Sudharshan Suresh | Suddhu

suddhu [at] cmu [dot] edu

I'm a PhD student in the Robotics Institute at Carnegie Mellon University, where I work with Michael Kaess in the Robot Perception Lab. I'm broadly interested in statistical methods for robot perception and state-estimation.

I completed my Masters in Robotics at CMU working with Michael Kaess on underwater localization and active SLAM for AUVs. Prior to that, I worked with Red Whittaker on visual state-estimation for lunar rovers, and spent time at IISc Bangalore working on visual understanding. In my days of yore, I majored in Controls and Instrumentation at NIT Trichy.

CV  /  Google Scholar  /  RI webpage  /  Github

 

Research

(ongoing) Shape and pose estimation with contact implicit surfaces

Robots need accurate, online estimates of shape and pose while manipulating unknown objects. Interestingly—even when blindfolded—humans can infer object properties from local tactile information. We investigate combining Gaussian process implicit surfaces with incremental solvers to localize and infer the shape of objects

Active SLAM using 3D submap saliency for underwater volumetric exploration
 
S. Suresh, P. Sodhi, J. Mangelson, D. Wettergreen, and M. Kaess
 
IEEE Intl. Conf. on Robotics and Automation, ICRA, 2020. To appear.

(pdf / video)
Through-water stereo SLAM with refraction correction for AUV localization
 
S. Suresh, E. Westman, and M. Kaess
 
IEEE Robotics and Automation Letters, Part of ICRA/RA-L: Presented at ICRA 2019 and published in RA-L, Jan 2019

(pdf / video)
Localized imaging and mapping for underwater fuel storage basins
 
J. Hsiung, A. Tallaksen, L. Papincak, S. Suresh, H. Jones, W. L. Whittaker, and M. Kaess
 
Proceedings of the Symposium on Waste Management, Phoenix, Arizona, Mar 2018

(pdf / slides / video)
Optical kinematic state estimation of planetary rovers using downward-facing monocular fisheye camera (pdf / video / poster)
 
S. Suresh , E. Fang, and W. L. Whittaker
 
Robotics Institute Summer Scholars Working Paper Journal, Nov 2016
 
Camera-Only Kinematics for Small Lunar Rovers (poster / pdf)
 
E. Fang, S. Suresh, and W. L. Whittaker
 
Annual Meeting of the Lunar Exploration Analysis Group, Nov 2016
Object category understanding via eye fixations on freehand sketches
 
R. K. Sarvadevabhatla, S. Suresh and R. V. Babu
 
IEEE Transactions on Image Processing (TIP), May 2017

(paper / project page)

 

Projects

DeepGeo: photo localization with deep neural network   (arXiv / github)
 
S. Suresh, N. Chodosh, and M. Abello
 
A deep network that beats humans at GeoGuessr, trained on our 50States10K dataset.
Task and motion planning for robotic food preparation   (PDF / Video 1 / Video 2)
 
S. Suresh, T. Rhodes, M. Abello, and H. Yadav
 
Hierarchical task and motion planning for a 6-DOF robot arm, to prepare yogurt parfaits!
Thin structure reconstruction via 3D lines and points   (Poster)
 
S. Suresh and M. Abello
 
Reconstructing thin objects in a scene through an SfM pipeline can be hard!
Factor graph optimization for dynamic parameter estimation   (Report)
 
S. Suresh, E. Dexheimer, and M. Abello
 
We implement a method for estimation of MAV poses and dynamic parameters during flight.

Last updated circa April 2020

Template stolen from Jon Barron.