I'm

Manan Tayal

PhD Student@ IISc Bangalore, IIT Bombay Graduate, Robotics Engineer
Hero Image
Image

About Me

Hi! I am Manan, a Research Scholar at Robert Bosch Centre for Cyber Physical Systems (RBCCPS) in Indian Institute of Science (IISc) Bangalore, working on Control and Design of Walking Robots in the Stochastic Robotics Lab under the guidance of Prof. Shishir N. Y. Kolathaya and Prof. Ashitava Ghoshal and collaborating with Prof. Ayonga Hereid (Ohio State University)

Currently, my work is focussed towards the development of a lightweight control framework for robust proprioceptive bipedal walking.

I completed my B.Tech in Mechanical Engineering from Indian Institute of Technology Bombay (IITB). I actively work in the fields of Robotics, Controls and Learning. In my undergraduate years, I have also worked on various robotics projects like control of Quadruped Bot, Force controlled gripper, FLORENCE (A Robotic Nurse), etc.

My Resume

Working Experience

Aug'21 - Present

Research Scholar

Stochastic Robotics Lab

Apr'20 - May'20

Research Intern

Siemens Technology and Services Pvt. Ltd

Aug'19 - Mar'20

Robotics Control

Team Stride, IIT Bombay

Apr'19 - Mar'20

Manager

Tinkerers' Laboratory, IIT Bomaby

Oct'18 - Apr'19

Team Member,Robocon team IITB

ABU Robocon'19

Jul'18 - Jun'19

Freelance Educator

Toppr

Apr'18 - Mar'19

Convenor

Tinkerers' Laboratory, IIT Bombay

My Education

Aug'21 - Present

Indian Institute of Science (IISc) Bangalore

PhD, Cyber Physical Systems

CPI: 9.30/10

Aug'17 - July'21

Indian Institute of Technology Bombay(IITB)

BTech, Mechanical Engineering

CPI: 9.13/10

Apr'15 - Mar'17

S.D.Jain Modern School, Surat

Intermediate/+2

Percentage(12th Board): 94%

Apr'13 - Mar'15

S.D.Jain Modern School, Surat

Matriculation

CGPA (10th Board): 10/10

My Projects

My Projects

  • All
  • Robotics
  • AI
  • Mechanical Design
Image

Safe Reinforcement Learning Using Robust Control Barrier Functions

>
Image

Offline Reinforcement Learning with Implicit-Q-Learning

>
Image

FLORENCE (Robotic Nurse)

>
Image

Parallelisation of TSP

>
Image

Bone Conduction Headphone

>
Image

PANACEA

>
Image

Sleep Detector

>
Image

Quadruped in Pybullet

>
Image

Titanium Nanotubes

>
Image

Force Controlled Gripper

>

Research

Research Proposal

Design, Learning and Control of Legged Robots: The goal of the research is to design a low cost, affordable Bipedal Robot and to identify a minimum possible control framework that can be deployed to realise stable locomotion behaviour on challenging terrains

Work Done So Far

Have used Arms to stabilize the locomotion of Bipedal Robot while Walking and Hopping by using Learning Based control of Arm Motions and Swings

Course Work

Semester 1

E0 230 | Computational Methods of Optimization

Instructor: Prof. Chiranjib Bhattacharyya

Need for unconstrained methods in solving constrained problems. Necessary conditions of unconstrained optimization, Structure of methods, quadratic models. Methods of line search, Armijo-Goldstein and Wolfe conditions for partial line search. Global convergence theorem, Steepest descent method. Quasi-Newton methods: DFP, BFGS, Broyden family. Conjugate-direction methods: Fletcher-Reeves, Polak-Ribierre. Derivative-free methods: finite differencing. Restricted step methods. Methods for sums of squares and nonlinear equations. Linear and Quadratic Programming. Duality in optimization.

Semester 1

E1 222 | Stochastic Models and Applications

Instructor: Prof. Subbayya Sastry P

Probability spaces, conditional probability, independence, random variables, distribution functions, multiple random variables and joint distributions, moments, characteristic functions and moment generating functions, conditional expectation, sequence of random variables and convergence concepts, law of large numbers, central limit theorem, stochastic processes, Markov chains, Poisson process.

Semester 1

CP 212 | Design of Cyber-Physical Systems

Instructor: Prof. Shishir NY

1. Microprocessor system 2. Interfacing physical devices 3. Control system basics 4. EMI/EMC considerations 5. Network connectivity

Semester 1

CP | Mathematical Techniques for Robotics and Autonomous Systems

Instructor: Prof. Bharadwaj Amrutur

Fields and linear equations over fields, Vector spaces : Definition, basis and dimension, direct sums. Linear transformations: definition, the Rank-Nullity Theorem, the algebra of linear transformations. Dual spaces. Determinants. Eigenvalues and Eigenvectors, the characteristic polynomial, the Cayley-Hamilton Theorem, the minimal polynomial, and algebraic and geometric multiplicities. Diagonalization. Geometric Algebra

Semester 2

CP 315 | Robot Learning and Control

Instructor: Prof. Shishir NY

Robot dynamics and kinematics, nonlinear control and stability, Lyapunov theory, PD control, reinforcement learning, imitation learning, model-based and model-free methods, impedance control, trajectory optimization, online learning.

Semester 2

E1 277 | Reinforcement Learning

Instructor: Prof. GuganThoppe, Prof. Shalabh Bhatnagar

Introduction to reinforcement learning, introduction to stochastic dynamic programming, finite and infinite horizon models, the dynamic programming algorithm, infinite horizon discounted cost and average cost problems, numerical solution methodologies, full state representations, function approximation techniques,approximate dynamic programming, partially observable Markov decision processes, Q-learning, temporal difference learning, actor-critic algorithms.

Semester 2

E1 213 | Pattern Recognition and Neural Networks

Instructor: Prof. Prathosh AP

Introduction to pattern recognition, Bayesian decision theory, supervised learning from data, parametric and non parametric estimation of density functions, Bayes and nearest neighbor classifiers, introduction to statistical learning theory, empirical risk minimization, discriminant functions, learning linear discriminant functions, Perceptron, linear least squares regression, LMS algorithm, artificial neural networks for pattern classification and function learning, multilayer feed forward networks, backpropagation, RBF networks, deep neural Networks, support vector machines, kernel based methods, feature selection and dimensionality reduction methods

Publications

Pre-Prints

2022

Travelling Salesman Problem: Parallel Implementations & Analysis

arXiv preprint arXiv:2205.14352

A Gohil, M Tayal, T Sahu, V Sawalpurkar

[PDF]



2022

Safe Learning with Robust Control Barrier Functions: An Analysis using different Deep RL Models

arXiv preprint arXiv:2205.14352

M Tayal, Alokendu Mazumder

[PDF]