Adds time-based mdp (observation) functions.

CONTRIBUTORS.md

@@ -93,6 +93,7 @@ Guidelines for modifications:
 * Ryley McCarroll
 * Shafeef Omar
 * Shundo Kishi
+* Stefan Van de Mosselaer
 * Stephan Pleines
 * Tyler Lum
 * Victor Khaustov

source/isaaclab/config/extension.toml

@@ -1,7 +1,7 @@
 [package]
 
 # Note: Semantic Versioning is used: https://semver.org/
-version = "0.36.6"
+version = "0.36.7"
 
 # Description
 title = "Isaac Lab framework for Robot Learning"

source/isaaclab/docs/CHANGELOG.rst

@@ -1,6 +1,21 @@
 Changelog
 ---------
 
+0.36.7 (2025-04-17)
+~~~~~~~~~~~~~~~~~~~
+
+Added
+^^^^^
+
+* Added initialization of ``episode_length_buf`` in :meth:`load_managers()` of :class:`~isaaclab.envs.ManagerBasedRLEnv`
+  to make it available for use in mdp functions. Note: existing initialization in :meth:`__init__` left in place in case
+  it is needed for other use cases.
+* Added :attr:`~isaaclab.envs.ManagerBasedRLEnv.curr_episode_length` to :class:`~isaaclab.envs.ManagerBasedRLEnv` which
+  returns reshaped ``episode_length_buf`` so it is visible as an attribute in the documentation.
+* Added time observation functions to ~isaaclab.envs.mdp.observations module,
+  :func:`~isaaclab.envs.mdp.observations.current_time_s` and :func:`~isaaclab.envs.mdp.observations.remaining_time_s`.
+
+
 0.36.6 (2025-04-09)
 ~~~~~~~~~~~~~~~~~~~
 

source/isaaclab/isaaclab/envs/manager_based_rl_env.py

@@ -75,14 +75,16 @@ def __init__(self, cfg: ManagerBasedRLEnvCfg, render_mode: str | None = None, **
         # -- counter for curriculum
         self.common_step_counter = 0
 
+        # initialize the episode length buffer BEFORE loading the managers so it is available for use by mdp functions.
+        self.cfg = cfg
+        self.episode_length_buf = torch.zeros(self.cfg.scene.num_envs, device=self.cfg.sim.device, dtype=torch.long)
+
         # initialize the base class to setup the scene.
         super().__init__(cfg=cfg)
         # store the render mode
         self.render_mode = render_mode
 
         # initialize data and constants
-        # -- init buffers
-        self.episode_length_buf = torch.zeros(self.num_envs, device=self.device, dtype=torch.long)
         # -- set the framerate of the gym video recorder wrapper so that the playback speed of the produced video matches the simulation
         self.metadata["render_fps"] = 1 / self.step_dt
 
@@ -107,6 +109,7 @@ def max_episode_length(self) -> int:
     """
 
     def load_managers(self):
+
         # note: this order is important since observation manager needs to know the command and action managers
         # and the reward manager needs to know the termination manager
         # -- command manager

source/isaaclab/isaaclab/envs/mdp/observations.py

@@ -529,3 +529,18 @@ def last_action(env: ManagerBasedEnv, action_name: str | None = None) -> torch.T
 def generated_commands(env: ManagerBasedRLEnv, command_name: str) -> torch.Tensor:
     """The generated command from command term in the command manager with the given name."""
     return env.command_manager.get_command(command_name)
+
+
+"""
+Time.
+"""
+
+
+def current_time_s(env: ManagerBasedRLEnv) -> torch.Tensor:
+    """The current time in the episode (in seconds)."""
+    return env.episode_length_buf.unsqueeze(1) * env.step_dt
+
+
+def remaining_time_s(env: ManagerBasedRLEnv) -> torch.Tensor:
+    """The maximum time remaining in the episode (in seconds)."""
+    return env.max_episode_length_s - env.episode_length_buf.unsqueeze(1) * env.step_dt