic and indust...
Most real-world 3D sensors such as LiDARs perform fixed scans of the ent...
For robots to operate robustly in the real world, they should be aware o...
State-of-the-art object grasping methods rely on depth sensing to plan r...
Deep learning object detectors often return false positives with very hi...
Recent advances in 3D sensing have created unique challenges for compute...
We focus on the problem of class-agnostic instance segmentation of LiDAR...
When interacting with highly dynamic environments, scene flow allows
aut...
Acquiring accurate three-dimensional depth information conventionally
re...
We propose a point cloud annotation framework that employs human-in-loop...