fix(sim): split transfer and air-insert camera sets

roboimi/assets/models/manipulators/DianaMed/table_square.xml

@@ -7,7 +7,6 @@
           <geom name="table" condim="4" contype="1" conaffinity="1"  type="box" rgba="0.4 0.4 0.4 1" size="0.62 0.62 0.01" density="1500" friction="0.9 0.9 0.9"/>
       </body>
       <camera name="top" pos="0.0 1.0 2.0" fovy="44" mode="targetbody" target="table"/>
-      <camera name="left_side" pos="-0.55 0.85 0.85" fovy="65" mode="targetbody" target="table"/>
       <camera name="front" pos="0 0 0.8" fovy="65" mode="fixed" quat="0.7071 0.7071 0 0"/>
   </worldbody>
 </mujoco>

roboimi/envs/double_air_insert_env.py

@@ -120,15 +120,18 @@ class DualDianaMed_Air_Insert(DualDianaMed_Pos_Ctrl):
         set_socket_peg_task_state(self.mj_data, task_state)
         DualDianaMed.reset(self)
         self.top = None
-        self.left_side = None
         self.r_vis = None
+        self.l_vis = None
         self.front = None
+        if not self.is_render:
+            self._update_camera_images_sync()
+            return
         self.cam_flage = True
         while self.cam_flage:
             if (
                 type(self.top) == type(None)
-                or type(self.left_side) == type(None)
                 or type(self.r_vis) == type(None)
+                or type(self.l_vis) == type(None)
                 or type(self.front) == type(None)
             ):
                 time.sleep(0.001)

roboimi/envs/double_base.py

@@ -52,7 +52,6 @@ class DualDianaMed(MujocoEnv):
         self.r_vis = None
         self.l_vis = None
         self.top = None
-        self.left_side = None
         self.front = None
         self.obs = None
         
@@ -168,10 +167,9 @@ class DualDianaMed(MujocoEnv):
         obs['qpos'] = self.get_obs_qpos
         obs['action'] = self.compute_qpos
         obs['images'] = dict()
-        obs['images']['top']   = self.top
-        obs['images']['left_side'] = self.left_side
         obs['images']['r_vis'] = self.r_vis
         obs['images']['l_vis'] = self.l_vis
+        obs['images']['top'] = self.top
         obs['images']['front'] = self.front
         return obs
 
@@ -180,10 +178,9 @@ class DualDianaMed(MujocoEnv):
             self._update_camera_images_sync()
         obs = collections.OrderedDict()
         obs['images'] = dict()
-        obs['images']['top']   = self.top
-        obs['images']['left_side'] = self.left_side
         obs['images']['r_vis'] = self.r_vis
         obs['images']['l_vis'] = self.l_vis
+        obs['images']['top'] = self.top
         obs['images']['front'] = self.front
         return obs
     
@@ -202,14 +199,12 @@ class DualDianaMed(MujocoEnv):
 
     @property
     def cam_view(self):
-        if self.cam == 'top':
+        if self.cam == 'r_vis':
-            return self.top
-        elif self.cam == 'left_side':
-            return self.left_side
-        elif self.cam == 'r_vis':
             return self.r_vis
         elif self.cam == 'l_vis':
             return self.l_vis
+        elif self.cam == 'top':
+            return self.top
         elif self.cam == 'front':
             return self.front
         else:
@@ -230,8 +225,6 @@ class DualDianaMed(MujocoEnv):
         self.l_vis = img_renderer.render()[:, :, ::-1]
         img_renderer.update_scene(self.mj_data, camera="top")
         self.top = img_renderer.render()[:, :, ::-1]
-        img_renderer.update_scene(self.mj_data, camera="left_side")
-        self.left_side = img_renderer.render()[:, :, ::-1]
         img_renderer.update_scene(self.mj_data, camera="front")
         self.front = img_renderer.render()[:, :, ::-1]
 

roboimi/envs/double_pos_ctrl_env.py

@@ -73,8 +73,8 @@ class DualDianaMed_Pos_Ctrl(DualDianaMed):
         self.mj_data.joint('red_box_joint').qpos[6] = 0.0
         super().reset()
         self.top = None
-        self.left_side = None
         self.r_vis = None
+        self.l_vis = None
         self.front = None
         if not self.is_render:
             self._update_camera_images_sync()
@@ -83,8 +83,8 @@ class DualDianaMed_Pos_Ctrl(DualDianaMed):
         t=0
         while self.cam_flage:
             if(type(self.top)==type(None)
-               or type(self.left_side)==type(None)
                or type(self.r_vis)==type(None)
+               or type(self.l_vis)==type(None)
                or type(self.front)==type(None)):
                 time.sleep(0.001)
                 t+=1
@@ -146,7 +146,7 @@ def make_sim_env(task_name, headless=False):
             is_render=not headless,
             control_freq=30,
             is_interpolate=True,
-            cam_view='left_side'
+            cam_view='front'
         )
         return env
     if 'sim_transfer' in task_name:
@@ -156,7 +156,7 @@ def make_sim_env(task_name, headless=False):
             is_render=not headless,
             control_freq=30,
             is_interpolate=True,
-            cam_view='left_side'
+            cam_view='top'
         )
         return env
     else:
@@ -182,4 +182,3 @@ if __name__ == "__main__":
         env.step(action)
         if env.is_render:
             env.render()
-

roboimi/utils/constants.py

@@ -20,7 +20,7 @@ SIM_TASK_CONFIGS = {
         'dataset_dir': DATASET_DIR + '/sim_transfer',
         'num_episodes': 20,
         'episode_len': 700,
-        'camera_names': ['top','r_vis','front'],
+        'camera_names': ['r_vis', 'top', 'front'],
         'xml_dir': HOME_PATH + '/assets'
     },
     'sim_air_insert_socket_peg': {

tests/test_air_insert_env.py

@@ -94,10 +94,10 @@ class AirInsertTaskRegistrationTest(unittest.TestCase):
             is_render=False,
             control_freq=30,
             is_interpolate=True,
-            cam_view="left_side",
+            cam_view="front",
         )
 
-    def test_diana_table_scene_uses_left_side_camera_instead_of_angle(self):
+    def test_diana_table_scene_exposes_only_top_and_front_scene_cameras(self):
         xml_path = (
             pathlib.Path(__file__).resolve().parents[1]
             / "roboimi/assets/models/manipulators/DianaMed/table_square.xml"
@@ -106,11 +106,11 @@ class AirInsertTaskRegistrationTest(unittest.TestCase):
         cameras = {camera.attrib["name"]: camera.attrib for camera in root.findall(".//camera")}
 
         self.assertNotIn("angle", cameras, "DianaMed scene should stop exposing the old angle camera")
-        self.assertIn("left_side", cameras, "DianaMed scene should expose the left-side task camera")
+        self.assertNotIn("left_side", cameras, "DianaMed scene should no longer expose left_side")
-        left_side_pos = np.fromstring(cameras["left_side"]["pos"], sep=" ")
+        self.assertIn("top", cameras)
-        self.assertLess(float(left_side_pos[0]), 0.0)
+        self.assertIn("front", cameras)
-        self.assertEqual(cameras["left_side"].get("mode"), "targetbody")
+        self.assertEqual(cameras["top"].get("mode"), "targetbody")
-        self.assertEqual(cameras["left_side"].get("target"), "table")
+        self.assertEqual(cameras["top"].get("target"), "table")
 
 
 class AirInsertResetAndStateHelpersTest(unittest.TestCase):

tests/test_eval_vla_headless.py

@@ -74,7 +74,7 @@ class _FakeRenderer:
         self._env = env
         self._frames = [
             np.full((4, 4, 3), fill_value=index, dtype=np.uint8)
-            for index in range(5)
+            for index in range(8)
         ]
         self._index = 0
 
@@ -144,7 +144,7 @@ class EvalVLAHeadlessTest(unittest.TestCase):
             is_render=False,
             control_freq=30,
             is_interpolate=True,
-            cam_view="left_side",
+            cam_view="top",
         )
 
     def test_headless_sync_camera_capture_populates_images_without_gui_calls(self):
@@ -153,11 +153,10 @@ class EvalVLAHeadlessTest(unittest.TestCase):
         env.mj_data = object()
         env.exit_flag = False
         env.is_render = False
-        env.cam = 'angle'
+        env.cam = 'top'
         env.r_vis = None
         env.l_vis = None
         env.top = None
-        env.angle = None
         env.front = None
         env._offscreen_renderer = None
 
@@ -176,7 +175,6 @@ class EvalVLAHeadlessTest(unittest.TestCase):
         self.assertIsNotNone(env.r_vis)
         self.assertIsNotNone(env.l_vis)
         self.assertIsNotNone(env.top)
-        self.assertIsNotNone(env.angle)
         self.assertIsNotNone(env.front)
 
     def test_cam_start_skips_background_thread_when_headless(self):
@@ -196,11 +194,10 @@ class EvalVLAHeadlessTest(unittest.TestCase):
         env.mj_data = object()
         env.exit_flag = False
         env.is_render = False
-        env.cam = "left_side"
+        env.cam = "top"
         env.r_vis = None
         env.l_vis = None
         env.top = None
-        env.left_side = None
         env.front = None
 
         with mock.patch(
@@ -217,7 +214,6 @@ class EvalVLAHeadlessTest(unittest.TestCase):
         self.assertIsNotNone(env.r_vis)
         self.assertIsNotNone(env.l_vis)
         self.assertIsNotNone(env.top)
-        self.assertIsNotNone(env.left_side)
         self.assertIsNotNone(env.front)
 
     def test_eval_main_headless_skips_render_and_still_executes_policy(self):