mani-skill-nightly 2025.10.23.432__py3-none-any.whl → 2025.10.23.1953__py3-none-any.whl

mani_skill/agents/controllers/pd_joint_pos.py

@@ -199,7 +199,7 @@ class PDJointPosMimicController(PDJointPosController):
 
     def _get_joint_limits(self):
         joint_limits = super()._get_joint_limits()
-        joint_limits = joint_limits[self.control_joint_indices]
+        joint_limits = joint_limits[self.control_joint_indices.cpu().numpy()]
         if len(joint_limits.shape) == 1:
             joint_limits = joint_limits[None, :]
         return joint_limits

mani_skill/envs/sapien_env.py

@@ -51,7 +51,7 @@ class BaseEnv(gym.Env):
             GPU simulations. For example, environments with many moving objects are better simulated by parallelizing across CPUs.
 
         obs_mode: observation mode to be used. Must be one of ("state", "state_dict", "none", "sensor_data", "rgb", "depth", "segmentation", "rgbd", "rgb+depth", "rgb+depth+segmentation", "rgb+segmentation", "depth+segmentation", "pointcloud")
-            The obs_mode is mostly for convenience to automatically optimize/setup all sensors/cameras for the given observation mode to render the correct data and try to ignore unecesary rendering.
+            The obs_mode is mostly for convenience to automatically optimize/setup all sensors/cameras for the given observation mode to render the correct data and try to ignore unnecessary rendering.
             For the most advanced use cases (e.g. you have 1 RGB only camera and 1 depth only camera)
 
         reward_mode: reward mode to use. Must be one of ("normalized_dense", "dense", "sparse", "none"). With "none" the reward returned is always 0

mani_skill/envs/tasks/dexterity/insert_flower.py

@@ -109,10 +109,15 @@ class InsertFlowerEnv(BaseEnv):
             flower_collision_file, density=200, material=flower_material
         )
 
-        self.init_flower_pose = Pose.create_from_pq(
+        flower_builder.initial_pose = Pose.create_from_pq(
             [-0.242, 0.0, 0.015 + 0.001], [-0.352413, -0.258145, -0.635074, 0.637062]
         )
-        flower_builder.initial_pose = self.init_flower_pose
+        self.initial_flower_pos = torch.tensor(
+            [-0.242, 0.0, 0.015 + 0.001], device=self.device
+        )
+        self.initial_flower_quat = torch.tensor(
+            [-0.352413, -0.258145, -0.635074, 0.637062], device=self.device
+        )
         self.flower = flower_builder.build(name="flower")
         self.target_area_box = list(self.target_area.values())
         # Convert target_area into tensor for fast computation
@@ -133,11 +138,12 @@ class InsertFlowerEnv(BaseEnv):
 
             self.table_scene.initialize(env_idx)
 
-            flower_pose = self.init_flower_pose
-            flower_pose.p[:, :2] += (
-                torch.rand((b, 2)) * self.flower_spawn_half_size * 2
+            flower_pos = (
+                torch.rand((b, 3)) * self.flower_spawn_half_size * 2
                 - self.flower_spawn_half_size
+                + self.initial_flower_pos
             )
+            flower_pose = Pose.create_from_pq(flower_pos, self.initial_flower_quat)
             self.flower.set_pose(flower_pose)
 
     def _initialize_agent(self, env_idx: torch.Tensor):

{mani_skill_nightly-2025.10.23.432.dist-info → mani_skill_nightly-2025.10.23.1953.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mani_skill-nightly
-Version: 2025.10.23.432
+Version: 2025.10.23.1953
 Summary: ManiSkill3: A Unified Benchmark for Generalizable Manipulation Skills
 Home-page: https://github.com/haosulab/ManiSkill
 Author: ManiSkill contributors

{mani_skill_nightly-2025.10.23.432.dist-info → mani_skill_nightly-2025.10.23.1953.dist-info}/RECORD

@@ -10,7 +10,7 @@ mani_skill/agents/controllers/base_controller.py,sha256=o5qh7DZmzMpIINDIxC00IrJm
 mani_skill/agents/controllers/passive_controller.py,sha256=1cZp758AVuABvgWOzCeguBbbB8wJ6hF_cqN-k_vx5Kw,1322
 mani_skill/agents/controllers/pd_base_vel.py,sha256=-3ZzLZ9nRDMGHWnFE7c4reEbC3jHtQJCOx3LmArz95g,2868
 mani_skill/agents/controllers/pd_ee_pose.py,sha256=alYkN02OVYDbj7i1OqC6hC87o_FZ85SxHXNmBFXR-lw,13447
-mani_skill/agents/controllers/pd_joint_pos.py,sha256=z0r1OLYINf175qUD869Rkn1cQDTDVxNpIZKmbRSI4Sw,11102
+mani_skill/agents/controllers/pd_joint_pos.py,sha256=zgX-sFxDcOwr5YxgRlCC3eFf2X5jmKGHpkil6TKk1Y4,11116
 mani_skill/agents/controllers/pd_joint_pos_vel.py,sha256=wgiXmenTVIao1Tm1vtdJWTZRFJMB_yQBNd5vQaP8WXw,2489
 mani_skill/agents/controllers/pd_joint_vel.py,sha256=VZF06ISCkdKBX_fUHxb7mdl9GN1Lob5dhrFGlwCx16Q,1957
 mani_skill/agents/controllers/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -543,7 +543,7 @@ mani_skill/assets/robots/xarm7/meshes/visual/link7.glb,sha256=aZatACOv20VJbi2tOE
 mani_skill/assets/robots/xarm7/meshes/visual/link_base.glb,sha256=vcy2lN1V72jIsSDRT0ZKVskR_0pVOXtDvBkxO2GENWs,467668
 mani_skill/envs/__init__.py,sha256=YPlttBErTcf9vSnkZ54EQ8vTABSfFFrBdUY0AkF4vmg,43
 mani_skill/envs/minimal_template.py,sha256=n7XUY73FjWFf311bd2DoODA3dEqfdGYJLqhMVLy_Om0,2194
-mani_skill/envs/sapien_env.py,sha256=6AYcGdExOKCuyPX1YmJKD6YWVwUgZ21kuNyDg9NhwI8,75784
+mani_skill/envs/sapien_env.py,sha256=gwZqDmj4Z5sCqnr8Vrf1_OoeGIazHpz1DhqqN1j1byw,75786
 mani_skill/envs/scene.py,sha256=LodfSgU_tWh77jt4WHFr4xlr2NbK41-_mtEQsDEVb-0,48453
 mani_skill/envs/sim2real_env.py,sha256=UWwK2DzO8YkHBQmPMeODu3xKRd6W2fXglJ1GjiR78wk,19202
 mani_skill/envs/template.py,sha256=xEB-1Cz-XbLBadEX3kEvUyVuyOGyuyKp50EtDsVXvr4,11933
@@ -565,7 +565,7 @@ mani_skill/envs/tasks/control/assets/common/materials.xml,sha256=XxJ5NRzW5_g_pKL
 mani_skill/envs/tasks/control/assets/common/skybox.xml,sha256=UvNofKMDKbQHewom_qrZtz0gHhg8veD_vWzVLeUZB70,202
 mani_skill/envs/tasks/control/assets/common/visual.xml,sha256=7B0nSrcNlWBBM9r6ksDRGU3lG7qZe9U7cLxn65XYI_w,175
 mani_skill/envs/tasks/dexterity/__init__.py,sha256=BUM4SkQ1zXWzP0dXQTsP5vIoTfLENzh0oIfvlIQrhf4,163
-mani_skill/envs/tasks/dexterity/insert_flower.py,sha256=-h3j3ZQuAx1gRPvS0VS9RzEKXFQpFZLzU6u5ZcJQyJg,7164
+mani_skill/envs/tasks/dexterity/insert_flower.py,sha256=PVCZSGSztdcbFknSHXRcn_z3zI4fI1FoVDxO8poAlJk,7431
 mani_skill/envs/tasks/dexterity/rotate_single_object_in_hand.py,sha256=pk6dM25_jflSm0yehF7_8wDHWWrUNzbMy2JDNyiYzz0,14153
 mani_skill/envs/tasks/dexterity/rotate_valve.py,sha256=62a6sqNtK9h3j1UHAI8Rycy6T8XZxqWqOM5hVpBRCrU,11647
 mani_skill/envs/tasks/digital_twins/__init__.py,sha256=_yWWBFH-P69UTPvo9GRa8Ux_FXOjLWdkiK3rs2ojX3o,60
@@ -842,9 +842,9 @@ mani_skill/vector/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 mani_skill/vector/wrappers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mani_skill/vector/wrappers/gymnasium.py,sha256=YhiRL7FhGOvH9Ho09c_ubFpAFYUB3qskVw0NzxWdWUc,7628
 mani_skill/vector/wrappers/sb3.py,sha256=mnDpiAo1sOkIfpfxsxrRayUeAWVZnLIuUi48yAbwOFI,4716
-mani_skill_nightly-2025.10.23.432.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mani_skill_nightly-2025.10.23.432.dist-info/licenses/LICENSE-3RD-PARTY,sha256=yXvoAIyaRY7VDFhXV4Ea_Dmd_-IR59yyUy0Scz7eXzY,1604
-mani_skill_nightly-2025.10.23.432.dist-info/METADATA,sha256=WxASE-DQaq9ONPa1RsJ7tyCjvMz832yi-SI01BSC_Zo,9542
-mani_skill_nightly-2025.10.23.432.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
-mani_skill_nightly-2025.10.23.432.dist-info/top_level.txt,sha256=bkBgOVl_MZMoQx2aRFsSFEYlZLxjWlip5vtJ39FB3jA,11
-mani_skill_nightly-2025.10.23.432.dist-info/RECORD,,
+mani_skill_nightly-2025.10.23.1953.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mani_skill_nightly-2025.10.23.1953.dist-info/licenses/LICENSE-3RD-PARTY,sha256=yXvoAIyaRY7VDFhXV4Ea_Dmd_-IR59yyUy0Scz7eXzY,1604
+mani_skill_nightly-2025.10.23.1953.dist-info/METADATA,sha256=1nmVKLJRBq9ZOZxnRd5RijaD9jq0Rczv7W-lJiH5CrE,9543
+mani_skill_nightly-2025.10.23.1953.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+mani_skill_nightly-2025.10.23.1953.dist-info/top_level.txt,sha256=bkBgOVl_MZMoQx2aRFsSFEYlZLxjWlip5vtJ39FB3jA,11
+mani_skill_nightly-2025.10.23.1953.dist-info/RECORD,,