Skip to content

Latest commit

 

History

History
74 lines (42 loc) · 4.75 KB

writeup_template.md

File metadata and controls

74 lines (42 loc) · 4.75 KB

Project: Search and Sample Return

Writeup Template: You can use this file as a template for your writeup if you want to submit it as a markdown file, but feel free to use some other method and submit a pdf if you prefer.

The goals / steps of this project are the following:

Training / Calibration

  • Download the simulator and take data in "Training Mode"
  • Test out the functions in the Jupyter Notebook provided
  • Add functions to detect obstacles and samples of interest (golden rocks)
  • Fill in the process_image() function with the appropriate image processing steps (perspective transform, color threshold etc.) to get from raw images to a map. The output_image you create in this step should demonstrate that your mapping pipeline works.
  • Use moviepy to process the images in your saved dataset with the process_image() function. Include the video you produce as part of your submission.

Autonomous Navigation / Mapping

  • Fill in the perception_step() function within the perception.py script with the appropriate image processing functions to create a map and update Rover() data (similar to what you did with process_image() in the notebook).
  • Fill in the decision_step() function within the decision.py script with conditional statements that take into consideration the outputs of the perception_step() in deciding how to issue throttle, brake and steering commands.
  • Iterate on your perception and decision function until your rover does a reasonable (need to define metric) job of navigating and mapping.

Rubric Points

Here I will consider the rubric points individually and describe how I addressed each point in my implementation.

Writeup / README

1. Provide a Writeup / README that includes all the rubric points and how you addressed each one. You can submit your writeup as markdown or pdf.

You're reading it!

Notebook Analysis

1. Run the functions provided in the notebook on test images (first with the test data provided, next on data you have recorded). Add/modify functions to allow for color selection of obstacles and rock samples.

I've recorded my own data and saved it locally, then extracted an image for an obstacle as shown below to calibrate if existing threshold is good for obstacles.

alt text

1. Populate the process_image() function with the appropriate analysis steps to map pixels identifying navigable terrain, obstacles and rock samples into a worldmap. Run process_image() on your test data using the moviepy functions provided to create video output of your result.

And another!

I've fillted the logic for process image. One issue I faced was with the indexing of the data and i had to subtract -1 to access the right instance. I had to convert float np arrays to int so it can work well with the map.

Autonomous Navigation and Mapping

1. Fill in the perception_step() (at the bottom of the perception.py script) and decision_step() (in decision.py) functions in the autonomous mapping scripts and an explanation is provided in the writeup of how and why these functions were modified as they were.

I've re-used most of the code I had in the process_image() in that method. However, I've added logic to make dilation for the images which increased the accuracy besides putting some constants for the map updates based on the pitch and roll values. For the decision and rover files, I did minor adjustments and added variables to improve the navigation.

2. Launching in autonomous mode your rover can navigate and map autonomously. Explain your results and how you might improve them in your writeup.

The rover is able to map 40%+ of the map with 60% accuracy as show in the image below

alt text

I've tried different approaches for detecting that the rover is stuck and it worked. However, there are improvements needed on how to effectively react to being stuck. Finally, the rover does not do wall crawling so it can be improved for that as well.

Note: running the simulator with different choices of resolution and graphics quality may produce different results, particularly on different machines! Make a note of your simulator settings (resolution and graphics quality set on launch) and frames per second (FPS output to terminal by drive_rover.py) in your writeup when you submit the project so your reviewer can reproduce your results.

My platform is macOS running the simulator with Good graphics and 1024x768 resolution