Merge pull request #96 from diyjac/diyjac

merge changes in `diyjac` branch into `master` for release.

README.md

@@ -1,10 +1,12 @@
 ## Udacity Self Driving Car Nanodegree Final Project: System Integration
 
+![Carla](./imgs/Carla.png)
+
 This is Team Vulture project repo for the final project of the Udacity Self-Driving Car Nanodegree: Programming a Real Self-Driving Car. The project will require the use of Ubuntu Linux (the operating system of Carla) and a new simulator with integration with the Robotic Operation System or ROS.  This project will restrict the driving speed of Carla to ~ 10 MPH for field testing.
 
 NOTE: You will find our development, testing logs and __SAFETY NOTES__ in the [REPORT.md](./REPORT.md) file.
 
-__WARNING:__ *To maintain integrity of the SDCND Final System Integration Project, the throttle and brake actuation settings in this prepository are __NOT__ what were used in the successful navigation of Carla around the test track, and the final successful resulting rosbag URL has been __redacted__.  The last Udacity Capstone Project repository merge pulled into this github repository was on September 9, 2017: [https://github.com/udacity/CarND-Capstone/commit/140691dada1e659422693007eee48c6d5faca14f](https://github.com/udacity/CarND-Capstone/commit/140691dada1e659422693007eee48c6d5faca14f).  Further merges with upstream repository may render the project in this repository inoperable.  The final project results are now __static__, and no further update requests will be expected nor entertained.*
+__WARNING:__ *To maintain integrity of the SDCND Final System Integration Project, the throttle and brake actuation settings in this prepository are __NOT__ what were used in the successful navigation of Carla around the test track.  The last Udacity Capstone Project repository merge pulled into this github repository was on September 9, 2017: [https://github.com/udacity/CarND-Capstone/commit/140691dada1e659422693007eee48c6d5faca14f](https://github.com/udacity/CarND-Capstone/commit/140691dada1e659422693007eee48c6d5faca14f).  Further merges with upstream repository may render the project in this repository inoperable.  The final project results are now __static__, and no further update requests will be expected nor entertained.*
 
 
 ### The Team
@@ -190,22 +192,6 @@ rosrun tools autoTLDataCollector.py mysamples/session1
 ```
 ![./imgs/sdc-sysint-auto-data-collector.gif](./imgs/sdc-sysint-auto-data-collector.gif)
 
-The ROS Graph was updated as follows
-
-![./imgs/updated_ROS_graph.png](./imgs/updated_ROS_graph.png)
-
-as we were informed by Udacity
-
-![./imgs/info-Udacity-ros-graph.png](./imgs/info-Udacity-ros-graph.png)
-
-that the obstacle node is currently not implemented in the simulator.
-
-12. We did a complete analysis of the two Udacity sample Rosbags using the following Jupyter Notebook: [tools/data_visualization.ipynb](./tools/data_visualization.ipynb)
-
-SDC System Integration Carla Test Course Waypoints and Map from rosbag sample:
-
-![./imgs/udacity-test-course-waypoint-map-from-rosbag.png](./imgs/udacity-test-course-waypoint-map-from-rosbag.png)
-
 ### Real world testing
 1. Download [training bag](https://drive.google.com/file/d/0B2_h37bMVw3iYkdJTlRSUlJIamM/view?usp=sharing) that was recorded on the Udacity self-driving car
 2. Unzip the file

REPORT.md

@@ -129,8 +129,49 @@ This is a separate report that can be viewed here: [classifier/readme.md](./clas
 
 #### 3.4 Traffic Light Detector
 We updated the traffic light detector so as to make it not retrieve camera images until it is within 40 meters of a traffic light.  Otherwise, it would unregister from the /raw_camera topic, and only resubscribe when it gets within range.
-
 #### 3.5 Last Waypoint Behavior
 As requested by Udacity, the system will stop Carla at the last waypoint, as shown below:
 
 ![./imgs/last_waypoint.jpg](./imgs/last_waypoint.jpg)
+
+### 4 Obstacle Waypoints
+The ROS Graph was updated as follows
+
+![./imgs/updated_ROS_graph.png](./imgs/updated_ROS_graph.png)
+
+as we were informed by Udacity
+
+![./imgs/info-Udacity-ros-graph.png](./imgs/info-Udacity-ros-graph.png)
+
+that the obstacle node is currently not implemented in the simulator.
+
+### 5 Simulator Integration Testing
+
+We tested this configuration in the Simulator at 40kmph and 10mph speed settings.  You may watch our simulator test videos below:
+
+##### 40kmph Simulator Test
+
+[![Team Vulture Simulator Test at 40kmph](./imgs/40kmph-simulator-test.png)](https://youtu.be/Znhn1LKZFEY)
+
+##### 10mph Simulator Test at 2X speed
+
+[![Team Vulture Simulator Test at 10mph](./imgs/10mph-simulator-test.png)](https://youtu.be/Xgm4EDbJgq0)
+
+
+### 6 Site Testing
+
+Our first site testing was not completely satisficatory.  Our throttle setting was set too high and made Carla very hard to control as can be seen in  our first attempt to make Carla move:
+
+[![Team Vulture First to Move Carla!](./imgs/vulture-first-udacity-sdc-team-to-move-carla.png)](https://www.youtube.com/watch?v=MfNFXf6fuzk)
+
+[![Team Vulture First to Move Carla! - Front Camera](./imgs/vulture-test.png)](https://youtu.be/1TjhlsXzrqU)
+
+In addition, we use the given site waypoints `churchlot_with_cars.csv` which made a counter-clockwise loop around the test track instead of clockwise as recorded in the sample rosbag:
+
+[![Team Vulture following original `churchlot_with_cars.csv` waypoints](./imgs/vulture_loop_speed_adjusted.png)](https://youtu.be/e5UM0yUBtao)
+
+We did a complete analysis of the two Udacity rosbags using the following Jupyter Notebook: [tools/data_visualization.ipynb](./tools/data_visualization.ipynb)
+
+SDC System Integration Carla Test Course Waypoints and Map from rosbag sample:
+
+![./imgs/udacity-test-course-waypoint-map-from-rosbag.png](./imgs/udacity-test-course-waypoint-map-from-rosbag.png)

classifier/readme.md

@@ -272,7 +272,7 @@ This behavior resulted in not following this approach further.
 Applying a [color classifier](https://github.com/algolia/color-extractor) from github just detected a lot of black and grey and no prominent green or red in the images of the dataset nr. 1.3. This approach has not been followed further.
 
 
-## 2.4 GAN
+## 2.4 Generative Adversarial Network (GAN)
 
 ![GAN Simulator Accuracy](../imgs/GAN-sim-accuracy.png)