Siddhant Panigrahi

What have I done ?

Projects

This section deals with providing readers a brief summary of the projects in which I was involved and the papers published by me. Each project revolves around a conceptual idea which is designed, modeled, simulated and then brought to life. Rather than boring you with the entire design methodology I have provided a short outlook on each project separately. Many projects includes the sweat and blood of other members who have been duly credited.

Feel like suggesting something ? You know where to reach me

Till then keep inventing

Mobile Robotics

Novel hybrid VTOL Tiltrotor

The novel design of the Tiltrotor was presented to increase the endurance of the VTOL thrust vectoring ability of the individual actuators, enabling takeoff and hovering as a VTOL vehicle and flight as a fixed-wing aircraft.

Credits : Dr Asokan T, Kumar Surjdeo Singh, Siva Sai Krishna

Publication

Modelling and control of submersible multi-medium UAV

This work presents the mathematical model and control of a proposed submersible UAV. The governing equations have significant changes between these mediums, and they are coupled non-linear system of differential equations.

Credits : Dr Asokan T, Vaibhav Ashok , Dr. Thiyagarajan Ranganathan

Publication

All-Terrain Rover for improved lateral stability

This research presents the conceptual design of a novel four-wheeled rover based on the DUNE rover architecture. A mathematical model of the proposed rover is formulated to quantitatively compare the stability and mobility performance metrics on multiple terrain conditions with that of the conventional DUNE rover design.

Credits : Dr Asokan T, Aditya Kuncolienkar

Publication

Computer Vision

Plant-based disease detection using onboard aerial payloads

In this current research, we present the methodology for performing real-time plant disease detection using lighter versions of deep learning algorithms implemented on sample payloads of mobile robots. Field studies demonstrate that such a fabricated platform can characterise not only the disease but also identify its associated stages with a Mean Average Precision (mAP) of 96% within 6000 training iterations, achieving a detection speed of 6-10 FPS.

Credits : Dr Asokan T, Prajwal Maski

Publication

Biodiversity analysis using mobile robotic platforms

In this research, we present the methodology in developing a real-time biodiversity map using deep learning algorithms like YOLOv3, which is applied on high spatial resolution photographs or real-time videos captured by inexpensive cameras mounted on a UAV platform for in-situ data acquisition.
Credits : Dr Asokan T, Prajwal Maski

Publication

Real-time joint angle estimation using for rehabilitation

The fusion of a low-cost vision-based sensor using computer vision with an inertial measurement unit is proposed in this paper to perform real-time joint angle estimation. This paper presents a robust, low-cost, and portable platform using inertial and vision sensors for real-time joint angle tracking for rehabilitative tasks.

Credits : Dr Asokan T, Poongavnam Palani, Abhinav Jammi

Publication

Robot navigation

SLAM in indoor mobile robots

The entire aim of this project was to implement SLAM and local and global-based planning algorithms in indoor environments using Turtlebot 3. The experimental demonstration is shown along the RViz and Gazebo simulation for the simulated workspace.

Credits : Dr Asokan T, Dr Nagamanikandan, Dr Bijo Sebastian, Dr Nirav Patel

Multimedia

Swarm based exploration in unknown environments

The objective of this research is to study the functionality of multi-robot systems by investigating map-merging and nearest-robot navigation using a case study of Turtlebot3. In this study, computational simulations are performed in the ROS framework, where multiple robots are deployed to generate individual local maps.

Credits : Dr Sivasankar Ganesan

Publication

Heuristic Soft Actor-Critic method for autonomous mobile robot navigation

Existing literature on deep reinforcement learning-based methods (DRL) for mobile robot navigation are effective in understanding indoor environments. This paper proposes a study on heuristic-based DRL technique for autonomous mobile robot navigation.

Credits : Dr Asokan T, Dr Sivasankar, Maram Vishnu, Pranalli Engole

Multimedia

Soft Robotics / Rehabilitation

Self-evolving control of soft pneumatic rotary actuators

This research presents the dynamic modelling and self-evolving fuzzy-based closed-loop control for Soft Bidirectional Bending Actuator (SBBA) using visual feed-back. Exteroceptive feedback is obtained from color markers, which is integrated with the proposed control method to regulate the input pressure to the actuator.

Credits : Dr Asokan T, Adil Mohammed Kizhakkethil, Kumar Surjdeo Singh

Multimedia

Virtual reality based training simulator for MIS

Virtual reality (VR) has been proven to be a great tool for embodied learning, but existing studies demonstrate a need for suitable open-source interactive platforms for medical interventions. Addressing this need for robot-assisted surgery (RAS) skills acquisition, we propose a heuristic learning scheme in a simulator encompassing cross-platform registration tasks to train individuals for typical minimally invasive procedures (MIS).

Credits : Dr Nirav Patel, Abhinav Azad

Publication

Three-Axis Force Monitoring Device for Static Shoulder Therapy

Static shoulder rehabilitation exercises are performed by stroke patients suffering from shoulder subluxation, which requires pushing the hand against a rigid surface. This paper also presents the design of the three-axis force sensor along with system mechatronics design and calibration. The device is then tested by incorporating it with a simple game interface to carry out a game-based rehabilitation exercise.

Credits : Dr Asokan T, Avinash Pramod, Naveen Varala Reddy

Publication

Sensing Methodologies

13489373_1135190316531192_1300774692_n.mp4

Fragmentation in Ballistic missiles

The aim of this project was to experimentally study fragmentation of elastic membrane and analogously compare it to ballistic missiles. The primary aim of this study is to find out the relationship between critical pressure, no of fragments, and distance of impact so that these parameters can be optimized to increase the impact of any elastic ballistic member.

Credits : Dr HS Panda

Certification

Solar energy harvesting using DSSC

Major problem with solar cells of recent times is the cumbersome manufacturing process and its expense. In Dye sensitized solar cells we bio-mimic the chloroplast of plants and implement the same idea of photosynthesis to harvest clean, green and sustainable energy.

Credits : Dr Agnimitra Biswas, Siddharth Hota, Jai Prakash

Project Presentation

Analysis of Closed-Loop Depth Control for Underwater Glider-RoBuoy

Underwater gliders (UGs) generally employ concept of variable buoyancy for motion. Variable buoyancy results in heave motion and addition of wings to the glider creates a pitching moment due to lift and drag forces acting on the wings. Proposed design parameters of RoBuoy are utilized and dynamic modeling is simulated in MATLAB Simulink environment. A dual loop control methodology is also proposed for depth control of RoBuoy to achieve a trajectory tracking with a maximum permissible error of 0.2 m in zigzag trajectory.

Credits : Dr Asokan T, Chandra Prabha, Kailash RS

Paper Link

How can you reach me ?

Looking forward to hearing from you soon

Siddhant Panigrahi,

Robotics Lab, Dept. of Engineering Design, Indian Institute of Technology Madras, Chennai 600036, INDIAEmail : sid.panigrahi1709@gmail.com

Page updated

Google Sites

Report abuse