Self-Driving Car Engineer Nanodegree Program
DEVELOPMENT IS DESCRIBED BELLOW.
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).
To run the simulator on Mac/Linux, first make the binary file executable with the following command:
sudo chmod u+x {simulator_file_name}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 with 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.
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.
- Clone this repo.
- Make a build directory:
mkdir build && cd build - Compile:
cmake .. && make - Run it:
./path_planning.
Here is the data provided from the Simulator to the C++ Program
["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
//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
["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"] 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.
-
The car uses a perfect controller and will visit every (x,y) point it receives 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 receives 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.
-
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 it's 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.
A really helpful resource for doing this project and creating smooth trajectories was using http://kluge.in-chemnitz.de/opensource/spline/, the spline function is in a single header file and easy to use.
- 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
- uWebSockets
- Run either
install-mac.shorinstall-ubuntu.sh. - If you install from source, checkout to commit
e94b6e1, i.e.git clone https://github.com/uWebSockets/uWebSockets cd uWebSockets git checkout e94b6e1
- Run either
Feel free to use the Dockerfile to develop and run the program. The devcontainet.json file (inside .devcontainer) is included to help vscode development.
As the trajectory planner works on Frenet coordinates, an important step is to have a smooth function to project back from Frenet to cartesian. Two splines 1m apart are generated from the waypoints and their respective outward vector. From these two splines, one can interpolate and extrapolate the position of other in the Frenet coordinates. The resulting map prevents instantaneous velocity changes to happen because of a non-smooth cartesian projection.
All the necessary steps for path planning are included in the TrajectoryPlanners struct, they are behaviour planning (based on state), trajectory generation (different for forward and lateral movement) and trajectory selection (based on cost functions).
A simple but effective switch-case state machine is implemented on the select_state method. It uses the following rationale, one should always change to an adjacent line if it is faster and has enough clearance, forward speed should enable the tracking of the car in front when present and be the top speed otherwise.
The two steps of the state machine are as follows:
uint target_lane;
// Keep lane if it is the fastest
if (lane_speed[ergo_lane] >= lane_speed[(ergo_lane + 1) % 3] && lane_speed[ergo_lane] >= lane_speed[(ergo_lane + 2) % 3])
target_lane = ergo_lane;
// "State Machine" for lane selection
else switch (ergo_lane) {
case 0:
target_lane = lane_position[1] > t_tolerance * fwd.state.vel + fwd.state.pos ? 1 : 0;
break;
case 1:
target_lane = lane_speed[2] > lane_speed[0] ? 2 : 0;
target_lane = lane_position[target_lane] > t_tolerance * fwd.state.vel + fwd.state.pos ? target_lane : 1;
break;
case 2:
target_lane = lane_position[1] > t_tolerance * fwd.state.vel + fwd.state.pos ? 1 : 2;
break;
}The speed selection decays it exponentially as the car gets closer to another vehicle:
double ds = lane_position[target_lane] - fwd.state.pos;
ds = ds > 0 ? ds : 0;
fwd.target_speed = lane_speed[target_lane] * (1 - std::exp(-ds / 30));The forward movement is treated as a control problem where the setpoint is given by the behaviour layer. The linear control parameters were selected in a way to guarantee fast, but subcritical convergence and keep jerk and acceleration within bounds.
The lateral movement is an L2 jerk-minimizing quintic polynomial to the centre of the target line and final velocity and acceleration zero. A set of candidates with varying transition time is created and evaluated by the trajectory selection.
The final trajectory selected based on a cost function that balances: lateral jerk, centerline distance, centerline alignment, wobbling and safety. The final result is a trajectory that is not only comfortable and safe but intrinsically fast.
