ft[examples]: observation checking and info for panda mujoco example.

examples/panda_mujoco.py

@@ -1,44 +1,46 @@
 import numpy as np
 import sys
 import gymnasium as gym
-from urdfenvs.urdf_common.generic_mujoco_env import GenericMujocoEnv
-from urdfenvs.urdf_common.generic_mujoco_robot import GenericMujocoRobot
+from urdfenvs.generic_mujoco.generic_mujoco_env import GenericMujocoEnv
+from urdfenvs.generic_mujoco.generic_mujoco_robot import GenericMujocoRobot
 from urdfenvs.robots.generic_urdf import GenericUrdfReacher
 from urdfenvs.urdf_common.urdf_env import UrdfEnv
 from urdfenvs.scene_examples.obstacles import sphereObst1, sphereObst2, wall_obstacles, cylinder_obstacle
 
 
-def run_panda(n_steps: int = 1000, render: bool = True, physics_engine: str = 'bullet'):
+def run_panda(n_steps: int = 1000, render: bool = True, physics_engine: str = "bullet"):
     obstacles = [sphereObst1, sphereObst2, cylinder_obstacle] + wall_obstacles
-    if physics_engine == 'mujoco':
+    if physics_engine == "mujoco":
+
         robots  = [
-            GenericMujocoRobot(xml_file='panda_scene.xml'),
+            GenericMujocoRobot(xml_file="panda_scene.xml", mode="vel"),
         ]
-        env = GenericMujocoEnv(robots, obstacles, render=True)
-    if physics_engine == 'bullet':
+        env = GenericMujocoEnv(robots, obstacles, render=render)
+    if physics_engine == "bullet":
         robots = [
             GenericUrdfReacher(urdf="panda.urdf", mode="vel"),
         ]
         env= UrdfEnv(
             dt=0.01, robots=robots,
-            render=True,
+            render=render,
             observation_checking=False,
         )
         for obstacle in obstacles:
             env.add_obstacle(obstacle)
         env.set_spaces()
 
 
-    #observation, info = env.reset(seed=42)
-    pos0=np.array([0,0,0,-1.57079,0,1.57079,-0.7853,0.04,0.04])
-    env.reset(pos=pos0)
+    ob, info = env.reset()
 
-    action_mag = np.array([0.3, -0.2, 0.3, -0.15, 0.2, -0.01, 0.35, 0.01])
+    action_mag = np.array([0.8, -0.2, 0.3, -0.15, 0.2, -0.01, 0.35, 0.01])
     t = 0.0
     for _ in range(n_steps):
         t += env.dt
         action = action_mag * np.cos(t)
-        observation, *_ = env.step(action)
+        ob, _, terminated, _, info = env.step(action)
+        if terminated:
+            print(info)
+            break
     env.close()
 
 if __name__ == "__main__":