Merge pull request #145 from inverted-ai/develop

Develop

README.md

@@ -1,7 +1,7 @@
 [pypi-badge]: https://badge.fury.io/py/invertedai.svg
 [pypi-link]: https://pypi.org/project/invertedai/
 [colab-badge]: https://colab.research.google.com/assets/colab-badge.svg
-[colab-link]: https://colab.research.google.com/github/inverted-ai/invertedai/blob/develop/examples/IAI_demo.ipynb
+[colab-link]: https://colab.research.google.com/github/inverted-ai/invertedai/blob/develop/examples/IAI_full_demo.ipynb
 [rest-link]: https://app.swaggerhub.com/apis-docs/InvertedAI/InvertedAI
 [examples-link]: https://github.com/inverted-ai/invertedai/tree/master/examples
 
@@ -41,13 +41,14 @@ so you can also download it and build locally.
 
 ``` python
 import numpy as np
-import imageio
+import matplotlib.pyplot as plt
 import invertedai as iai
 
-location = "canada:vancouver:drake_street_and_pacific_blvd"  # select one of available locations
+location = "iai:drake_street_and_pacific_blvd"  # select one of available locations
 
 iai.add_apikey('')  # specify your key here or through the IAI_API_KEY variable
 
+print("Begin initialization.")
 # get static information about a given location including map in osm
 # format and list traffic lights with their IDs and locations.
 location_info_response = iai.location_info(location=location)
@@ -64,7 +65,18 @@ response = iai.initialize(
 )
 agent_attributes = response.agent_attributes  # get dimension and other attributes of NPCs
 
-images = [response.birdview.decode()]  # images storing visualizations of subsequent states
+location_info_response = iai.location_info(location=location)
+rendered_static_map = location_info_response.birdview_image.decode()
+scene_plotter = iai.utils.ScenePlotter(rendered_static_map,
+                                       location_info_response.map_fov,
+                                       (location_info_response.map_center.x, location_info_response.map_center.y),
+                                       location_info_response.static_actors)
+scene_plotter.initialize_recording(
+    agent_states=response.agent_states,
+    agent_attributes=agent_attributes,
+)
+
+print("Begin stepping through simulation.")
 for _ in range(100):  # how many simulation steps to execute (10 steps is 1 second)
 
     # get next traffic light state
@@ -80,11 +92,21 @@ for _ in range(100):  # how many simulation steps to execute (10 steps is 1 seco
         traffic_lights_states=light_response.traffic_lights_states,
     )
 
-    # save the visualization - requires np and cv2
-    images.append(response.birdview.decode())
+    # save the visualization
+    scene_plotter.record_step(response.agent_states,light_response.traffic_lights_states)
 
+print("Simulation finished, save visualization.")
 # save the visualization to disk
-imageio.mimsave("iai-example.gif", np.array(images), format="GIF-PIL")
+fig, ax = plt.subplots(constrained_layout=True, figsize=(50, 50))
+gif_name = 'minimal_example.gif'
+scene_plotter.animate_scene(
+    output_name=gif_name,
+    ax=ax,
+    direction_vec=False,
+    velocity_vec=False,
+    plot_frame_number=True
+)
+print("Done")
 
 ```
 
@@ -96,17 +118,18 @@ your machine and the NPC engine running on Inverted AI servers. The basic integr
 ```python
 from typing import List
 import numpy as np
-import imageio
 import invertedai as iai
+import matplotlib.pyplot as plt
 
-# iai.add_apikey('')  # specify your key here or through the IAI_API_KEY variable
+iai.add_apikey('')  # specify your key here or through the IAI_API_KEY variable
 
 
 class LocalSimulator:
     """
     Mock up of a local simulator, where you control the ego vehicle. This example only supports single ego vehicle.
     """
-    def __init__(self, ego_state: iai.AgentState, npc_states: List[iai.AgentState]):
+
+    def __init__(self, ego_state: iai.common.AgentState, npc_states: List[iai.common.AgentState]):
         self.ego_state = ego_state
         self.npc_states = npc_states
 
@@ -119,8 +142,8 @@ class LocalSimulator:
         dx = self.ego_state.speed * dt * np.cos(self.ego_state.orientation)
         dy = self.ego_state.speed * dt * np.sin(self.ego_state.orientation)
 
-        self.ego_state = iai.AgentState(
-            center=iai.Point(x=self.ego_state.center.x + dx, y=self.ego_state.center.y + dy),
+        self.ego_state = iai.common.AgentState(
+            center=iai.common.Point(x=self.ego_state.center.x + dx, y=self.ego_state.center.y + dy),
             orientation=self.ego_state.orientation,
             speed=self.ego_state.speed,
         )
@@ -130,32 +153,56 @@ class LocalSimulator:
         self.npc_states = predicted_npc_states
         return self.ego_state
 
-
+print("Begin initialization.")
+location = 'iai:ubc_roundabout'
 iai_simulation = iai.BasicCosimulation(  # instantiate a stateful wrapper for Inverted AI API
-    location='canada:vancouver:ubc_roundabout',  # select one of available locations
+    location=location,  # select one of available locations
     agent_count=5,  # how many vehicles in total to use in the simulation
     ego_agent_mask=[True, False, False, False, False],  # first vehicle is ego, rest are NPCs
-    get_birdview=True,  # provides simple visualization - don't use in production
+    get_birdview=False,  # provides simple visualization - don't use in production
     traffic_lights=True,  # gets the traffic light states and used for initialization and steping the simulation
 )
+
+location_info_response = iai.location_info(location=location)
+rendered_static_map = location_info_response.birdview_image.decode()
+scene_plotter = iai.utils.ScenePlotter(rendered_static_map,
+                                       location_info_response.map_fov,
+                                       (location_info_response.map_center.x, location_info_response.map_center.y),
+                                       location_info_response.static_actors)
+scene_plotter.initialize_recording(
+    agent_states=iai_simulation.agent_states,
+    agent_attributes=iai_simulation.agent_attributes,
+)
+
+print("Begin stepping through simulation.")
 local_simulation = LocalSimulator(iai_simulation.ego_states[0], iai_simulation.npc_states)
-images = [iai_simulation.birdview.decode()]  # images storing visualizations of subsequent states
 for _ in range(100):  # how many simulation steps to execute (10 steps is 1 second)
     # query the API for subsequent NPC predictions, informing it how the ego vehicle acted
     iai_simulation.step([local_simulation.ego_state])
     # collect predictions for the next time step
     predicted_npc_behavior = iai_simulation.npc_states
     # execute predictions in your simulator, using your actions for the ego vehicle
     updated_ego_agent_state = local_simulation.step(predicted_npc_behavior)
-    # save the visualization - requires np and cv2
-    images.append(iai_simulation.birdview.decode())
+    # save the visualization with ScenePlotter
+    scene_plotter.record_step(iai_simulation.agent_states)
+
+print("Simulation finished, save visualization.")
 # save the visualization to disk
-imageio.mimsave("iai-example.gif", np.array(images), format="GIF-PIL")
+fig, ax = plt.subplots(constrained_layout=True, figsize=(50, 50))
+gif_name = 'cosimulation_minimal_example.gif'
+scene_plotter.animate_scene(
+    output_name=gif_name,
+    ax=ax,
+    direction_vec=False,
+    velocity_vec=False,
+    plot_frame_number=True
+)
+print("Done")
 
 ```
 To quickly check out how Inverted AI NPCs
 behave, try our
-[Colab](https://colab.research.google.com/github/inverted-ai/invertedai-drive/blob/develop/examples/npc_only_colab.ipynb),
+[Colab](https://colab.research.google.com/github/inverted-ai/invertedai-drive/blob/develop/examples/IAI_full_demo.ipynb),
 where all agents are NPCs, or go to our
 [github repository](https://github.com/inverted-ai/invertedai/tree/master/examples) to execute it locally.
 When you're ready to try our NPCs with a real simulator, see the example [CARLA integration](https://github.com/inverted-ai/invertedai/tree/master/examples/carla).

docs/source/cppapi/cpp-blame.md

@@ -0,0 +1,17 @@
+# BLAME (C++)
+
+
+```{eval-rst}
+.. doxygenfunction:: invertedai::blame
+   :project: InvertedAI-CPP
+```
+
+---
+```{eval-rst}
+.. doxygenclass:: invertedai::BlameRequest
+   :members:
+   :undoc-members:
+.. doxygenclass:: invertedai::BlameResponse
+   :members:
+   :undoc-members:
+```

docs/source/cppapi/index.md

@@ -7,6 +7,7 @@ accessed directly. Below are the key functions of the library, along with some c
 ```{toctree}
 :maxdepth: 1
 
+cpp-blame
 cpp-drive
 cpp-initialize
 cpp-location-info

docs/source/pythonapi/index.md

@@ -7,13 +7,13 @@ accessed directly. Below are the key functions of the library, along with some c
 ```{toctree}
 :maxdepth: 1
 
+sdk-blame
 sdk-drive
 sdk-initialize
-sdk-location-info
 sdk-light
-sdk-blame
-sdk-simulation
+sdk-location-info
 sdk-common
+sdk-simulation
 sdk-env-var
 ```
 

examples/README.md

@@ -4,16 +4,19 @@ This folder contains examples demonstrating how to use the Inverted AI API in Py
 <!-- start exampels -->
 [Click here](https://download-directory.github.io/?url=https://github.com/inverted-ai/invertedai/tree/master/examples) to download the folder as a zip-file.
 To run the examples locally, first build the virtual environment.
-```commandline
+```bash
 python -m venv .venv
 source .venv/bin/activate
+pip install --upgrade pip
 pip install --upgrade -r requirements.txt
+# optionally install carla, if you want to run carla demos 
+pip install carla==0.9.13
 ```
-*If running into package not found issue like`ERROR: No matching distribution found for carla==0.9.13`, try update 
-the pip: `pip install upgrade pip `.  
+*If you run into an issue like`ERROR: No matching distribution found for carla==0.9.13`, your Python version may not
+be CARLA-compatible.
 
 Then, once you obtain an API key, you can run the examples.
-```commandline
+```bash
 python npc_only.py --api_key $IAI_API_KEY
 ```
 There are currently three different examples available.
@@ -28,7 +31,7 @@ quickly give you an idea for how the underlying NPCs behave. This example is ava
 in a few different versions, one calling the underlying REST API directly, and others
 using the wrapper provided as a part of our library, the latter version also being
 available as a Jupyter notebook and
-[Colab](https://colab.research.google.com/github/inverted-ai/invertedai-drive/blob/develop/examples/npc_only_colab.ipynb).
+[Colab](https://colab.research.google.com/github/inverted-ai/invertedai-drive/blob/develop/examples/npc_only.ipynb).
 
 ## Cosimulation Minimal example
 

examples/carla/region_drive.py

@@ -1,6 +1,9 @@
+import sys
+sys.path.append('../')
+
 import argparse
 import invertedai as iai
-from invertedai.simulation.simulator import Simulation, SimulationConfig
+from simulation.simulator import Simulation, SimulationConfig
 import pathlib
 import pygame
 from tqdm import tqdm
@@ -17,7 +20,7 @@
 parser.add_argument("-cap", "--quadtree_capacity", type=int, default=15)
 parser.add_argument("-ad", "--agent_density", type=int, default=10)
 parser.add_argument("-ri", "--re_initialization", type=int, default=30)
-parser.add_argument("-len", "--simulation_length", type=int, default=10000)
+parser.add_argument("-len", "--simulation_length", type=int, default=600)
 args = parser.parse_args()
 
 
@@ -29,12 +32,12 @@
 
 cfg = SimulationConfig(location=args.location, map_center=(response.map_center.x, response.map_center.y),
                        map_fov=response.map_fov, rendered_static_map=rendered_static_map,
-                       map_width=response.map_fov+200, map_height=response.map_fov+200, agent_density=args.agent_density,
+                       map_width=response.map_fov, map_height=response.map_fov, agent_density=args.agent_density,
                        initialize_stride=50, quadtree_capacity=args.quadtree_capacity,
                        re_initialization_period=args.re_initialization)
 simulation = Simulation(cfg=cfg)
 
-fps = 100
+fps = 60
 clock = pygame.time.Clock()
 run = True
 start = perf_counter()

examples/cosimulation_minimal_example.py

@@ -1,17 +1,17 @@
 from typing import List
 import numpy as np
-import imageio
 import invertedai as iai
+import matplotlib.pyplot as plt
 
-# iai.add_apikey('')  # specify your key here or through the IAI_API_KEY variable
+iai.add_apikey('')  # specify your key here or through the IAI_API_KEY variable
 
 
 class LocalSimulator:
     """
     Mock up of a local simulator, where you control the ego vehicle. This example only supports single ego vehicle.
     """
 
-    def __init__(self, ego_state: iai.AgentState, npc_states: List[iai.AgentState]):
+    def __init__(self, ego_state: iai.common.AgentState, npc_states: List[iai.common.AgentState]):
         self.ego_state = ego_state
         self.npc_states = npc_states
 
@@ -24,8 +24,8 @@ def _step_ego(self):
         dx = self.ego_state.speed * dt * np.cos(self.ego_state.orientation)
         dy = self.ego_state.speed * dt * np.sin(self.ego_state.orientation)
 
-        self.ego_state = iai.AgentState(
-            center=iai.Point(x=self.ego_state.center.x + dx, y=self.ego_state.center.y + dy),
+        self.ego_state = iai.common.AgentState(
+            center=iai.common.Point(x=self.ego_state.center.x + dx, y=self.ego_state.center.y + dy),
             orientation=self.ego_state.orientation,
             speed=self.ego_state.speed,
         )
@@ -35,24 +35,48 @@ def step(self, predicted_npc_states):
         self.npc_states = predicted_npc_states
         return self.ego_state
 
-
+print("Begin initialization.")
+location = 'iai:ubc_roundabout'
 iai_simulation = iai.BasicCosimulation(  # instantiate a stateful wrapper for Inverted AI API
-    location='canada:vancouver:ubc_roundabout',  # select one of available locations
+    location=location,  # select one of available locations
     agent_count=5,  # how many vehicles in total to use in the simulation
     ego_agent_mask=[True, False, False, False, False],  # first vehicle is ego, rest are NPCs
-    get_birdview=True,  # provides simple visualization - don't use in production
+    get_birdview=False,  # provides simple visualization - don't use in production
     traffic_lights=True,  # gets the traffic light states and used for initialization and steping the simulation
 )
+
+location_info_response = iai.location_info(location=location)
+rendered_static_map = location_info_response.birdview_image.decode()
+scene_plotter = iai.utils.ScenePlotter(rendered_static_map,
+                                       location_info_response.map_fov,
+                                       (location_info_response.map_center.x, location_info_response.map_center.y),
+                                       location_info_response.static_actors)
+scene_plotter.initialize_recording(
+    agent_states=iai_simulation.agent_states,
+    agent_attributes=iai_simulation.agent_attributes,
+)
+
+print("Begin stepping through simulation.")
 local_simulation = LocalSimulator(iai_simulation.ego_states[0], iai_simulation.npc_states)
-images = [iai_simulation.birdview.decode()]  # images storing visualizations of subsequent states
 for _ in range(100):  # how many simulation steps to execute (10 steps is 1 second)
     # query the API for subsequent NPC predictions, informing it how the ego vehicle acted
     iai_simulation.step([local_simulation.ego_state])
     # collect predictions for the next time step
     predicted_npc_behavior = iai_simulation.npc_states
     # execute predictions in your simulator, using your actions for the ego vehicle
     updated_ego_agent_state = local_simulation.step(predicted_npc_behavior)
-    # save the visualization - requires np and cv2
-    images.append(iai_simulation.birdview.decode())
+    # save the visualization with ScenePlotter
+    scene_plotter.record_step(iai_simulation.agent_states)
+
+print("Simulation finished, save visualization.")
 # save the visualization to disk
-imageio.mimsave("iai-example.gif", np.array(images), format="GIF-PIL")
+fig, ax = plt.subplots(constrained_layout=True, figsize=(50, 50))
+gif_name = 'cosimulation_minimal_example.gif'
+scene_plotter.animate_scene(
+    output_name=gif_name,
+    ax=ax,
+    direction_vec=False,
+    velocity_vec=False,
+    plot_frame_number=True
+)
+print("Done")