Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_episode_3.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,133 @@
+---
+license: apache-2.0
+library_name: lerobot
+tags:
+  - robotics
+  - imitation-learning
+  - aloha
+  - act
+  - lerobot
+datasets:
+  - lerobot/aloha_sim_insertion_human_image
+pipeline_tag: robotics
+---
+
+# ACT Model for ALOHA Insertion Task
+
+A lightweight Action Chunking with Transformers (ACT) model trained on the ALOHA simulation Insertion task. This is a **difficult bimanual coordination task** with lower success rate compared to TransferCube.
+
+## Model Description
+
+| Property | Value |
+|----------|-------|
+| Architecture | ACT (Action Chunking with Transformers) |
+| Parameters | 52M |
+| Task | ALOHA Insertion-v0 |
+| Training Steps | 200,000 |
+| Batch Size | 32 |
+| Success Rate | ~15% |
+
+## Training Data
+
+- **Dataset**: [lerobot/aloha_sim_insertion_human_image](https://huggingface.co/datasets/lerobot/aloha_sim_insertion_human_image)
+- **Episodes**: 50 human demonstrations
+- **Frames**: 20,000
+
+## Task Description
+
+The Insertion task requires a bimanual robot to:
+1. Pick up a socket with the left arm
+2. Pick up a peg with the right arm
+3. Insert the peg into the socket in mid-air
+
+⚠️ **This is a difficult task** requiring precise bimanual coordination. Success rate is significantly lower than TransferCube.
+
+## Demo Video
+
+<video controls src="eval_episode_3.mp4" title="Insertion Demo"></video>
+
+## Training Environment
+
+- **GPU**: RTX A6000
+- **Framework**: LeRobot 0.4.3
+- **Training Time**: Around 13 hours
+
+## Usage
+
+### Installation
+```bash
+pip install lerobot gym-aloha
+```
+
+### Training
+```bash
+lerobot-train \
+    --policy.type=act \
+    --dataset.repo_id=lerobot/aloha_sim_insertion_human_image \
+    --env.type=aloha \
+    --env.task=AlohaInsertion-v0 \
+    --batch_size=32 \
+    --steps=200000 \
+    --eval.n_episodes=10 \
+    --eval_freq=20000 \
+    --save_freq=20000 \
+    --output_dir=./outputs/act_aloha_insertion \
+    --wandb.enable=false \
+    --policy.push_to_hub=false
+```
+
+### Evaluation
+```bash
+lerobot-eval \
+    --policy.path=LeTau/act_aloha_insertion \
+    --env.type=aloha \
+    --env.task=AlohaInsertion-v0 \
+    --eval.batch_size=1 \
+    --eval.n_episodes=20
+```
+
+### Fine-tuning
+```bash
+lerobot-train \
+    --resume=true \
+    --config_path=LeTau/act_aloha_insertion/train_config.json \
+    --steps=300000
+```
+
+## Results
+
+| Evaluation | Episodes | Success Rate | Avg Sum Reward |
+|------------|----------|--------------|----------------|
+| Training (120K) | 10 | 10% | 40.3 |
+| Training (200K) | 10 | 20% | 40.4 |
+| Independent | 20 | 15% | 51.2 |
+
+**Expected success rate: 15-20%**
+
+### Task Difficulty Comparison
+
+| Task | Difficulty | Success Rate |
+|------|------------|--------------|
+| TransferCube | Easy | 35-42% |
+| **Insertion** | **Hard** | **15-20%** |
+
+## Detailed Evaluation Results (Independent)
+```
+Sum Rewards: [0.0, 0.0, 0.0, 240.0, 121.0, 0.0, 0.0, 0.0, 43.0, 0.0,
+              256.0, 0.0, 0.0, 321.0, 0.0, 0.0, 0.0, 0.0, 43.0, 0.0]
+
+Successes: 3/20 episodes
+```
+
+## Limitations
+
+- **Difficult task**: Insertion requires precise bimanual coordination
+- **Limited training data**: Only 50 demonstration episodes available
+- **Low success rate**: This is a baseline model for a challenging task
+- **Single task**: Only trained on Insertion, no multi-task capability
+
+
+## Acknowledgments
+
+- [LeRobot](https://github.com/huggingface/lerobot) framework by HuggingFace
+- [ALOHA](https://tonyzhaozh.github.io/aloha/) project by Stanford

config.json

@@ -0,0 +1,62 @@
+{
+    "type": "act",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                14
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                14
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "push_to_hub": false,
+    "repo_id": "LeTau/act_aloha_insertion",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "outputs/act_aloha_insertion/checkpoints/120000/pretrained_model",
+    "chunk_size": 100,
+    "n_action_steps": 100,
+    "normalization_mapping": {
+        "VISUAL": "MEAN_STD",
+        "STATE": "MEAN_STD",
+        "ACTION": "MEAN_STD"
+    },
+    "vision_backbone": "resnet18",
+    "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+    "replace_final_stride_with_dilation": 0,
+    "pre_norm": false,
+    "dim_model": 512,
+    "n_heads": 8,
+    "dim_feedforward": 3200,
+    "feedforward_activation": "relu",
+    "n_encoder_layers": 4,
+    "n_decoder_layers": 1,
+    "use_vae": true,
+    "latent_dim": 32,
+    "n_vae_encoder_layers": 4,
+    "temporal_ensemble_coeff": null,
+    "dropout": 0.1,
+    "kl_weight": 10.0,
+    "optimizer_lr": 1e-05,
+    "optimizer_weight_decay": 0.0001,
+    "optimizer_lr_backbone": 1e-05
+}

eval_episode_3.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f765663c13d22619e353e75779529613058ebb15194bbf5067605b1f95edf33
+size 209726

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebfbc706321db770c2d70705ca1ebf451854b2f3a42b44f56ded21404edd9249
+size 206765304

policy_postprocessor.json

@@ -0,0 +1,32 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              14
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "MEAN_STD",
+          "STATE": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

policy_postprocessor_step_0_unnormalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6a772396a0edb89347d065ba58e3e5f5ad853b2629db0527554ee54ad13be7
+size 3892

policy_preprocessor.json

@@ -0,0 +1,56 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {}
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              480,
+              640
+            ]
+          },
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              14
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              14
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "MEAN_STD",
+          "STATE": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
+    }
+  ]
+}

policy_preprocessor_step_3_normalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6a772396a0edb89347d065ba58e3e5f5ad853b2629db0527554ee54ad13be7
+size 3892

train_config.json

@@ -0,0 +1,230 @@
+{
+    "dataset": {
+        "repo_id": "lerobot/aloha_sim_insertion_human_image",
+        "root": null,
+        "episodes": null,
+        "image_transforms": {
+            "enable": false,
+            "max_num_transforms": 3,
+            "random_order": false,
+            "tfs": {
+                "brightness": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "brightness": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "contrast": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "contrast": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "saturation": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "saturation": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "hue": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "hue": [
+                            -0.05,
+                            0.05
+                        ]
+                    }
+                },
+                "sharpness": {
+                    "weight": 1.0,
+                    "type": "SharpnessJitter",
+                    "kwargs": {
+                        "sharpness": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "affine": {
+                    "weight": 1.0,
+                    "type": "RandomAffine",
+                    "kwargs": {
+                        "degrees": [
+                            -5.0,
+                            5.0
+                        ],
+                        "translate": [
+                            0.05,
+                            0.05
+                        ]
+                    }
+                }
+            }
+        },
+        "revision": null,
+        "use_imagenet_stats": true,
+        "video_backend": "torchcodec",
+        "streaming": false
+    },
+    "env": {
+        "type": "aloha",
+        "task": "AlohaInsertion-v0",
+        "fps": 50,
+        "features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    14
+                ]
+            },
+            "agent_pos": {
+                "type": "STATE",
+                "shape": [
+                    14
+                ]
+            },
+            "pixels/top": {
+                "type": "VISUAL",
+                "shape": [
+                    480,
+                    640,
+                    3
+                ]
+            }
+        },
+        "features_map": {
+            "action": "action",
+            "agent_pos": "observation.state",
+            "top": "observation.image.top",
+            "pixels/top": "observation.images.top"
+        },
+        "max_parallel_tasks": 1,
+        "disable_env_checker": true,
+        "episode_length": 400,
+        "obs_type": "pixels_agent_pos",
+        "observation_height": 480,
+        "observation_width": 640,
+        "render_mode": "rgb_array"
+    },
+    "policy": {
+        "type": "act",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.top": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    14
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    14
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "push_to_hub": false,
+        "repo_id": "LeTau/act_aloha_insertion",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "outputs/act_aloha_insertion/checkpoints/120000/pretrained_model",
+        "chunk_size": 100,
+        "n_action_steps": 100,
+        "normalization_mapping": {
+            "VISUAL": "MEAN_STD",
+            "STATE": "MEAN_STD",
+            "ACTION": "MEAN_STD"
+        },
+        "vision_backbone": "resnet18",
+        "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+        "replace_final_stride_with_dilation": 0,
+        "pre_norm": false,
+        "dim_model": 512,
+        "n_heads": 8,
+        "dim_feedforward": 3200,
+        "feedforward_activation": "relu",
+        "n_encoder_layers": 4,
+        "n_decoder_layers": 1,
+        "use_vae": true,
+        "latent_dim": 32,
+        "n_vae_encoder_layers": 4,
+        "temporal_ensemble_coeff": null,
+        "dropout": 0.1,
+        "kl_weight": 10.0,
+        "optimizer_lr": 1e-05,
+        "optimizer_weight_decay": 0.0001,
+        "optimizer_lr_backbone": 1e-05
+    },
+    "output_dir": "outputs/act_aloha_insertion",
+    "job_name": "aloha_act",
+    "resume": true,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 32,
+    "steps": 200000,
+    "eval_freq": 20000,
+    "log_freq": 200,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 20000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 1e-05,
+        "weight_decay": 0.0001,
+        "grad_clip_norm": 10.0,
+        "betas": [
+            0.9,
+            0.999
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": null,
+    "eval": {
+        "n_episodes": 10,
+        "batch_size": 1,
+        "use_async_envs": false
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": null
+    },
+    "use_rabc": false,
+    "rabc_progress_path": null,
+    "rabc_kappa": 0.01,
+    "rabc_epsilon": 1e-06,
+    "rabc_head_mode": "sparse",
+    "rename_map": {},
+    "checkpoint_path": "outputs/act_aloha_insertion/checkpoints/120000"
+}