working on ant environment

libraries/dmc/tasks/quadruped.py

@@ -24,6 +24,7 @@
 from dm_control.utils import containers
 from dm_control.utils import rewards
 from dm_control.utils import xml_tools
+from dm_control.utils import io as resources
 from lxml import etree
 import numpy as np
 from scipy import ndimage
@@ -73,7 +74,7 @@ def get_model_and_assets():
     """Returns a tuple containing the model XML string and a dict of assets."""
     root_dir = os.path.dirname(os.path.dirname(__file__))
     xml = resources.GetResource(
-        os.path.join(root_dir, 'custom_dmc_tasks', 'quadruped.xml'))
+        os.path.join(root_dir, 'tasks', 'quadruped.xml'))
     return xml, common.ASSETS
 
 
@@ -84,7 +85,7 @@ def make_model(floor_size=None,
     """Returns the model XML string."""
     root_dir = os.path.dirname(os.path.dirname(__file__))
     xml_string = common.read_model(
-        os.path.join(root_dir, 'custom_dmc_tasks', 'quadruped.xml'))
+        os.path.join(root_dir, 'tasks', 'quadruped.xml'))
     parser = etree.XMLParser(remove_blank_text=True)
     mjcf = etree.XML(xml_string, parser)
 

libraries/safe/dmc/ant.py → libraries/safe/dmc/ant_obstacle.py

@@ -36,8 +36,10 @@ def make(task,
     env.task.visualize_reward = visualize_reward
     return env
 
-@SUITE.add('benchmarking')
-def navigate(time_limit=_DEFAULT_TIME_LIMIT, random=None, environment_kwargs=None):
+@SUITE.add()
+def navigate(time_limit=_DEFAULT_TIME_LIMIT, 
+             random=None,
+             environment_kwargs=None):
     """Navigate to a goal position"""
     walker = Ant()
     arena = obstacles.Obstacle()

libraries/safe/dmc/obstacles.py

@@ -10,7 +10,7 @@
 
 _GROUNDPLANE_QUAD_SIZE = 0.25
 _TOP_CAMERA_DISTANCE = 7.0
-_TOP_CAMERA_Y_PADDING_FACTOR = 2.2
+_TOP_CAMERA_Y_PADDING_FACTOR = 2.5
 
 
 class Obstacle(composer.Arena):
@@ -19,7 +19,7 @@ def _build(self, size=(11, 11), name='obstacle'):
         super()._build(name=name)
 
         self._aesthetic = 'outdoor_natural'
-        self._size = size
+        self.size = size
 
         sky_info = locomotion_arenas_assets.get_sky_texture_info(self._aesthetic)
 
@@ -55,27 +55,71 @@ def _build(self, size=(11, 11), name='obstacle'):
             pos = [0, 0, 0]
         )
 
-        #TODO: Work out why the ground doesn't render correctly
+        #TODO: Work out why the ground doesn't render correctly 
         ground_size = max(size)
         top_camera_fovy = (360 / np.pi) * np.arctan2(
             _TOP_CAMERA_Y_PADDING_FACTOR * ground_size / 2,
             _TOP_CAMERA_DISTANCE)
-        print(f'top_camera_distance: {_TOP_CAMERA_DISTANCE}')
         self._top_camera = self._mjcf_root.worldbody.add(
             'camera',
             name='top_camera',
             pos=[0, 0, _TOP_CAMERA_DISTANCE],
             zaxis=[0, 0, 1],
-            fovy = top_camera_fovy
+            fovy=top_camera_fovy
         )
-
+        
         self._obstacle = self._mjcf_root.worldbody.add(
-            'site',
-            name='obstacle',
+            'geom',
+            type='box',
+            name='box_obstacle',
+            size=[2.0, 2.0, 0.5],
+            rgba=[1, 0, 0, 1],
+            pos = [0.5, 0, 0]
+        )
+
+        self._wall_height = 1.0
+        self._wall_thickness = 0.5
+        self._wall_colour = [0, 0, 0, 0.0]
+        self._wall_left = self._mjcf_root.worldbody.add(
+            'geom',
+            type='box',
+            name='wall_left',
+            size=[self._wall_thickness, size[1], self._wall_height],
+            rgba=self._wall_colour,
+            pos=[size[0], 0.0, 0.0]
+        )
+        self._wall_right = self._mjcf_root.worldbody.add(
+            'geom',
+            type='box',
+            name='wall_right',
+            size=[self._wall_thickness, size[1], self._wall_height],
+            rgba=self._wall_colour,
+            pos=[-size[0], 0.0, 0.0]
+        )
+        self._wall_front = self._mjcf_root.worldbody.add(
+            'geom',
+            type='box',
+            name='wall_front',
+            size=[size[0], self._wall_thickness, self._wall_height],
+            rgba=self._wall_colour,
+            pos=[0.0, size[1], 0.0]
+        )
+        self._wall_back = self._mjcf_root.worldbody.add(
+            'geom',
             type='box',
-            pos=(0., 0., 0.),
-            size=(1.0, 2.0, 2.0),
-            rgba=(1.0, 0.0, 0.0, 1.0)
+            name='wall_back',
+            size=[size[0], self._wall_thickness, self._wall_height],
+            rgba=self._wall_colour,
+            pos=[0.0, -size[1], 0.0]
+        )
+
+        self._objective = self._mjcf_root.worldbody.add(
+            'geom',
+            type='sphere',
+            name='goal_position',
+            size=[0.7],
+            rgba=[0, 0, 1, 1],
+            pos=[-5.0, 0.0, 0.0]
         )
 
     def _build_observables(self):
@@ -89,10 +133,6 @@ def ground_geoms(self):
     def top_camera(self):
         return self._top_camera
 
-    @property
-    def size(self):
-        return self._size
-
     def regenerate(self, random_state):
         pass
 

libraries/safe/simple_point_bot.py

@@ -72,6 +72,11 @@ def step(self, a):
         constr = self.obstacle(next_state)
         self.done = self._episode_steps >= self.horizon
 
+        # Terminate episode if we hit the wall
+        if 0+1 >= self.state[0] or self.state[0] >= WINDOW_WIDTH-1:
+            self.done = True
+        if 0+1 >= self.state[1] or self.state[1] >= WINDOW_HEIGHT-1:
+            self.done = True
         if self._from_pixels:
             obs = self._state_to_image(self.state)
         else:

utils/env_constructor.py

@@ -10,6 +10,7 @@
 
 import libraries.dmc as cdmc
 from libraries.safe import SimplePointBot, SimpleVelocityBot
+from libraries.safe.dmc import ant_obstacle
 from .wrappers import GymWrapper
 from .wrappers import FrameStack
 
@@ -22,7 +23,8 @@
     'CarRacing-v2': 'gym',
     'LunarLander-v2': 'gym',
     'SimplePointBot': 'safe',
-    'SimpleVelocityBot': 'safe'
+    'SimpleVelocityBot': 'safe',
+    'ant_obstacle': 'dmc'
 }
 
 SAFE_ENVS = {