mithi/some-udacity-projects

Some of my projects as a former mentor, reviewer, and beta-tester of Robotics and Self-Driving Car ND

Some Udacity Projects

Robotics Nanodegree Term 2 Beta Test

• Adaptive Monte-Carlo Localization
• Robotics Inference

Intro to Self-Driving Car Review Submission

• Traffic Light Detector

Rover

• Perception and Mapping: a "search, sample, and return project" with a virtual rover.

Follow Me

• I used a fully-convolutional neural network to paint all pixels in an image which is part of a person. Two types of persons are identified, the “hero” target person, and everyone else.

Behavioral Cloning

• Cloning Driving Behavior with Keras and a Videogame-Like Simulator

Histogram Filter

• Localization using Histogram Filter Algorithm

Perception PR 2

• A catkin workspace in ROS where a virtual PR2 Robot with an RGBD camera perceives objects and places them on the appropriate dropbox.

Point Cloud Recognition

• A catkin workspace in ROS that capture features of objects and then train a classifier to correctly identify the objects from a point cloud file.

PID Toy

• A small collection of toys to demonstrate PID control concepts.

Related Projects

• Particle Filters and Kidnapped Vehicle Project
  • A particle-filter visualization in Python using Bokeh based on Udacity's free A.I. for Robotics course
  • A particle filter implementation to track a kidnapped robot.
• Inverse Kinematics Arm
  • An Inverse Kinematics 6DOF Robot Arm Pick and Place Project in ROS.
• Point Cloud Filter
  • Scripts showcasing filtering techniques applied to point cloud data.
• Point Cloud Clusters
  • A catkin workspace in ROS which uses DBSCAN to identify which points in a point cloud belong to the same object.
• Highway Path Planning
  • My path-planning pipeline to navigate a car safely around a virtual highway with other traffic.
• Model Predictive Control
  • A software pipeline using the Model Predictive Control method to drive a car around a virtual track.
• Semantic Segmentation
  • A Fully Convolutional Network (FCN) script to label the pixels of a road in images
• Traffic Sign Classification
  • A deep neural network to classify traffic signs, using TensorFlow.
• Unscented Kalman Filter
  • An unscented Kalman Filter implementation in C++ for fusing lidar and radar sensor measurements.
• Extended Kalman Filter
  • An extended Kalman Filter implementation in C++ for fusing lidar and radar sensor measurements.
• Vehicle Tracking
  • A vehicle detection and tracking pipeline with OpenCV, histogram of oriented gradients (HOG), and support vector machines (SVM).
• Advanced Lane Detection
  • An advanced lane-finding algorithm using distortion correction, image rectification, color transforms, and gradient thresholding.

some-udacity-projects's Issues

tf.python.control_flow_ops

tf.python.control_flow_ops is returning error : module 'tensorflow' has no attribute 'python'. I have updated the tensorflow.

Also, What will happen if I remove 'tf.python.control_flow_ops=tf'. The program runs when I remove the code.