Animesh Singhal's Projects
cascaded PID controller for drone with speed & throttle constraints; capable of handling model-errors
This repository is Gazebo plugin for actor to navigation in simulation environment autonomously.
A collection of ROS1 and ROS2 dockers with GUI capabilities.
Advanced lane-finding algorithm using distortion correction, image rectification, color transforms, and gradient thresholding. Lane curvature and vehicle displacement identified.
Convolutional neural network built and trained – for end-to-end driving in a simulator – using TensorFlow and Keras.
Kalman filter applied – on lidar and radar measurements from the self-driving car – to track a bicycle's position and velocity.
Detection of highway lane lines on a video stream. Used OpenCV image analysis techniques to identify lines, including Hough Transforms and Canny edge detection.
Localization of self-driving car by applying a 2-D particle filter – using map of location, (noisy) initial GPS estimate, (noisy) sensor and control data.
Safe navigation of a self-driving car around a virtual highway with other traffic. The car passes slower traffic whenever possible – driving within the speed, acceleration, and jerk limits.
Implementation of a PID controller for keeping the car on track by appropriately adjusting the steering angle and parameter tuning.
ROS nodes to implement core functionality of the autonomous vehicle system, including traffic light detection, control, and waypoint following.
Deep neural network built and trained to classify traffic signs, using TensorFlow.