cdthompson / deepracer-k1999-race-lines

Race-line calculation of a DeepRacer track

Discovering Race Lines in DeepRacer Track Geometries

The AWS DeepRacer Virtual Circuit is run every month and uses reinforcement learning to teach a car to successfully navigate a race track.

Rewards functions are developed by each competitor in order to guide the learning, and these functions can vary widely. One of the experiments I wanted to try was to be overly prescriptive to the car.

Source and Result

Original Track	Calculated Race Line	Numpy coordinates
		NumPy: Canada_Training Python Code: Canada_Training.py
		NumPy: reinvent_base.npy Python Code: reinvent_base.py
		NumPy: reinvent2019.npy Python Code: reinvent2019.py

Method

Borrowed directly from Rémi Coulom's PhD Thesis:

The code was hastily written but achieved a good enough result, so I stopped improving it. One limitation is that the points along the race line will never migrate in the opposite direction of curvature, leaving some room for further straightening of the race line.

deepracer-k1999-race-lines's Issues

Error when running the /deepracer-k1999-race-lines/Race-Line-Calculation.ipynb

---

ValueError Traceback (most recent call last)
Cell In[8], line 14
12 l_inner_border = LineString(inner_border)
13 l_outer_border = LineString(outer_border)
---> 14 road_poly = Polygon(np.vstack((l_outer_border, np.flipud(l_inner_border))))
15 print("Is loop/ring? ", l_center_line.is_ring)
16 road_poly

File <array_function internals>:200, in flipud(*args, **kwargs)

File ~/.local/lib/python3.10/site-packages/numpy/lib/twodim_base.py:154, in flipud(m)
152 m = asanyarray(m)
153 if m.ndim < 1:
--> 154 raise ValueError("Input must be >= 1-d.")
155 return m[::-1, ...]

ValueError: Input must be >= 1-d.

Error keeps arising while trying to run Load the track to analyze

ValueError Traceback (most recent call last)
Cell In[13], line 14
12 l_inner_border = LineString(inner_border)
13 l_outer_border = LineString(outer_border)
---> 14 road_poly = Polygon(np.vstack((l_outer_border, np.flipud(l_inner_border))))
15 print("Is loop/ring? ", l_center_line.is_ring)
16 road_poly

File <array_function internals>:200, in flipud(*args, **kwargs)

File /usr/local/lib/python3.11/site-packages/numpy/lib/twodim_base.py:154, in flipud(m)
152 m = asanyarray(m)
153 if m.ndim < 1:
--> 154 raise ValueError("Input must be >= 1-d.")
155 return m[::-1, ...]

ValueError: Input must be >= 1-d.

how to generate the .npy file from .world file?

I find that the AWS provide .world file , but how to get the .npy file for the new tracks?

eg. the track Championship Cup Warm-up 2019

thanks