| https://devsonni.github.io |
| DS | https://devsonni.github.io/ |
| DS | https://devsonni.github.io/ |
| Home | https://devsonni.github.io/#about |
| Projects | https://devsonni.github.io/#projects |
| Publications | https://devsonni.github.io/#publications |
| Contact | https://devsonni.github.io/#contact |
|
Worcester Polytechnic Institute
| https://www.wpi.edu |
|
| https://scholar.google.com/citations?hl=en&user=v2yCu80AAAAJ&view_op=list_works&gmla=AJsN-F5Ipj6zbjyyc_Ga3XoOia8XhwhWaLQ4mIX6sNTyezHmwviCRmN1sPOvGERUT0Ou2mgXe8UMxJ2bS_-iU8rXNvoUTNNM6EUKdRZfgRmmDxl3Hwiy5J8 |
|
| https://github.com/devsonni |
|
| https://www.linkedin.com/in/dev-soni-880033184/ |
|
| https://drive.google.com/file/d/1yZUDFpR6Cqz6HAXV23i_Df__5PRRgVu6/view?usp=sharing |
| Worcester Polytechnic Institute | https://www.wpi.edu |
| Mowito.in | https://www.mowito.in/ |
| MOON-Lab | https://moonlab.iiserb.ac.in/ |
| Indian Institute of Science Education and Research, Bhopal | https://www.iiserb.ac.in/ |
| Dr. P. B. Sujit | https://scholar.google.com/citations?user=qqwyAwoAAAAJ |
| Computer Vision | https://devsonni.github.io |
| Robotics | https://devsonni.github.io |
|
| https://devsonni.github.io/project/autocalib/ |
| AutoCalib - Camera Calibration | https://devsonni.github.io/project/autocalib/ |
|
This project implements Zhang’s method for camera calibration. Camera calibration is essential in computer vision to obtain the intrinsic and extrinsic parameters of a camera, which are used to correct image distortions and understand the 3D geometry of the scene.
| https://devsonni.github.io/project/autocalib/ |
|
Code
| https://github.com/devsonni/CameraCalibration |
|
| https://devsonni.github.io/project/autopano/ |
| AutoPano - Panorama Stitching | https://devsonni.github.io/project/autopano/ |
|
The panorama stitching project uses SIFT feature descriptors for key point matching and RANSAC for outlier rejection. The images are blended with distance transformation, resulting in a seamless and coherent panoramic image.
| https://devsonni.github.io/project/autopano/ |
|
Code
| https://github.com/devsonni/AutoPano |
|
| https://devsonni.github.io/project/charts-classifier-using-cnn/ |
| Charts Classifier Using CNN | https://devsonni.github.io/project/charts-classifier-using-cnn/ |
|
Convolution Neural Network architecture was designed to classify chats data into one of five categories (Vertical Bar, Horizontal Bar, Dot Line, Line, Pie). Fine tunned VGG16 model for this task. Implement GradCAM to visualize activation areas in images.
| https://devsonni.github.io/project/charts-classifier-using-cnn/ |
|
Code
| https://github.com/devsonni/Chart-Classification-Using-CNN----Keras |
|
| https://devsonni.github.io/project/powered-lower-limb-exoskeleton/ |
| Powered Lower Limb Exoskeleton | https://devsonni.github.io/project/powered-lower-limb-exoskeleton/ |
|
I was team leader of the winning team in the Robofest2.0 competition under the powered lower-limb exoskeleton category. The competition was a state-level competition, and teams from tier-1 universities such as SVNIT, Nirma University, BVM, and more participated. Click and find more details regarding the competition and our project.
| https://devsonni.github.io/project/powered-lower-limb-exoskeleton/ |
|
PDF
| https://github.com/devsonni/Powered-Lowerlimb-Exoskeleton/blob/main/Pdf/Powered%20Exoskeleton%20-%20ITM%20Vocational%20University.pdf |
|
Code
| https://github.com/devsonni/Powered-Lowerlimb-Exoskeleton |
|
Slides
| https://drive.google.com/file/d/1UiS9KuFzgWpcNpdP616V2AENGmsnLGZb/view?usp=sharing |
|
Video
| https://youtu.be/J-kVJl1uBLg |
|
| https://devsonni.github.io/project/nonlinear-model-predictive-controller-for-target-tracking/ |
| Nonlinear Model Predictive Controller for Target Tracking | https://devsonni.github.io/project/nonlinear-model-predictive-controller-for-target-tracking/ |
|
Nonlinear Model Predictive Controller (NMPC) implemented with the use of CasADi optimization framework and matlab simulation environment. Controller is able to avoid Static & Dynamic Obstacles also State and Control Constraints of UAV and gimbal was added to make problem realistic.
| https://devsonni.github.io/project/nonlinear-model-predictive-controller-for-target-tracking/ |
|
Code
| https://github.com/devsonni/MPC-Implementation |
|
Video
| https://devsonni.github.io/will%20add%20soon |
|
| https://devsonni.github.io/project/controlling-quadrotor-with-pid-controller/ |
| Controlling Quadrotor with PID Controller | https://devsonni.github.io/project/controlling-quadrotor-with-pid-controller/ |
|
Coded PID controllers for controlling Quadrotor in 1D, 2D and 3D planes, and created inner loop (altitude control) and outer loop (position control) of PID controller for 3D control of Quadrotor.
| https://devsonni.github.io/project/controlling-quadrotor-with-pid-controller/ |
|
Code
| https://github.com/devsonni/Control-of-Quadrotor |
|
Video
| https://youtu.be/2QQ5qjsZ9E4 |
|
| https://devsonni.github.io/project/factory-automation-with-robot-operating-system-ros/ |
| Factory Automation with Robot Operating System (ROS) | https://devsonni.github.io/project/factory-automation-with-robot-operating-system-ros/ |
|
This project was a course work of this course. Project consists of setting up Pub-Sub mechanism for communicating between two ROS nodes, modifying URDF model of factory, ROS Navigation stack for navigating turtle bot in factory environment, manipulation of robotic arm by ROS MoveIt package and behaviour setup with FlexBE App state machine.
| https://devsonni.github.io/project/factory-automation-with-robot-operating-system-ros/ |
| this | https://www.edx.org/course/hello-real-world-with-ros-robot-operating-system |
|
Code
| https://github.com/devsonni/hrwros_ws |
|
Video
| https://www.youtube.com/watch?feature=player_embedded&v=Wp_6LamoRL0 |
|
| https://devsonni.github.io/project/learning-nmpc-with-q-learning-reinforcement-learning-algorithm/ |
| Learning NMPC with Q-Learning-Reinforcement Learning algorithm | https://devsonni.github.io/project/learning-nmpc-with-q-learning-reinforcement-learning-algorithm/ |
|
Q-Reinforcement learning algorithms is designed to improve video cinematography of car racing scenario, for each racing iteration different NMPC weights are selected and optimal policy is being developed - performance of the filming car improves with respect to race iteration.
| https://devsonni.github.io/project/learning-nmpc-with-q-learning-reinforcement-learning-algorithm/ |
|
PDF
| https://drive.google.com/file/d/1rpYImnOZGlbbJ-1rbkSQZR77havK46RD/view?usp=sharing |
|
Code
| https://github.com/devsonni/RL-NMPC |
|
Slides
| https://devsonni.github.io/slides/example/ |
| Wowchemy | https://wowchemy.com/?utm_campaign=poweredby |
| open source | https://github.com/wowchemy/wowchemy-hugo-themes |
|
Copy
| https://devsonni.github.io |
|
Download
| https://devsonni.github.io |