{
"model": "lightnav",
"checkpoint": "/home/siqiteam/real_baseline_deploy/assets/final/lightnav_real/checkpoint",
"ready": true,
"busy": false,
"episode": null,
"worker": {
"status": "ready",
"model": "lightnav",
"load_seconds": 24.980417925864458,
"checkpoint": "/home/siqiteam/real_baseline_deploy/assets/final/lightnav_real/checkpoint",
"load_count": 1,
"device_name": "NVIDIA RTX PRO 6000 Blackwell Workstation Edition"
},
"robot_calibrated": true
}Episodes ยท Download episode{
"schema": "real-baseline-v1",
"model": "lightnav",
"checkpoint": "/home/siqiteam/real_baseline_deploy/assets/final/lightnav_real/checkpoint",
"epoch": 18,
"step": 246474,
"instruction": "go to the vending machine",
"client_plan": [
"go to the vending machine"
],
"task_condition": "full original instruction; supplied stages logged only",
"configuration": {
"model": "lightnav",
"project": "/home/siqiteam/real_baseline_deploy/final_service_state/project",
"checkpoint": "/home/siqiteam/real_baseline_deploy/assets/final/lightnav_real/checkpoint",
"epoch": 18,
"step": 246474,
"worker_python": "/home/siqiteam/real_baseline_deploy/envs/lightnav/bin/python",
"host": "127.0.0.1",
"ws_port": 5931,
"http_port": 5930,
"seed": 42,
"wire_horizon": 12,
"action_semantics": "body_increment_goals",
"action_dt_s": null,
"robot_calibrated": true,
"require_timestamps": true,
"log_root": "/home/siqiteam/real_baseline_deploy/lightnav/final_logs"
},
"worker": {
"status": "ready",
"model": "lightnav",
"load_seconds": 25.280952685978264,
"checkpoint": "/home/siqiteam/real_baseline_deploy/assets/final/lightnav_real/checkpoint",
"load_count": 1,
"device_name": "NVIDIA RTX PRO 6000 Blackwell Workstation Edition"
},
"status": "closed",
"started_at": 1792325410.229633,
"units": "m_m_rad",
"robot_execution_tested": false,
"ended_at": 1792325421.2161007,
"end_reason": "disconnect"
}
Local predicted trajectory; measured poses are in trajectory.json.
{
"instruction": "go to the vending machine",
"all_observations": [
{
"path": "/home/siqiteam/real_baseline_deploy/lightnav/final_logs/episode-20261018-201010-2ce28693/steps/000000/input-000.jpg",
"sha256": "d000031be1af9b56d75ec22b30b114ba7af677e5454b3c4b237e0f25dbb0f8c6",
"pose": [
3.208214276128708e-06,
-0.00010164785147984117,
-6.020135889306388e-05
],
"timestamp": 3823.175736498,
"observation_id": 0
}
],
"time_resampled_indices": [
0
],
"model": "lightnav",
"pose_conditioning": "not fed to these REAL adapters",
"client_plan_used": false,
"history_sampling": {
"method": "nearest captured observation per occupied 4Hz bin; empty bins omitted",
"max_capture_gap_s": 0.0,
"unobserved_time_filled": false
},
"history_indices": [
0
],
"segments": [
{
"indices": [
0,
0
],
"tensor": "processed/segment0.pt",
"shape": [
2,
3,
256,
448
]
}
],
"prompt": "<|im_start|>user\nYou are a mobile robot. You are given visual observations over time, ordered from earliest to most recent:<0.0 seconds><|vision_start|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|vision_end|>. Your assigned task is: <navigation_task>go to the vending machine</navigation_task>. You may be at the beginning, middle, or end of the task. Predict your future trajectory as a sequence of coarse-to-fine trajectory tokens.<|im_end|>\n<|im_start|>assistant\n",
"tokenized": {
"input_ids": [
[
151644,
872,
198,
2610,
525,
264,
6371,
12305,
13,
1446,
525,
2661,
9124,
23722,
916,
882,
11,
11457,
504,
29658,
311,
1429,
3213,
31252,
15,
13,
15,
6486,
29,
151652,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151653,
13,
4615,
12607,
3383,
374,
25,
220,
151669,
3346,
311,
279,
85044,
5662,
151670,
13,
1446,
1231,
387,
518,
279,
7167,
11,
6149,
11,
476,
835,
315,
279,
3383,
13,
32710,
697,
3853,
34682,
438,
264,
8500,
315,
49247,
4686,
2220,
482,
34682,
11211,
13,
151645,
198,
151644,
77091,
198
]
],
"decoded": "<|im_start|>user\nYou are a mobile robot. You are given visual observations over time, ordered from earliest to most recent:<0.0 seconds><|vision_start|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|vision_end|>. Your assigned task is: <navigation_task>go to the vending machine</navigation_task>. You may be at the beginning, middle, or end of the task. Predict your future trajectory as a sequence of coarse-to-fine trajectory tokens.<|im_end|>\n<|im_start|>assistant\n",
"tensor_shapes": {
"input_ids": [
1,
193
],
"attention_mask": [
1,
193
],
"pixel_values_videos": [
1,
448,
1536
],
"video_grid_thw": [
1,
3
],
"_original_video_grid_thw": [
1,
3
],
"_post_vit_pool_factors": [
1
],
"position_ids": [
1,
3,
193
],
"mm_token_type_ids": [
1,
193
]
}
},
"history_fps": 4,
"model_history_refs": [
{
"path": "/home/siqiteam/real_baseline_deploy/lightnav/final_logs/episode-20261018-201010-2ce28693/steps/000000/input-000.jpg",
"sha256": "d000031be1af9b56d75ec22b30b114ba7af677e5454b3c4b237e0f25dbb0f8c6",
"pose": [
3.208214276128708e-06,
-0.00010164785147984117,
-6.020135889306388e-05
],
"timestamp": 3823.175736498,
"observation_id": 0
}
]
}
<|im_start|>user You are a mobile robot. You are given visual observations over time, ordered from earliest to most recent:<0.0 seconds><|vision_start|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|vision_end|>. Your assigned task is: <navigation_task>go to the vending machine</navigation_task>. You may be at the beginning, middle, or end of the task. Predict your future trajectory as a sequence of coarse-to-fine trajectory tokens.<|im_end|> <|im_start|>assistant
{
"status": "ok",
"native": {
"actions": [
[
0.003880070988088846,
-0.0006173825240693986,
-0.153917595744133
],
[
0.13614977704023443,
-0.006653214997101399,
-0.034516796469688416
],
[
0.12757471000686638,
0.0005417941410907866,
0.009060859680175781
],
[
0.1130857682462753,
-0.0001628643946197661,
0.013548880815505981
],
[
0.09295031146686485,
0.00023206226977606943,
0.021091431379318237
],
[
0.0863873379617972,
0.000478625117296733,
0.019159898161888123
],
[
0.07455663533718318,
-0.0007812499343987159,
-0.005159646272659302
],
[
0.14160241596075154,
0.0019392904863219755,
0.016178756952285767
],
[
0.10093083046644699,
-5.7324175960403456e-05,
0.015215307474136353
],
[
0.024339954038765824,
-1.82983541914092e-05,
0.005247347056865691
]
],
"stop": false,
"plan": null,
"raw": "<apos_1133><opos_604><act_l0_3><act_l1_53><act_l2_150><|im_end|>",
"waypoints": [
[
0.003880070988088846,
-0.0006173825240693986,
-0.153917595744133
],
[
0.137400284409523,
-0.028065145015716553,
-0.1884343922138214
],
[
0.26281824707984924,
-0.051430393010377884,
-0.17937353253364563
],
[
0.37406057119369507,
-0.07176663726568222,
-0.16582465171813965
],
[
0.46577414870262146,
-0.08688066899776459,
-0.1447332203388214
],
[
0.5513272881507874,
-0.09886655956506729,
-0.1255733221769333
],
[
0.625199019908905,
-0.10897939652204514,
-0.1307329684495926
],
[
0.7658458948135376,
-0.12551607191562653,
-0.11455421149730682
],
[
0.8661086559295654,
-0.13710980117321014,
-0.09933890402317047
],
[
0.8903267979621887,
-0.13954193890094757,
-0.09409155696630478
]
],
"pointing": {
"apos": 1133,
"opos": 604
},
"rvq_codes": [
3,
53,
150
],
"model_input": {
"history_indices": [
0
],
"segments": [
{
"indices": [
0,
0
],
"tensor": "processed/segment0.pt",
"shape": [
2,
3,
256,
448
]
}
],
"prompt": "<|im_start|>user\nYou are a mobile robot. You are given visual observations over time, ordered from earliest to most recent:<0.0 seconds><|vision_start|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|vision_end|>. Your assigned task is: <navigation_task>go to the vending machine</navigation_task>. You may be at the beginning, middle, or end of the task. Predict your future trajectory as a sequence of coarse-to-fine trajectory tokens.<|im_end|>\n<|im_start|>assistant\n",
"tokenized": {
"input_ids": [
[
151644,
872,
198,
2610,
525,
264,
6371,
12305,
13,
1446,
525,
2661,
9124,
23722,
916,
882,
11,
11457,
504,
29658,
311,
1429,
3213,
31252,
15,
13,
15,
6486,
29,
151652,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151656,
151653,
13,
4615,
12607,
3383,
374,
25,
220,
151669,
3346,
311,
279,
85044,
5662,
151670,
13,
1446,
1231,
387,
518,
279,
7167,
11,
6149,
11,
476,
835,
315,
279,
3383,
13,
32710,
697,
3853,
34682,
438,
264,
8500,
315,
49247,
4686,
2220,
482,
34682,
11211,
13,
151645,
198,
151644,
77091,
198
]
],
"decoded": "<|im_start|>user\nYou are a mobile robot. You are given visual observations over time, ordered from earliest to most recent:<0.0 seconds><|vision_start|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|video_pad|><|vision_end|>. Your assigned task is: <navigation_task>go to the vending machine</navigation_task>. You may be at the beginning, middle, or end of the task. Predict your future trajectory as a sequence of coarse-to-fine trajectory tokens.<|im_end|>\n<|im_start|>assistant\n",
"tensor_shapes": {
"input_ids": [
1,
193
],
"attention_mask": [
1,
193
],
"pixel_values_videos": [
1,
448,
1536
],
"video_grid_thw": [
1,
3
],
"_original_video_grid_thw": [
1,
3
],
"_post_vit_pool_factors": [
1
],
"position_ids": [
1,
3,
193
],
"mm_token_type_ids": [
1,
193
]
}
},
"history_fps": 4
},
"native_latency_ms": 1198.890884872526
},
"response": {
"type": "step",
"actions": [
[
0.003880070988088846,
-0.0006173825240693986,
-0.153917595744133
],
[
0.13614977704023443,
-0.006653214997101399,
-0.034516796469688416
],
[
0.12757471000686638,
0.0005417941410907866,
0.009060859680175781
],
[
0.1130857682462753,
-0.0001628643946197661,
0.013548880815505981
],
[
0.09295031146686485,
0.00023206226977606943,
0.021091431379318237
],
[
0.0863873379617972,
0.000478625117296733,
0.019159898161888123
],
[
0.07455663533718318,
-0.0007812499343987159,
-0.005159646272659302
],
[
0.14160241596075154,
0.0019392904863219755,
0.016178756952285767
],
[
0.10093083046644699,
-5.7324175960403456e-05,
0.015215307474136353
],
[
0.024339954038765824,
-1.82983541914092e-05,
0.005247347056865691
],
[
0.0,
0.0,
0.0
],
[
0.0,
0.0,
0.0
]
],
"stop": false,
"plan": null,
"valid_actions": 10,
"action_semantics": "body_increment_goals",
"action_dt_s": null,
"units": "m_m_rad",
"robot_ready": true,
"padding": "zero_tail_not_stop",
"stop_semantics": "no_terminal_claim",
"episode_id": "episode-20261018-201010-2ce28693",
"inference_id": 0,
"model": "lightnav",
"model_inference_executed": true
},
"model_seconds": 1.4103667479939759,
"peak_memory_bytes": 9155978752,
"allocated_memory_bytes": 9095067648,
"reserved_memory_bytes": 9279897600,
"load_count": 1,
"total_seconds": 1.4207102861255407
}
{
"frame": "m_m_rad",
"local_prediction": [
[
0.0,
0.0,
0.0
],
[
0.003880070988088846,
-0.0006173825240693986,
-0.153917595744133
],
[
0.137400284409523,
-0.028065145015716553,
-0.1884343922138214
],
[
0.26281824707984924,
-0.05143039301037789,
-0.17937353253364566
],
[
0.37406057119369507,
-0.07176663726568222,
-0.1658246517181397
],
[
0.46577414870262146,
-0.08688066899776459,
-0.14473322033882147
],
[
0.5513272881507874,
-0.09886655956506729,
-0.12557332217693334
],
[
0.625199019908905,
-0.10897939652204515,
-0.13073296844959265
],
[
0.7658458948135376,
-0.12551607191562655,
-0.11455421149730688
],
[
0.8661086559295654,
-0.13710980117321017,
-0.09933890402317053
],
[
0.8903267979621887,
-0.1395419389009476,
-0.09409155696630483
]
],
"observed_poses": [
[
3.208214276128708e-06,
-0.00010164785147984117,
-6.020135889306388e-05
]
]
}