1. EDUCATION
· University of Michigan, GPA:3.95/4.0 Ann Arbor, MI
Master of Science in Engineering, Robotics Sept. 2018 - Apr. 2020
Coursework: Self Driving Cars, Computer Vision, Computational Data Science, Machine Learning,
Deep Learing Mobile Robotics.
· VIT University, CGPA: 9.35/10 Vellore, India
Bachelor of Technology in Mechanical Engineering May 2018
Coursework: Industrial Automation controllers, Mechatronics, Data Structure and Algorithms,
Robotics, Applied Numerical Methods, Probability and Random processes, Complex Theory.
: vatsuak@umich.edu : (734)-8813359 : kaustavchak
KAUSTAV CHAKRABORTY
RESEARCH
Graduate Student Research Assistant, Bipedal Robot Laboratory, Ann Arbor Michigan May 2019
Designed Deep Neural for LiDAR based Detection of Visual Fiducial scans with an accuray of 99.82%
(1% improvement over the State of Art) in Tensorflow with CUDA architecture under Prof. Jessie Grizzle
Handled over 80Gb of real world dataset collected by Cassie robot’s Vision Suite to produce online software
Read Lidar data from Velodyne Ultra Puck using Velodyne ROS Package and stored raw returns as ROSBAG files
Applied SVD, homogeneous transforms for dimentionality reduction and data projections for feature engineering
Employed LSTM and PointNets to build novel convolutional RNN network
Graduate Researcher, Biologically Inspired Robotics and Dynamical Systems Lab, Ann Arbor, MI. Nov. 2018
· Designed Self-righting shell for Terrestial Hexapod -“Big Ant” under Prof. Shai Revzen
· Optimized Spline Designs in the form of 2nd order differential equations,parameterized with 6 variables using Matlab
· Studied and employed complex geomectric structures like Gomboc, to apply concepts of equiliburim position
· Modelled 3D sturucture of shell inspried from insects using Solidworks and Audodesk Inventor
· Created protype of model using 3D printer for physical experiments
EXPERIENCE
Innovation Chair, Human Powered Vehicle Student Team, VIT University, Vellore, India May 2016 – Mar. 2018
· Lead a team of five in the implementation of innovative safety features based on proximity sensors to automatically apply the brakes
and extend a balancing platform based on emergency circumstances in two wheeled vehicles.
· Managed two team-departments in CAD modelling, FEA, and coding in C.
· Implemented an air-bag helmet to protect a two-wheeler rider, in Aruino using an external IMU.
Plant Automation and Calibration Intern., Dec. 2016 – Feb. 2017
Hindustan Petroleum Corporation Limited, Kolkata, India
· Calibrated and maintained large datasets for the daily operation of centrifugal pumps, which includes the rate and quantity of oil flow,
the amount of electricity consumed, and the mechanical work done
· Studied the working of Variable Frequency Drives and manually calibrated Flowmeters
· Applied regression techniques to estimate cost of running and brought the margin of error to 0.75%
· Analytically quantified cost effectivity between the mechanical and automation processes. It was assessed that the process of
automation cuts down the cost of the pump operation by at least 35% annually.
· Presented poster titled, “Effect of Variable Frequency Drive On The Mechanical Efficiency Of Reciprocating Pumps”.
SKILLS
Languages: Python, C/C++, Julia, MatLab, JAVA, .
Frameworks: TensorFlow, Keras, OpenAI gym, Pytorch, OpenCV, Open3D, Scikit-Image, Scikit-Learn.
Others: Git/Version Control, SolidWorks, Autodesk Fusion, ANSYS, ADAMS, Automation Studio, Step7, Picosoft, JSON,
Allen Bradley PLC controller, MS Office, LaTex.
Platforms: ROS, Linux-Ubuntu, Mac OS, Windows.
2. PROJECTS
Probabilistic Robotics
· Applied SLAM to mobile robotics using techniques like Monte Carlo Methods, Baeyes Localization, Kalaman Filters and its
derivatives
· Modelled basic vehicular odometry to represenst motion models for two dimentional motion
· Coded in MATLAB to map environment using Victoria Parks Dataset
· Designed JORB-SLAM, an innovative multi-agent slam system that employs a centrlized optimization technique by running
ORB-SLAM in one or more agents, additionally using AprilTags based visual localization to provide infrormation and add
additional linkages/keyframes to the factor graph so developed, and tested the results on KITTI dataset as well as self-collected
dataset.
Computer Vision
· Implemented essential image techniques like feature detection, Visual bag of words, Panoramic stitching , Structure from motion
and camera calibration in Python using openCV, open3D
· Implemented and trained a U-Net inspired model using Pytorch to segment Facade dataset achieveing 70% accuracy
· Coded backpropagagation algorithm and feed forward operations like convolution, pooling, fully conncted layers and trained an
MNIST classifier to achieve 95% acccuracy on testing dataset
· Extended the work in “Neural Artistic Style Transfer” by changing the loss funtion to integrate of more than one style to to the
base image along with the addition of skipped connections to better accumulate features
Computational Data Science
· Implemented essential feature engineering techniques like SVD, ICA, PCA, Multidimensional scaling, Graph analysis, and
decision theory.
· Coded in Julia language to implement classification, structure from illumination, background-foreground subtraction.
Self-Driving Cars: Control and Perception
· Employed transfer learining using RCNN, and VGG models for recognizing 5 different car classes in a data set of size 10 Gb
sourced from GTA 5 game achieving a prediction accuracy of 72%
· Implemented concepts of stereo perception, SLAM, visual odometry in real-world lidar data and camera images.
· Programmed in MATLAB to manipulate images, cloud point data and designing multi-layed perceptrons to classify MNIST
dataset
· Generated and simulated trajectory for a dynamic model of using techniques like nonlinear optimization, LQR for a bicycle
model as well as the Pacejka Tire model.
Object detection
· Implemented hand crafted classifiers to perform object detection and segmentation
· Used basic openCV function to detect shape, difference in illumination to determine the bounding boxes around various objects
in images.
· Attained an accuracy of 80% on a completely unknown custom dataset of 150 images
Robotics Systems Laboratory
· Built and controlled a 4-DoF robotic arm coupled with Kinect depth-camera, forward and inverse kinematics, trajectory planning
and motion smoothing. Designed a rack-and-pinion based gripper.
· Employed methods of particle filtering using incoming sensor information from 2D RP-LiDAR to build a SLAM system for
autonomous wheeled robot. Implemented occupancy grid mapping and A* path planning.
· Designed a PID controlled cascading control loop to balance a bi-wheeled balancing robot, using wheel encoders and gyroscope
for implementing a unique gyrodometry based dead-reckoning system.
AWARDS
· Top 3% among 800 students in class of 2018 Mechanical Engineering(B.tech) from VIT University, India
·1st Position in Innovation Event and 5th Position in Design Event in ASME HPVC Asia Pacific-2017
·1st position in Invention Showcase at Student Led Design Conference India 2016
PUBLICATIONS
· “Investigation and Evaluation of Hygrothermal Effects on GFRP and CFRP” at Proceedings of The nineteenth National Seminar
on Aerospace Structures, Feb 23-25, 2017, VIT –Vellore.
· “Effect Of Flake Reinforcement On Mechanical Properties Of AA 6061 Nano Composite With Secondary Nano Platelet-Graphene
Processed Through Powder Metallurgy” at International Conference On Emerging Trends In Materials And Manufacturing
Engineering,2017, National Institute of Technology, Tiruchirapalli.