Rescue People


 

The goal of this exercise is to program a drone to search and localize the position of lost people on the high seas.

 

To do this we must get to the estimate coordinates of the accident, then perform a coverage algorithm to explore the zone and, by recognizing the faces, count the number of people and where they are. Finally the drone must return to the boat to land.


First we need to transform the GPS coordinates to UTM. We used an online conversion tool that returned the following:

-Survivors : 430492m E, 4459162m N.

-Boat : 430532m E, 4459132m N.


So the position we must tell the drone to go to is -40m East and 30m North.


To cover the area where the accident occurred, the drone will describe a spiral movement and since there are no objects near we do not have to take care of the obstacle avoidance part. Each iteration the linear velocity and angle to face will increase to achieve this, the final trajectory will be similar to this outline:



Now for the face detection we will use the Haar-cascade detection from OpenCV. To detect the face despite of the camera orientation, the image will be rotated until a face is found or it returns to its original position. Then we obtain the coordinates in the world frame by detecting the center of the face, and applying a linear regression to get the global position.

To not detect a same face multiple times we get the euclidean position between the new position and each one already in the list. Then we set a threshold distance, and if is higher we add it to the list.



For the landing a simple control in position is used to return to the boat. A possible improvement to this behavior would be to add a color filter, but the results are pretty good without it too.

 

An execution of the program can be seen here:

 




Comments

Post a Comment

Popular posts from this blog

Local Navigation with VFF

Image
       The main objective of the local navigation in robotic systems is to get to a near target in the safest and most efficient way possible. One of the many algorithms to solve this problem is the Virtual Force Field , developed by Borenstein and Koren.       The fundaments of it are that every obstacle in the environment generates a repulsive force towards the robot and the target generates an attractive force in the robot. So, with this two facts in mind we can find the combination of both forces that will guide the robot to its destination similar to the next image:        For a simplification each object generates only                      one mayor force, instead of multiple repulsive forces.      Now, we want to make a reactive navigation system for a car with an  implementation of  this algorithm. Since the sensor we are usin...
Read more

Autoparking

Image
  We have to make a program that parks a car in a parallel disposition. To do so the car must follow a trajectory similar to the one in this image: On the hardware part, we can access three 2D lasers positioned on the front, right and rear of the car. We can also send linear and angular speed commands.   The software implementation is based on a finite-state machine architecture.The algorithm can be divided into four main states: -First we have to find a free space and advance some distance to have enough space to move in reverse.  -Secondly we move backwards and move the steering wheel in the same direction of the space where we want to park.  -Then we steer in the other direction while moving backwards.  -Finally, to relocate the car into a position in line with the other car we can advance forward or backwards while steering to one side or the other depending on the situation. To find a free space to park we check the right-side laser, until we find a positio...
Read more

Global Navigation with GPP

Image
  This time the objective is to create a plan or path to guide a robot to a distant location, specifically a taxi. To solve this the Gradient Path Planing (GPP) will be used. This algorithm gives us the shortest way to reach the target by calculating the descending gradient of a given grid, similar to this figure:     In our case the planing will be done with an ascending gradient instead of a descending one, but this will be explained later.        At first instance we need to be aware that the GPP method needs a metric grid map of the world, this means that the map will consist of diferent cells that will mantain some correlation with the real world distances between objects, fo example it could look like this:               Now that we have the map, we need to fill the cells to calculate the path. In the algorithm we are using the target will generate an expansive wave that will assign lower values...
Read more