Instructions to use INSAIT-Institute/LADDER-SimplerEnv-Long with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use INSAIT-Institute/LADDER-SimplerEnv-Long with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Shorter model card
Browse files
README.md
CHANGED
|
@@ -1,67 +1,47 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
library_name: lerobot
|
| 4 |
-
tags: [lerobot, envhub, robotics, simulation, benchmark,
|
| 5 |
---
|
| 6 |
|
| 7 |
# LADDER SimplerEnv-Long
|
| 8 |
|
| 9 |
-
|
| 10 |
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
|
| 14 |
-
|-
|
| 15 |
-
|
|
| 16 |
-
| SimplerEnv-Long | this one | SAPIEN 3 / ManiSkill 3 | WidowX | 54 | 24 |
|
| 17 |
-
| RobotArena-∞-Long | [`INSAIT-Institute/LADDER-RobotArena-Long`](https://huggingface.co/INSAIT-Institute/LADDER-RobotArena-Long) | Genesis | WidowX | 47 | 8 |
|
| 18 |
|
| 19 |
## Evaluate a policy
|
| 20 |
|
| 21 |
-
|
| 22 |
|
| 23 |
```bash
|
| 24 |
-
pip install -e ".[dataset,evaluation,remote]" # plus your policy's extra
|
| 25 |
lerobot-env-server --envhub=INSAIT-Institute/LADDER-SimplerEnv-Long@v1.0.0 --docker=true
|
| 26 |
lerobot-eval --policy.path=<your WidowX checkpoint> \
|
| 27 |
--env.type=envhub --env.hub_path=INSAIT-Institute/LADDER-SimplerEnv-Long@v1.0.0 \
|
| 28 |
-
--env.server.endpoint=tcp/127.0.0.1:7448 \
|
| 29 |
-
--
|
| 30 |
```
|
| 31 |
|
| 32 |
-
- `--env.task` takes
|
| 33 |
-
-
|
| 34 |
-
- `@v1.0.0` pins this repository to its release for LADDER v1.0.0 (or pin a commit): LeRobot runs its `env.py`.
|
| 35 |
-
|
| 36 |
-
Two other ways to run it, as fast as the one above:
|
| 37 |
|
| 38 |
-
|
| 39 |
-
- In-process: `pip install "lerobot[dataset,evaluation]>=0.7.0" -r requirements.txt` next to your policy, then run `lerobot-eval` as above without `--env.server.endpoint` and with `--env.trust_remote_code=true`. Only when this repository's pinned versions suit your policy.
|
| 40 |
-
|
| 41 |
-
## Observations, actions and scores
|
| 42 |
|
| 43 |
| | |
|
| 44 |
|---|---|
|
| 45 |
-
| Observation | `pixels.main`:
|
| 46 |
-
| Action | `[dx, dy, dz, drx, dry, drz, gripper]`
|
| 47 |
| Control rate | 5 Hz |
|
| 48 |
-
|
|
| 49 |
-
| Instruction | `task_description`, e.g. "put the carrot on the plate and then the spoon on the towel" |
|
| 50 |
-
| Success | `info["is_success"]`: LADDER's task success (`pc_success` in LeRobot) |
|
| 51 |
-
| Progress | `info["metrics"]["subgoal_progress"]` (and `subgoals_done`): LADDER's subgoal score at the end of the episode, each subgoal met in the final state and, for an object moved twice, in order; all of them once the task succeeded. `reward` is its change at each step, so `avg_sum_reward` in LeRobot is the mean final progress |
|
| 52 |
-
|
| 53 |
-
Options, passed as `--env.make_env_kwargs='{...}'` (`--sim.kwargs='{make_env_kwargs: {...}}'` for the server): `front_camera_name` (default `main`). The camera renders at 480x640, as in LADDER.
|
| 54 |
-
|
| 55 |
-
## How it relates to LADDER
|
| 56 |
-
|
| 57 |
-
`ladder/` is LADDER's own code at release [`v1.0.0`](https://github.com/insait-institute/ladder/releases/tag/v1.0.0), unchanged: the task definitions, scene layouts and success predicates. `env.py` builds the suite's environment with the settings of LADDER's own server config (`widowx_composition.yaml`). The simulation assets and SAPIEN's PhysX library are downloaded from that release on first use (about 160 MB, checked by sha256) into `~/.cache/ladder/envhub` (`LADDER_CACHE` moves it).
|
| 58 |
-
|
| 59 |
-
The full suite is all 54 tasks with 24 episodes each. LADDER's own harness (`scripts/eval.sh`) stays the reference for leaderboard results; see [EVALUATION.md](https://github.com/insait-institute/ladder/blob/main/EVALUATION.md).
|
| 60 |
|
| 61 |
-
##
|
| 62 |
|
| 63 |
-
- The reset frames match LADDER's recorded episodes
|
| 64 |
-
- LADDER's Bridge policy, run through this repository's Docker image with LADDER's own policy server and client settings, on 4 tasks (`all1_towel`, `split2`, `ordered_plate_2`, `spoons2`; 96 episodes), succeeded in 60 and 64 of 96 episodes in two runs. LADDER's published episodes of the same tasks: 59 of 96.
|
| 65 |
|
| 66 |
## Citation
|
| 67 |
|
|
@@ -77,4 +57,4 @@ The full suite is all 54 tasks with 24 episodes each. LADDER's own harness (`scr
|
|
| 77 |
|
| 78 |
## License
|
| 79 |
|
| 80 |
-
MIT, as LADDER.
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
library_name: lerobot
|
| 4 |
+
tags: [lerobot, envhub, robotics, simulation, benchmark, ladder, widowx, maniskill, sapien]
|
| 5 |
---
|
| 6 |
|
| 7 |
# LADDER SimplerEnv-Long
|
| 8 |
|
| 9 |
+
54 WidowX tasks of 1 to 10 pick-and-place subgoals in the Bridge digital twin of SimplerEnv, on SAPIEN 3 / ManiSkill 3. It is one of the three suites of [LADDER](https://ladderrobotics.ai), a long-horizon manipulation benchmark, packaged as a LeRobot [EnvHub](https://huggingface.co/docs/lerobot/envhub) environment. Each simulator needs its own Python environment, so each suite is its own repository:
|
| 10 |
|
| 11 |
+
| Suite | Repository | Simulator | Robot | Tasks |
|
| 12 |
+
|---|---|---|---|---|
|
| 13 |
+
| RoboLab-Long | [`INSAIT-Institute/LADDER-RoboLab-Long`](https://huggingface.co/INSAIT-Institute/LADDER-RoboLab-Long) | Isaac Sim 6 | Franka (DROID) | 44 |
|
| 14 |
+
| SimplerEnv-Long | this one | SAPIEN 3 / ManiSkill 3 | WidowX | 54 |
|
| 15 |
+
| RobotArena-∞-Long | [`INSAIT-Institute/LADDER-RobotArena-Long`](https://huggingface.co/INSAIT-Institute/LADDER-RobotArena-Long) | Genesis | WidowX | 47 |
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Evaluate a policy
|
| 18 |
|
| 19 |
+
From a LeRobot checkout, with Docker and the NVIDIA Container Toolkit:
|
| 20 |
|
| 21 |
```bash
|
| 22 |
+
pip install -e ".[dataset,evaluation,remote]" # plus your policy's extra
|
| 23 |
lerobot-env-server --envhub=INSAIT-Institute/LADDER-SimplerEnv-Long@v1.0.0 --docker=true
|
| 24 |
lerobot-eval --policy.path=<your WidowX checkpoint> \
|
| 25 |
--env.type=envhub --env.hub_path=INSAIT-Institute/LADDER-SimplerEnv-Long@v1.0.0 \
|
| 26 |
+
--env.server.endpoint=tcp/127.0.0.1:7448 --env.task=all2_plate \
|
| 27 |
+
--eval.batch_size=24 --eval.n_episodes=24 --eval.use_async_envs=false
|
| 28 |
```
|
| 29 |
|
| 30 |
+
- `--env.task` takes a task, a comma-separated list, or nothing for the whole suite ([task list](https://github.com/insait-institute/ladder/blob/main/TASKS.md)). A task's 24 episodes run as one batch, so keep the batch size at 24.
|
| 31 |
+
- To run it in-process instead, `pip install "lerobot[dataset,evaluation]>=0.7.0" -r requirements.txt` and replace `--env.server.endpoint` with `--env.trust_remote_code=true`.
|
|
|
|
|
|
|
|
|
|
| 32 |
|
| 33 |
+
## Interface
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
| | |
|
| 36 |
|---|---|
|
| 37 |
+
| Observation | `pixels.main`: 480x640 RGB; `agent_pos`: end-effector pose `[x, y, z, rx, ry, rz]` (base frame, axis-angle, BridgeData convention) and gripper (1 open) |
|
| 38 |
+
| Action | `[dx, dy, dz, drx, dry, drz, gripper]`: translation in the base frame, rotation in the end-effector frame, applied to the commanded pose as LADDER runs its Bridge policy; gripper 1 open, 0 closed |
|
| 39 |
| Control rate | 5 Hz |
|
| 40 |
+
| Score | `pc_success`: LADDER's task success. `avg_sum_reward`: its subgoal progress at the end of the episode (also `info["metrics"]["subgoal_progress"]`) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
+
## Relation to LADDER
|
| 43 |
|
| 44 |
+
`ladder/` is LADDER's code at release [v1.0.0](https://github.com/insait-institute/ladder/releases/tag/v1.0.0), unchanged, run with the settings of LADDER's own server. The simulation assets (160 MB) are downloaded from that release on first use. Its reset frames match LADDER's recorded episodes, and LADDER's Bridge policy run through it succeeds as often as in LADDER's published episodes (60 and 64 of 96 against 59 on four tasks). LADDER's own harness stays the reference for the [leaderboard](https://ladderrobotics.ai).
|
|
|
|
| 45 |
|
| 46 |
## Citation
|
| 47 |
|
|
|
|
| 57 |
|
| 58 |
## License
|
| 59 |
|
| 60 |
+
MIT, as LADDER. Downloaded assets keep their own licenses ([THIRD_PARTY_NOTICES.md](https://github.com/insait-institute/ladder/blob/main/THIRD_PARTY_NOTICES.md)).
|