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^.
For the solution, I implemented the following process:
In this step, the JSON message is parsed and converted in a instance of the Vehicle class, that contains all data of the ego vehicle, and also a list of the detected vehicles that are in the sensor fusion data. This instance is then given to the TrajectoryPlanner class, that implements the algorithms that will calculate the safest and most eficient trajectory path.
After the data from the simulator has been processed, the detected vehicles are sorted by lane, to make easier the calculation of the kinematics and costs of every potential trajectory. This is implemented by checking all possible lanes (the current lane, and the side lanes that the vehicle can switch to) for conditions that add to the cost of the kinematics of switching (or staying) in the analyzed lane. The cost (or score) of each lane starts at 0, and keeps adding up. The cost is calculated based on this metrics:
Since staying in the same lane is preferred to switch to other lanes, changing lane adds 10^3^ to the cost of the kinematics for that lane. This cost is relatively low, but is high enough to prevent switching lanes when there can be a ties.
Safety is the priority, and that is why the chance of a collision with other vehicle adds the highest cost to the kinematics of a lane, with a value of 10^5^. This makes the vehicle to change lanes as soon a slower vehicle is detected in the current lane. Also the distance of the slower vehicle to the ego vehicle is factored in the cost, to break ties and choose the lane with the safest distance to other vehicles.
currentKinematics.score += COST_COLLISION;
currentKinematics.score += collisionDistance / distanceToEgo * COST_COLLISION_DISTANCE;There is two types of collisions the planner can detect: collisions in the same lane, or collisions in another lanes. The collisions in the same lane occur when there's a vehicle going slowly in the current lane in a range from 0 to 30 meters. Collisions in other lanes are checked to verify if a lane change is possible; in the case, the collision distance with vehicles coming from the back is set to 10 meters. When a collision with a vehicle ahead is detected, the recommended speed of the motion is set to the speed of that vehicle.
This represents the cost of the distance of the vehicle that is the nearest to the ego vehicle (The bigger the distance, the lower the cost). This helps to break ties when there's more than one available lane to change, and to prevent that the ego vehicle goes to a lane that will encounter another slow car.
Here ego changes lane based in the best minimum nearest vehicle distance.
Once all the cost and stats for every lane has been calculated, the lane with the lower cost is selected to use as the parameters to generate the new trajectory.
The new trajectory is generated by using three points (separated by 30, 60 and 90 meters) and two points from the previous path of the vehicle, that are interpolated by using a spline (implemented by the spline library suggested). Then, using the spline, the planner will generate up to 50 trajectory waypoints, depending of the size of the points that are left from the previous path that the simulator hasn't processed yet.
The kinematics for the chosen lane will be used to the generation of the waypoints, first by changing the current lane to generate the points to set the spline, and then by adjusting the current speed (by means of changing acceleration), that will be used to generate the intermediate points for the trajectory of the car.
As a result of the implementation, the ego vehicle can travel around 10 miles without any incident (could be longer, my tests didn't go farther than that), always trying to keep the most safest and eficient trajectory, and trying to keep a speed close to the limit.
Here ego maintains speed during traffic, and changes lanes when the planner finds a lane with a better speed.
In this case, the ego vehicle chose the lane with less traffic. Notice how when it finds a slower vehicle after changing, checks for vehicles in other lanes to make a safe lane change.
A video of the whole run around the track can be watched here.
I think maybe the path could be smoother, maybe with the use of the JMT. In some cases, there's sudden lane changes, that are safe and in the jerk valid range, but they seem sudden:
I also found some cases where ego had some lane indecision (given that sometimes the traffic doesn't keep a constant velocity). Maybe this can be solved by analyzing previous states of the surrounding vehicles, and setting a range of speed that can be considered better.
In this project I didn't implement a finite state machine perse, so maybe this can help the next iteration of the planner to know what was the intention of the last motion. Also, the code could use some refactoring, in the form of using a decorator pattern to implement the different cost calculations.
Another improvement could be to pre-calculate most lane and detected vehicles statistics, which can help in implementing a better design of the architecture of the solution and reduce the overhead of multiple cycles on the list of lanes and vehicles.
Self-Driving Car Engineer Nanodegree Program
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).
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.
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 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.
-
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.
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 hearder file is really 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
We've purposefully kept editor configuration files out of this repo in order to keep it as simple and environment agnostic as possible. However, we recommend using the following settings:
- indent using spaces
- set tab width to 2 spaces (keeps the matrices in source code aligned)
Please (do your best to) stick to Google's C++ style guide.
Note: regardless of the changes you make, your project must be buildable using cmake and make!
Help your fellow students!
We decided to create Makefiles with cmake to keep this project as platform agnostic as possible. Similarly, we omitted IDE profiles in order to ensure that students don't feel pressured to use one IDE or another.
However! I'd love to help people get up and running with their IDEs of choice. If you've created a profile for an IDE that you think other students would appreciate, we'd love to have you add the requisite profile files and instructions to ide_profiles/. For example if you wanted to add a VS Code profile, you'd add:
- /ide_profiles/vscode/.vscode
- /ide_profiles/vscode/README.md
The README should explain what the profile does, how to take advantage of it, and how to install it.
Frankly, I've never been involved in a project with multiple IDE profiles before. I believe the best way to handle this would be to keep them out of the repo root to avoid clutter. My expectation is that most profiles will include instructions to copy files to a new location to get picked up by the IDE, but that's just a guess.
One last note here: regardless of the IDE used, every submitted project must still be compilable with cmake and make./
A well written README file can enhance your project and portfolio. Develop your abilities to create professional README files by completing this free course.