Name: Shambhuraj Anil Mane
Type: User
Company: Worcester Polytechnic Institute
Bio: I am currently a Robotics Masters student at Worcester Polytechnic Institute graduating in May 2025.
Location: United States
Blog: https://shambhurajmane.github.io/
Shambhuraj Anil Mane's Projects
The purpose of this repository is to stitch two or more images in order to create one seamless panorama image. The functions covered are Corner detection, Adaptive Non-Maximal Suppression, Feature Matching, RANSAC for outlier rejection, Homography estimation and Blending.
This report presents a two-phase assignment focusing on boundary detection and neural network architecture evaluation. Thee objective is to develop a pb (probability of boundary) algorithm for efficient boundary detection in images. Phase 2, we will implement multiple neural network architectures for analysis on various criteria on CIFAR10 dataset.
This repository implemts a baseline convolutional neural network, few techniques to improve its accuracy, along with implemention of ResNet, ResNeXt and DenseNet architectures.
mplemented algorithms like BFS, DFS, Dikjstras, A*, PRM, RRT and RRT* with a configurable density of obstacles and conducted a comprehensive comparative analysis of these algorithms. ◦ Developed a state lattice planner for differential and Ackermann constraints, incorporating optimized cost functions within a hybrid A* framework
This repository delves into the critical realm of multi-agent path planning of Non-holonomic Mobile robots. The objective is to design and implement ICBS (Improved Conflict-Based Search) that enables multiple agents to navigate environments, coordinating their movements seamlessly while avoiding collisions.
This repository implements boundary detection pipeline by applying filter banks, specifically implementing DoG filters, Leung-Malik Filters and Gabor Filters, to produce a texton map capturing image texture through clustered filter responses.
This repository demonstartes, RL based path planning for short range given a target state (pose). The robot is equipped with a 2D Lidar sensor, RL-based path planner provides optimal paths to given target pose independent of map environmennt.
Here I have performed ROS2 implementations of some foundation concepts in Robotics. This repository encompasses essential concepts such as kinematics, dynamics, sensing, and control.
In this repository postion, velocity and current control methods are implemented to Open manipulator X arm.
Readme.md for Github profile
Portfolio