diff --git a/docs/intro_observationbuilder.rst b/docs/intro_observationbuilder.rst
index 65d0b6a43d363dbfa418e9c2f76013483c2df4b1..86631e3f455110996c84e0035871445b5280c83f 100644
--- a/docs/intro_observationbuilder.rst
+++ b/docs/intro_observationbuilder.rst
@@ -84,7 +84,8 @@ Note that this simple strategy fails when multiple agents are present, as each a
"""
def __init__(self):
super().__init__(max_depth=0)
- # We set max_depth=0 in because we only need to look at the current position of the agent to decide what direction is shortest.
+ # We set max_depth=0 in because we only need to look at the current
+ # position of the agent to decide what direction is shortest.
self.observation_space = [3]
def reset(self):
@@ -120,7 +121,8 @@ Note that this simple strategy fails when multiple agents are present, as each a
env = RailEnv(width=7,
height=7,
- rail_generator=complex_rail_generator(nr_start_goal=10, nr_extra=1, min_dist=8, max_dist=99999, seed=0),
+ rail_generator=complex_rail_generator(nr_start_goal=10, nr_extra=1, \
+ min_dist=8, max_dist=99999, seed=0),
number_of_agents=2,
obs_builder_object=SingleAgentNavigationObs())
@@ -154,3 +156,138 @@ navigation to target, and shows the path taken as an animation.
The code examples above appear in the example file `custom_observation_example.py <https://gitlab.aicrowd.com/flatland/flatland/blob/master/examples/custom_observation_example.py>`_. You can run it using :code:`python examples/custom_observation_example.py` from the root folder of the flatland repo. The two examples are run one after the other.
+Example 3 : Using custom predictors and rendering observation
+--------------
+
+Because the re-scheduling task of the Flatland-Challenge_ requires some short time planning we allow the possibility to use custom predictors that help predict upcoming conflicts and help agent solve them in a timely manner.
+In the **Flatland Environment** we included an initial predictor ShortestPathPredictorForRailEnv_ to give you an idea what you can do with these predictors.
+
+Any custom predictor can be passed to the observation builder and then be used to build the observation. In this example_ we illustrate how an observation builder can be used to detect conflicts using a predictor.
+
+The observation is incomplete as it only contains information about potential conflicts and has no feature about the agent objectives.
+
+In addition to using your custom predictor you can also make your custom observation ready for rendering. (This can be done in a similar way for your predictor).
+All you need to do in order to render your custom observation is to populate :code:`self.env.dev_obs_dict[handle]` for every agent (all handles). (For the predictor use :code:`self.env.dev_pred_dict[handle]`).
+
+In contrast to the previous examples we also implement the :code:`def get_many(self, handles=None)` function for this custom observation builder. The reasoning here is that we want to call the predictor only once per :code:`env.step()`. The base implementation of :code:`def get_many(self, handles=None)` will call the :code:`get(handle)` function for all handles, which mean that it normally does not need to be reimplemented, except for cases as the one below.
+
+.. _ShortestPathPredictorForRailEnv: https://gitlab.aicrowd.com/flatland/flatland/blob/master/flatland/envs/predictions.py#L81
+.. _example: https://gitlab.aicrowd.com/flatland/flatland/blob/master/examples/custom_observation_example.py#L110
+
+.. code-block:: python
+
+ class ObservePredictions(TreeObsForRailEnv):
+ """
+ We use the provided ShortestPathPredictor to illustrate the usage of predictors in your custom observation.
+
+ We derive our observation builder from TreeObsForRailEnv, to exploit the existing implementation to compute
+ the minimum distances from each grid node to each agent's target.
+
+ This is necessary so that we can pass the distance map to the ShortestPathPredictor
+
+ Here we also want to highlight how you can visualize your observation
+ """
+
+ def __init__(self, predictor):
+ super().__init__(max_depth=0)
+ self.observation_space = [10]
+ self.predictor = predictor
+
+ def reset(self):
+ # Recompute the distance map, if the environment has changed.
+ super().reset()
+
+ def get_many(self, handles=None):
+ '''
+ Because we do not want to call the predictor seperately for every agent we implement the get_many function
+ Here we can call the predictor just ones for all the agents and use the predictions to generate our observations
+ :param handles:
+ :return:
+ '''
+
+ self.predictions = self.predictor.get(custom_args={'distance_map': self.distance_map})
+
+ self.predicted_pos = {}
+ for t in range(len(self.predictions[0])):
+ pos_list = []
+ for a in handles:
+ pos_list.append(self.predictions[a][t][1:3])
+ # We transform (x,y) coodrinates to a single integer number for simpler comparison
+ self.predicted_pos.update({t: coordinate_to_position(self.env.width, pos_list)})
+ observations = {}
+
+ # Collect all the different observation for all the agents
+ for h in handles:
+ observations[h] = self.get(h)
+ return observations
+
+ def get(self, handle):
+ '''
+ Lets write a simple observation which just indicates whether or not the own predicted path
+ overlaps with other predicted paths at any time. This is useless for the task of navigation but might
+ help when looking for conflicts. A more complex implementation can be found in the TreeObsForRailEnv class
+
+ Each agent recieves an observation of length 10, where each element represents a prediction step and its value
+ is:
+ - 0 if no overlap is happening
+ - 1 where n i the number of other paths crossing the predicted cell
+
+ :param handle: handeled as an index of an agent
+ :return: Observation of handle
+ '''
+
+ observation = np.zeros(10)
+
+ # We are going to track what cells where considered while building the obervation and make them accesible
+ # For rendering
+
+ visited = set()
+ for _idx in range(10):
+ # Check if any of the other prediction overlap with agents own predictions
+ x_coord = self.predictions[handle][_idx][1]
+ y_coord = self.predictions[handle][_idx][2]
+
+ # We add every observed cell to the observation rendering
+ visited.add((x_coord, y_coord))
+ if self.predicted_pos[_idx][handle] in np.delete(self.predicted_pos[_idx], handle, 0):
+ # We detect if another agent is predicting to pass through the same cell at the same predicted time
+ observation[handle] = 1
+
+ # This variable will be access by the renderer to visualize the observation
+ self.env.dev_obs_dict[handle] = visited
+
+ return observation
+
+We can then use this new observation builder and the renderer to visualize the observation of each agent.
+
+
+.. code-block:: python
+
+ # Initiate the Predictor
+ CustomPredictor = ShortestPathPredictorForRailEnv(10)
+
+ # Pass the Predictor to the observation builder
+ CustomObsBuilder = ObservePredictions(CustomPredictor)
+
+ # Initiate Environment
+ env = RailEnv(width=10,
+ height=10,
+ rail_generator=complex_rail_generator(nr_start_goal=5, nr_extra=1, min_dist=8, max_dist=99999, seed=0),
+ number_of_agents=3,
+ obs_builder_object=CustomObsBuilder)
+
+ obs = env.reset()
+ env_renderer = RenderTool(env, gl="PILSVG")
+
+ # We render the initial step and show the obsered cells as colored boxes
+ env_renderer.render_env(show=True, frames=True, show_observations=True, show_predictions=False)
+
+ action_dict = {}
+ for step in range(100):
+ for a in range(env.get_num_agents()):
+ action = np.random.randint(0, 5)
+ action_dict[a] = action
+ obs, all_rewards, done, _ = env.step(action_dict)
+ print("Rewards: ", all_rewards, " [done=", done, "]")
+ env_renderer.render_env(show=True, frames=True, show_observations=True, show_predictions=False)
+ time.sleep(0.5)