|
2004 - 2010 | 2010 - 2013 | June-Aug 2015 | June-Aug 2016 | June-Aug 2017 | Aug 2017 - May 2018 | 2013 - 2018 | 2018 - now |
I am a senior research scientist at NVIDIA Seattle Robotics
Lab. I am interested in using computer vision and 3D vision for robotics tasks such as object manipulation. At
the moment, I am mainly working on model-free object manipulation in unconstrained environments. In addition, I am
interested in 6D pose estimation of objects, instance segmentation, and recognition from RGB-D images. Prior to
NVIDIA, I finished my PhD in Computer Science
department at George Mason University
where I was working under the supervision of Prof. Jana Kosecka. During
my PhD, I worked on a variety of computer vision problems for robot perception such as: vision based navigation,
object pose estimation, object detection, semantic segmentation and image based localization. I was fortunate to
work with amazing collaborators in different research groups in industry. I did internships at Google Brain
Robotics, Zoox, and Google StreetView during my PhD. Prior to my PhD, I got my masters in AI and Robotics from
University of Tehran.
News:
Publications:
ProgPrompt: Generating Situated Robot Task Plans using Large Language Models
|
|||
MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare
|
|||
Learning Robust Real-World Dexterous Grasping Policies via Implicit Shape Augmentation
|
|||
Deep Learning Approaches to Grasp Synthesis: A Review
|
|||
IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
|
|||
RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks
|
|||
STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for
Reactive
Manipulation
|
|||
Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds
|
|||
NeRP: Neural Rearrangement Planning for Unknown Objects
|
|||
Reactive Long Horizon Task Execution via Visual Skill and Precondition
Models
|
|||
RGB-D Local Implicit Function for Depth Completion of Transparent
Objects
|
|||
Contact-GraspNet: Efficient 6-DoF Grasp Generation in
Cluttered
Scenes
|
|||
Object Rearrangement Using Learned Implicit Collision
Functions
|
|||
Reactive Human-to-Robot Handovers of Arbitrary Objects
Best Human Robot Interaction
Paper |
|||
ACRONYM: A Large-Scale Grasp Dataset Based on
Simulation
|
|||
Sim-to-Real for Robotic Tactile Sensing via
Physics-Based
Simulation and Learned Latent Projections
|
|||
Learning RGB-D Feature Embeddings for
Unseen
Object
Instance
Segmentation
|
|||
Interpreting and Predicting Tactile
Signals
via a
Physics-Based and Data-Driven
Framework
|
|||
LatentFusion: End-to-End
Differentiable
Reconstruction
and Rendering for Unseen Object
Pose
Estimation
|
|||
6-DOF Grasping for
Target-driven
Object
Manipulation in Clutter
Best Robot
Manipulation
Paper
Finalist |
|||
Self-supervised 6D Object
Pose
Estimation
for
Robot Manipulation
|
|||
A Billion Ways to
Grasps -
An
Evaluation
of Grasp Sampling
Schemes
on a
Dense,
Physics-based Grasp
Data
Set |
|||
The Best of Both
Modes:
Separately
Leveraging RGB and
Depth
for
Unseen
Object Instance
Segmentation
|
|||
6-DOF
GraspNet:
Variational
Grasp
Generation for
Object
Manipulation |
|||
PoseRBPF:
A
Rao-Blackwellized
Particle
Filter for
6D Object
Pose
Tracking |
|||
Visual
Represenatations
for
Semantic
Target
Driven
Navigation |
|||
Synthesizing
Training
Data
for
Object
Detection
in
Indoor
Scenes |
|||
3D
Bounding
Box
Estimation
Using
Deep
Learning
and
Geometry |
|||
Joint
Semantic
Segmentation
and
Depth
Estimation
with
Deep
Convolutional
Networks |
|||
Multiview
RGB-D
Dataset
for
Object
Instance
Detection | |||
Semantic
Image
Based
Geolocation
Given
a
Map |
|||
Deep
Convolutional
Features
for
Image
Based
Retrieval
and
Scene
Categorization |
|||
Semantically
Guided
Location
Recognition
for
Outdoors
Scenes |
|||
Semantically
Aware
Bag-of-words
for
Localization |
|||