|
suddhu [at] cmu [dot] edu I'm a final-year PhD candidate in the Robotics Institute at Carnegie Mellon University, advised by Michael Kaess. I work on spatial AI from touch and vision for robot manipulation. My thesis focuses on learning object-centric representations and harnessing vision-based touch. I'm also a visiting researcher at Meta AI, where I work with Mustafa Mukadam. I completed my Masters in Robotics at CMU with Michael Kaess on underwater exploration and SLAM (thesis). Prior to that, I worked with Red Whittaker on state-estimation for lunar rovers, and at IISc Bangalore working on visual understanding. In my undergrad, I majored in Controls and Instrumentation at NIT Trichy.
I'm on the job market for research positions in industry, starting early 2024. |
|
Updates
[Aug '23] |
Our work RotateIt, led by Haozhi, was accepted to CoRL 2023. |
[April '23] |
Spending the summer as a research scientist intern at Meta AI Menlo Park on visuo-tactile manipulation! |
[Dec '22] |
MidasTouch was showcased at CoRL 2022 with a live demo. |
[Oct '22] |
Successfully passed my Ph.D. thesis proposal! |
[Sep '22] |
MidasTouch was accepted to CoRL 2022 as an oral. |
[Aug '22] |
We've extended iSDF for neural mapping with the Franka robot, code here. |
Hover for more updates
[May '22] |
Organized the Debates on the Future of Robotics Research workshop at ICRA '22 |
[April '22] |
Spending the summer at Meta AI Pittsburgh working on pose tracking from touch |
[Jan '22] |
ShapeMap 3-D was accepted to ICRA 2022, with an open-source implementation. |
[Aug '21] |
Presented at the Tartan SLAM series on our working on perception for planar pushing, video here. |
[May '21] |
Tactile SLAM was the ICRA 2021 best paper in service robotics finalist! |
Research |
|
A visuotactile transformer gives us general dexterity for multi-axis object rotation in the wild.
|
|
Tracking the pose distribution of a robot finger on an object surface over time, using surface geometry captured by a tactile sensor
|
|
Can we efficiently reconstruct household objects with touch and vision? We harness the GelSight sensor and a depth-camera for 3-D shape perception, as inference on a spatial graph informed by a Gaussian process.
|
|
Can we estimate object shape and pose in real-time through purely tactile sensing? We demonstrate this for planar pushing, combining Gaussian process implicit surfaces with factor-graph based inference.
|
|
How do you balance volumetric exploration and pose uncertainty in exploration? We combine a sampling-based planner, deformable pose graph, and a 3D saliency metric to explore a 3D underwater volume.
|
|
How can you incorporate refraction into water-to-air visual SLAM? We present a novel method inspired by multimedia photogrammetry for underwater localization.
|
|
What's the ideal sensor suite for underwater dense mapping? We build and demonstrate an inspection solution comprising of a stereo camera, IMU, standard + structured lighting, and depth sensor.
|
|
Annual Meeting of the Lunar Exploration Analysis Group, Nov 2016
Is it possible to track a lunar rover's kinematic state through self-perception? With a downward-facing fisheye lens, we estimate the Autokrawler's kinematics on rugged terrain.
|
|
Can we better understand free-hand sketches through human gaze fixations? We collect the SketchFix-160 dataset and investigate visual saliency to reveal multi-level consistency in sketches.
|
Other projects
|
Extending iSDF to build real-time neural models of tabletop scenes with the Franka Panda arm
|
|
A deep network that beats humans at GeoGuessr, trained on our 50States10K dataset.
|
|
Hierarchical task and motion planning for a 6-DOF robot arm, to prepare yogurt parfaits!
|
|
Reconstructing thin objects in a scene through an SfM pipeline can be hard!
|
|
We implement a method for estimation of MAV poses and dynamic parameters during flight.
|
|
Last updated: Sep 2023 |