spsingh37

Wombat_robosuite

This work builds on top of mujoco-powered robosuite framework, and is designed for learning object-agnostic control policy for pick-and-place operations on a novel 6-DoF parallel manipulator using deep reinforcement learning. This pipeline utilizes DDPG combined with HER algorithm for training a robust manipulation policy.

3D_Liver_Tumor_segmentation

This project compares the performance of UNet, ResUNet, SegResNet, and UNETR architectures on the 2017 LiTS dataset for liver tumor segmentation. We evaluate segmentation accuracy using the DICE score to identify key factors for effective tumor segmentation.

Bayesian-filtering-and-SLAM

This is a comprehensive project focused on implementing popular algorithms for state estimation, robot localization, 2D mapping, and 2D & 3D SLAM. It utilizes various types of filters, including the Kalman Filter, Extended Kalman Filter, Unscented Kalman Filter, and Particle Filter.

Classical-computer-vision

This repo contains implementations of some of the classical computer vision algorithms/techniques for feature extraction, feature matching, image transformation, color image reconstruction, image denoising, image classification, and image segmentation.

Image-classification

This project explores image classification on the PROPS Classification Dataset. It includes K-Nearest Neighbors, Support Vector Machine, and Softmax classifiers, and two-layer and multi-layer neural networks. The goal is to build a machine learning pipeline, experiment with optimizers, and evaluate model performance.

KinoVision

This is a comprehensive project aimed at developing computer vision algorithms integrated with the kinematics of a 5-DOF manipulator. The project focuses on detecting and manipulating blocks within the reach of the robot arm.

Pose-Estimation

In this project I have implemented an end-to-end object pose estimator, based on PoseCNN, which consists of two stages - feature extraction with a backbone network and pose estimation represented by instance segmentation, 3D translation estimation, and 3D rotation estimation.

Robot-Navigation-SLAM

The project builds a comprehensive robotic system capable of autonomous navigation. This includes designing a feedback controller to regulate motor speed and a velocity-based movement controller, implementing 2D mapping using Lidar for simultaneous localization and mapping (SLAM), and constructing a path planner for effective navigation.

SelfDriveSuite

This is a comprehensive project focused on developing advanced algorithms for autonomous driving, including adaptive cruise control, model predictive control (MPC), and robust scene understanding in various weather conditions.

UAV-SaR-Tracking

This is a ROS package designed to implement Q-learning algorithm for the autonomous navigation of unmanned aerial vehicles (UAVs) in search-and-rescue (SaR) operations. It can also be used to train other reinforcement learning algorithms on UAVs. A PID algorithm is employed for position control.

spsingh37/UAV-SaR-Tracking

This is a ROS package designed to implement Q-learning algorithm for the autonomous navigation of unmanned aerial vehicles (UAVs) in search-and-rescue (SaR) operations. It can also be used to train other reinforcement learning algorithms on UAVs. A PID algorithm is employed for position control.

spsingh37/3D_Liver_Tumor_segmentation

This project compares the performance of UNet, ResUNet, SegResNet, and UNETR architectures on the 2017 LiTS dataset for liver tumor segmentation. We evaluate segmentation accuracy using the DICE score to identify key factors for effective tumor segmentation.

spsingh37/SelfDriveSuite

This is a comprehensive project focused on developing advanced algorithms for autonomous driving, including adaptive cruise control, model predictive control (MPC), and robust scene understanding in various weather conditions.

spsingh37/KinoVision

This is a comprehensive project aimed at developing computer vision algorithms integrated with the kinematics of a 5-DOF manipulator. The project focuses on detecting and manipulating blocks within the reach of the robot arm.

spsingh37/Robot-Navigation-SLAM

The project builds a comprehensive robotic system capable of autonomous navigation. This includes designing a feedback controller to regulate motor speed and a velocity-based movement controller, implementing 2D mapping using Lidar for simultaneous localization and mapping (SLAM), and constructing a path planner for effective navigation.

spsingh37/Bayesian-filtering-and-SLAM

This is a comprehensive project focused on implementing popular algorithms for state estimation, robot localization, 2D mapping, and 2D & 3D SLAM. It utilizes various types of filters, including the Kalman Filter, Extended Kalman Filter, Unscented Kalman Filter, and Particle Filter.

spsingh37/Image-classification

This project explores image classification on the PROPS Classification Dataset. It includes K-Nearest Neighbors, Support Vector Machine, and Softmax classifiers, and two-layer and multi-layer neural networks. The goal is to build a machine learning pipeline, experiment with optimizers, and evaluate model performance.

spsingh37/Pose-Estimation

In this project I have implemented an end-to-end object pose estimator, based on PoseCNN, which consists of two stages - feature extraction with a backbone network and pose estimation represented by instance segmentation, 3D translation estimation, and 3D rotation estimation.

spsingh37/Classical-computer-vision

This repo contains implementations of some of the classical computer vision algorithms/techniques for feature extraction, feature matching, image transformation, color image reconstruction, image denoising, image classification, and image segmentation.

spsingh37/ORB_SLAM3

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

spsingh37/robosuite

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

spsingh37/SAIND

spsingh37/spsingh37

spsingh37/spsingh37.github.io

spsingh37/Twilight_ORB_SLAM

spsingh37/Unsupervised-learning

This repo contains implementations of key unsupervised learning techniques, including image compression (K-means, GMM), PCA for Eigenfaces, ICA for audio separation, and CVAE for MNIST generation. It's a resource for understanding and applying foundational algorithms.