refactor of experiment suite name

Docs/benchmark_creating.md

@@ -4,25 +4,29 @@ Benchmarking your Agent
 ![Benchmark_structure](img/benchmark_diagram_small.png )
 
 The driving benchmark is associated with other two modules.
-The *agent* module, a controller which performs in a
+The *agent* module, a controller which performs in 
 another module, the *experiment suite*.
 Both modules are abstract classes that must be redefined by
 the user.
 
 The following code excerpt is
-an example of how to apply a driving benchmark
+an example of how to apply a driving benchmark;
 
     agent = ForwardAgent() 
-    experiment_suite = Basic()
+    experiment_suite = BasicExperiments()
     benchmark = DrivingBenchmark() 
-    benchmark_summary = benchmark.benchmark_agent(experiment_suite, agent, client)
+    performance_metrics_summary = benchmark.benchmark_agent(experiment_suite, agent, client)
 
 
 Following this excerpt, there are two classes to be defined.
-The ForwardAgent() and the BasicSuite().
-In this tutorial we are going to show how to create 
-a basic experiment suite  and a trivial forward going agent.
+The ForwardAgent() and the BasicExperiments().
+After that, we instantiate the driving benchmark with default parameters
+and execute it. As a result of the execution, the driving benchmark
+returns a summary of the calculated [performance metrics](benchmark_metrics.md).
 
+In this tutorial we are going to show how to define 
+a basic experiment suite and a trivial agent with a going
+forward policy.
 
 
 #### Defining the Agent
@@ -36,8 +40,8 @@ Lets start by deriving a simple Forward agent.
     class ForwardAgent(Agent):
 
 
-To have its performance evaluated, the Forward derived class _must_ redefine the *run_step* 
-function as it is done in the following excerpt:
+To have its performance evaluated, the ForwardAgent derived class _must_ 
+redefine the *run_step* function as it is done in the following excerpt:
 
     def run_step(self, measurements, sensor_data, directions, target):
         """
@@ -53,13 +57,14 @@ This function receives the following parameters:
  * [Measurements](measurements.md): the entire state of the world received
  by the client from the CARLA Simulator. These measurements contains agent position, orientation,
  dynamic objects information, etc.
- * [Sensor Data](cameras_and_sensors.md): The measured data from defined sensors, such as Lidars or RGB cameras.
+ * [Sensor Data](cameras_and_sensors.md): The measured data from defined sensors, 
+ such as Lidars or RGB cameras.
  * Directions: Information from the high level planner. Currently the planner sends
  a high level command from the set: STRAIGHT, RIGHT, LEFT, NOTHING.
  * Target Position: The position and orientation of the target.
  
  With all this information, the *run_step* function is expected 
- to return a [control message]() containing, 
+ to return a [vehicle control message](measurements.md) containing, 
  steering value, throttle value, brake value, etc.
 
 
@@ -95,7 +100,7 @@ as in the following code.
 
 The user must select the weathers to be used. One should select the set
 of test weathers and the set of train weathers. This is defined as a
-class property as in the following example.
+class property as in the following example:
 
     @property
     def train_weathers(self):
@@ -108,13 +113,13 @@ class property as in the following example.
 ##### Building Experiments
 
 The [experiments are composed by a *task* that is defined by a set of *poses*](benchmark_structure.md).
-Lets start by selecting poses for one of the cities, Town01.
+Lets start by selecting poses for one of the cities, Town01 for instance.
  First of all, we need to see all the possible positions, for that, with
   a CARLA simulator running in a terminal, run:
     
     python view_start_positions.py
  
- ![town01_positions](img/welcome.png)
+ ![town01_positions](img/town01_positions.png)
  
   
   
@@ -132,7 +137,7 @@ Figure 3, shows these defined poses for both carla towns.
 
 
  ![town01_positions](img/initial_positions.png)
- >Figure 3: The poses used on this basic *Experimental Suite* example. Poses are
+ >Figure 3: The poses used on this basic *Experiment Suite* example. Poses are
  a tuple of start and end position of a goal-directed episode. Start positions are
  shown in Blue, end positions in Red. Left: Straight poses,
  where the goal is just straight away from the start position. Middle: One turn
@@ -157,7 +162,7 @@ vector as we show in the following code excerpt:
 
 ```
 experiments_vector = []
-    for weather in self.weathers:
+    for weather in used_weathers:
 
         for iteration in range(len(poses_tasks)):
             poses = poses_tasks[iteration]

Docs/benchmark_metrics.md

@@ -2,11 +2,20 @@
 Driving Benchmark Performance Metrics
 ------------------------------
 
+This page explains the performance metrics module.
+Use to compute a summary of results based on the agent
+actions when completing  the experiments.
 
 
-The benchmark module provides the following performance metrics, which 
-are related to infraction:
+### Provided performance metrics
 
+The driving benchmark performance metrics module provides the following performance metrics:
+
+* Percentage of Success: The percentage of episodes (poses from tasks),
+that the agent successfully completed.
+
+* Average Completion: The average distance towards the goal that the 
+agent was able to travel.
 
 * Off Road Intersection: The number of times the agent goes out of the road. 
  The intersection is only counted if the area of the vehicle outside
@@ -26,16 +35,21 @@ are related to infraction:
 objects with an impact bigger than a *threshold*.
 
 
-These results can be computed with the metrics module, by using the following
-code excerpt:
+### Executing and Setting Parameters
+
+The metrics are computed as the final step of the benchmark
+and it is returned by the [benchmark_agent()](benchmark_creating.md).
+Internally it is executed as follows:
 
     metrics_object = Metrics(metrics_parameters)
     summary_dictionary = metrics_object.compute(path_to_execution_log)
 
-The class is instanced with a dictionary of parameters. 
-These parameters could be changed by changing 
-The function receives the full path to the execution log and a dictionary with
-parameters. It returns a dictionary with the metrics.
+The performance metric compute function
+receives the full path to the execution log 
+and dictionary with the performance metrics.
+
+Also, the metric class is instanced with the metric parameters.
+
 
 The parameters are:
 * Threshold: The threshold used by the metrics.
@@ -44,20 +58,43 @@ The parameters are:
 of frames that the agent needs to keep doing the infraction for
 it to be counted as another infraction. 
 
-*Frames Skip: It is related to the number of frames that are
+* Frames Skip: It is related to the number of frames that are
 skipped after a collision or a intersection starts.
 
+These parameters are defined as property of the *Experiment Suite*
+base class and can be redefined at your 
+[custom *Experiment Suite*](benchmark_creating.md/#defining-the-experiment-suite).
+
+The default defined parameters are: 
 
 
-On your experiment suite class definition you could also
-redefine the metrics experiment.
+    @property
+        def metrics_parameters(self):
+        """
+        Property to return the parameters for the metric module
+        Could be redefined depending on the needs of the user.
+        """
+        return {
 
+            'intersection_offroad': {'frames_skip': 10,
+                                     'frames_recount': 20,
+                                     'threshold': 0.3
+                                     },
+            'intersection_otherlane': {'frames_skip': 10,
+                                       'frames_recount': 20,
+                                       'threshold': 0.4
+                                       },
+            'collision_other': {'frames_skip': 10,
+                                'frames_recount': 20,
+                                'threshold': 400
+                                },
+            'collision_vehicles': {'frames_skip': 10,
+                                   'frames_recount': 30,
+                                   'threshold': 400
+                                   },
+            'collision_pedestrians': {'frames_skip': 5,
+                                      'frames_recount': 100,
+                                      'threshold': 300
+                                      },
 
-####Benchmark Execution
-
-
-During the execution the benchmark module stores
-the [measurements](measurements.md)  and
- [controls](measurements.md) for every single step.
- These results are stored on the *_benchmarks_results*
- folder.
+              }

Docs/benchmark_start.md

@@ -51,7 +51,8 @@ Run the help command to see options available.
 
 
 When running the driving benchmark for the basic configuration
-you should [expect the following results](benchmark_creating.md/#expected-results).
+you should [expect the following results](benchmark_creating.md/#expected-results)
+to be printed on the terminal.
 
 
 

PythonClient/carla/driving_benchmark/experiment_suite/__init__.py

@@ -1,2 +1,2 @@
-from .basic import Basic
+from .basic_experiment_suite import BasicExperimentSuite
 from .corl_2017 import CoRL2017

PythonClient/carla/driving_benchmark/experiment_suite/basic_experiment_suite.py

@@ -14,7 +14,7 @@ from carla.settings import CarlaSettings
 from .experiment_suite import ExperimentSuite
 
 
-class Basic(ExperimentSuite):
+class BasicExperimentSuite(ExperimentSuite):
 
     @property
     def train_weathers(self):

PythonClient/driving_benchmark_example.py

@@ -11,7 +11,7 @@ import logging
 
 from carla.driving_benchmark import run_driving_benchmark
 from carla.driving_benchmark.experiment_suite import CoRL2017
-from carla.driving_benchmark.experiment_suite import Basic
+from carla.driving_benchmark.experiment_suite import BasicExperimentSuite
 from carla.agent import ForwardAgent
 
 
@@ -85,7 +85,7 @@ if __name__ == '__main__':
     else:
         print ' WARNING: running the basic driving benchmark, to run the CORL 2017, you should run' \
               ' python driving_benchmark_example.py --corld-2017'
-        experiment_suite = Basic(args.city_name)
+        experiment_suite = BasicExperimentSuite(args.city_name)
 
     # Now actually run the driving_benchmark
     run_driving_benchmark(agent, experiment_suite, args.city_name,

PythonClient/test/acceptance_tests/test_benchmark_module.py

@@ -18,7 +18,7 @@ import unittest
 
 from carla.agent.agent import Agent
 
-from carla.driving_benchmark.experiment_suite.basic import Basic
+from carla.driving_benchmark.experiment_suite.basic_experiment_suite import BasicExperimentSuite
 
 from carla.client import make_carla_client, VehicleControl
 from carla.tcp import TCPConnectionError

PythonClient/test/unit_tests/test_experiment_suite.py

@@ -1,7 +1,7 @@
 import unittest
 from carla.driving_benchmark.experiment_suite.experiment_suite import ExperimentSuite
 
-from carla.driving_benchmark.experiment_suite.basic import Basic
+from carla.driving_benchmark.experiment_suite.basic_experiment_suite import BasicExperimentSuite
 
 from carla.driving_benchmark.experiment_suite.corl_2017 import CoRL2017