Nonlinear Model Predictive Control for Mobile Robots
NMPC algorithm for collision-free navigation of a mobile robot in unknown and dynamic environments
NMPC algorithm for collision-free navigation of a mobile robot in unknown and dynamic environments
Policy Generation for Mobile Robot in obstacle environment using Policy Iteration , Generalised Policy Iteration , and Value Iteration in both Deterministic , and Stochastic Models. Here process is assumed to be Markov Decision Process , and the problem is solved using Dynamic Programming
Swapping faces in the images using Thin Plate Spline and Triangulation Methods
Designed a control algorithm for under-actuated systems based on time dependant linear quadratic regulator
Mapping 3D scene using camera motion , Linear PnP and Bundle Adjustment
The project demonstrates the fabrication practices and integration approach to assemble the platform and replicate internal involuntary body movements associated with breathing, heart movement, and peristalsis.
Design of various controllers for planar RR bot using MATLAB. Tested these algorithms using ROS and Gazebo
Seamless Panorama stitching using ANMS and Deep Learning
Time series response of closed loop control systems with P,I,PI,PD and PID controls with unit step response.
Navigating Mobile robots using various sampling based algorithms such as Probabilistic Road Map,RRT and RRT*
simplified version of Probability of Boundary (pb lite) detection algorithm, and CNN for Image classification
Motion planning for mobile robots using Informed RRT* and , Motion planning in dynamic environment using D* agorithm.
Stereo visual inertial odometry using Multi- State Constraint Kalman Filter
Built a wall climbing robot to test the android based visual feedback controller.
Calibrating camera’s intrinsic and extrinsic parameters using Zhang’s calibration method
Predictive Maintenance architecture for Rotary equipment in manufacturing operations using AI and DSP
Iterative closest point implementation for mapping the LIDAR , and segmentation using neural networks
Python Program to compute best fit line or plane using random sample consensus