Path Planning

Part of the Self-Driving Car nanodegree. Starter code and data from Udacity.

Build

• #> git submodule update --init --recursive
• #> mkdir build && cd build && cmake .. && make

Run

• #> ./PathPlanner

Reflection

Behaviour planning

The behaviour planner can be found in behaviour.hpp. It's moddeled as a finite state machine, currently only dealing with 4 states:

• INIT: start state
• KEEP_LANE: Stay in the current lane and adapt to any vehicle in the path
• CHANGE_LANE_LEFT: Change to the lane to the left, taking into account any traffic there
• CHANGE_LANE_RIGHT: same, but to the right.

To choose which state is next, first we decide if the previous action is actually completed. Next every possible successor state is assigned a cost if feasible at all and then the costs are weighed. The cost functions can be found in cost.hpp.

To ensure reasonable behaviour without spending hours watching the simulator, a set of tests were added here behaviour.test.cpp.

Trajectory generation

For the trajectory generation, we rely on spline interpolation to create a smooth path. The trajectory generation code may be found in trajectory.hpp.

To derive a new trajectory we first establish a reference state, either by using 2 points from the previous, unconsumed, part of the path or by taking the ego position and yaw and generating an artificial previous path.

With this reference state we create a coarse set of way points, adding 3 more points that either follow the current lane or transition into the required lane if lane switching.

The way points are then transformed into a local coordinate space, offset from the reference coordinate (either the ego position or the end of the included path from last iteration). The coordinate conversion is encapsulated in coordinates.hpp.

The set of next points in the trajectory is then started of with 2 points from the previous path to ensure a smooth transition. I opted not to included the full set of points from the previous path to ensure a quick reaction to new situations.

The continuation of the trajectory is generated by specifying a target distance and creating points a regular interval. The distance between these points is carefully controlled to ensure the car's acceleration and jerk meet the desired target and restrictions. The points are at the same time converted back to the global coordinate space

Simulator.

You can download the Term3 Simulator which contains the Path Planning Project from the [releases tab (https://github.com/udacity/self-driving-car-sim/releases/tag/T3_v1.2).

Goals

In this project your goal is to safely navigate around a virtual highway with other traffic that is driving +-10 MPH of the 50 MPH speed limit. You will be provided the car's localization and sensor fusion data, there is also a sparse map list of waypoints around the highway. The car should try to go as close as possible to the 50 MPH speed limit, which means passing slower traffic when possible, note that other cars will try to change lanes too. The car should avoid hitting other cars at all cost as well as driving inside of the marked road lanes at all times, unless going from one lane to another. The car should be able to make one complete loop around the 6946m highway. Since the car is trying to go 50 MPH, it should take a little over 5 minutes to complete 1 loop. Also the car should not experience total acceleration over 10 m/s^2 and jerk that is greater than 10 m/s^3.

The map of the highway is in data/highway_map.txt

Each waypoint in the list contains [x,y,s,dx,dy] values. x and y are the waypoint's map coordinate position, the s value is the distance along the road to get to that waypoint in meters, the dx and dy values define the unit normal vector pointing outward of the highway loop.

The highway's waypoints loop around so the frenet s value, distance along the road, goes from 0 to 6945.554.

Here is the data provided from the Simulator to the C++ Program

Main car's localization Data (No Noise)

• ["x"] The car's x position in map coordinates
• ["y"] The car's y position in map coordinates
• ["s"] The car's s position in frenet coordinates
• ["d"] The car's d position in frenet coordinates
• ["yaw"] The car's yaw angle in the map
• ["speed"] The car's speed in MPH

Previous path data given to the Planner

Note: Return the previous list but with processed points removed, can be a nice tool to show how far along the path has processed since last time.

• ["previous_path_x"] The previous list of x points previously given to the simulator
• ["previous_path_y"] The previous list of y points previously given to the simulator

Previous path's end s and d values

• ["end_path_s"] The previous list's last point's frenet s value
• ["end_path_d"] The previous list's last point's frenet d value

Sensor Fusion Data, a list of all other car's attributes on the same side of the road. (No Noise)

["sensor_fusion"] A 2d vector of cars and then that car's

• car's unique ID,
• car's x position in map coordinates,
• car's y position in map coordinates,
• car's x velocity in m/s,
• car's y velocity in m/s,
• car's s position in frenet coordinates,
• car's d position in frenet coordinates.

Details

1. The car uses a perfect controller and will visit every (x,y) point it recieves in the list every .02 seconds. The units for the (x,y) points are in meters and the spacing of the points determines the speed of the car. The vector going from a point to the next point in the list dictates the angle of the car. Acceleration both in the tangential and normal directions is measured along with the jerk, the rate of change of total Acceleration. The (x,y) point paths that the planner recieves should not have a total acceleration that goes over 10 m/s^2, also the jerk should not go over 50 m/s^3. (NOTE: As this is BETA, these requirements might change. Also currently jerk is over a .02 second interval, it would probably be better to average total acceleration over 1 second and measure jerk from that.
2. There will be some latency between the simulator running and the path planner returning a path, with optimized code usually its not very long maybe just 1-3 time steps. During this delay the simulator will continue using points that it was last given, because of this its a good idea to store the last points you have used so you can have a smooth transition. previous_path_x, and previous_path_y can be helpful for this transition since they show the last points given to the simulator controller with the processed points already removed. You would either return a path that extends this previous path or make sure to create a new path that has a smooth transition with this last path.

Dependencies

• cmake >= 3.5
  • All OSes: click here for installation instructions
• make >= 4.1
  • Linux: make is installed by default on most Linux distros
  • Mac: install Xcode command line tools to get make
  • Windows: Click here for installation instructions
• gcc/g++ >= 5.4
  • Linux: gcc / g++ is installed by default on most Linux distros
  • Mac: same deal as make - [install Xcode command line tools]((https://developer.apple.com/xcode/features/)
  • Windows: recommend using MinGW