I want to find the next moves of cars from the previous moves, but I could not figure out what should I use as an algorithm. Can you help me to find a way to solve this problem?

I have a lot of car data like below:

enter image description here

The data format is simple. Each car has a data file, which includes all moves which are performed in one second. The green box shows the starting point and the blue box shows the end point of the movements.

To be clearer, I can explain the Car1 data file content like this:

second, y, x
1        6  0
2        6  1
3        6  2
4        5  2
5        4  2
6        3  2
7        3  3
8        3  4
9        3  5
10       3  6

So what should I do to train a model with all these data and to find a result like below: green box shows the starting point, the red line shows the data which I have as test, the yellow line shows the data which I want to find as a result.

enter image description here

Please share your ideas with me.

  • $\begingroup$ I'm not sure if it makes sense to predict the next possible moves given the previous ones, if you want to get from the green to the blue box, especially when the green and blue boxes are placed randomly on the grid. Do you always know where the green and blue boxes are, even if you don't have the data? If yes, then you can solve this with reinforcement learning, but you need to define a reward function, which should not be too difficult in this case. $\endgroup$
    – nbro
    Jan 17 at 14:10


You must log in to answer this question.

Browse other questions tagged .