You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
#### IMPORTANT: The file structure has changed! Please check [Dataset Setup](https://github.com/motional/nuplan-devkit/blob/master/docs/dataset_setup.md) page for the updated file structure.
35
+
- The nuPlan sensor data for the v1.1 dataset has been released. Please download the latest dataset from the nuPlan [page](https://www.nuscenes.org/nuplan#download).
36
+
- Due to the size of the sensor data, it will be released gradually. This first set of sensor data are the blobs corresponding to nuPlan mini.
37
+
- A short tutorial for the sensor data is provided `nuplan_sensor_data_tutorial.ipynb` to get you started.
#### The challenge will be presented as part of the [New Advances On Autonomous Driving](https://opendrivelab.com/event/cvpr23_ADworkshop) workshop at CVPR 2023
36
-
#### The nuPlan Dataset v1.1 has been released. Please download the latest dataset from the nuPlan [page](https://www.nuscenes.org/nuplan#download).
40
+
#### IMPORTANT: The Planning Challenge will be using devkit version 1.2 from now on. Submissions generated from version v1.1 should remain compatible. However, please double-check by submitting to the warm-up phase.
41
+
- The nuPlan Planning Competition is live!
42
+
- The challenge will be presented as part of the [New Advances On Autonomous Driving](https://opendrivelab.com/event/cvpr23_ADworkshop) workshop at CVPR 2023
43
+
- The nuPlan Dataset v1.1 has been released. Please download the latest dataset from the nuPlan [page](https://www.nuscenes.org/nuplan#download).
* v1.2 Devkit: The nuPlan sensor data have been released! Improved feature caching and nuBoard dashboard functionality. Changed dataset file structure, data interfaces now allow retrieval of sensor data. Pinned several packages including hydra, numpy and sqlalchemy.
49
+
- January 20th 2023
41
50
* v1.1 Devkit: The official nuPlan Challenge Release. Optimized training caching, simulation improvements, shapely 2.0 update.
42
51
- Oct 13th 2022
43
52
* v1.1 Dataset: Full nuPlan dataset - improved route plan, traffic light status, mission goal and more!
Copy file name to clipboardExpand all lines: docs/baselines.md
+15-1Lines changed: 15 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -27,4 +27,18 @@ go based on the distance between itself and a given agent. Of course, it is wise
27
27
28
28
Hence, the IDMPlanner uses breadth-first search to find the path towards the mission goal, and the IDM policy describes how far along that path the planner should be.
29
29
30
-
Link to the [code](https://github.com/motional/nuplan-devkit/blob/master/nuplan/planning/simulation/planner/idm_planner.py)
30
+
Link to the [code](https://github.com/motional/nuplan-devkit/blob/master/nuplan/planning/simulation/planner/idm_planner.py)
31
+
32
+
## UrbanDriverOpenLoopModel (MLPlanner)
33
+
The UrbanDriverOpenLoopModel functions as an example trained machine learning planner using the `MLPlanner` interface.
34
+
The implementation is an open-loop version of L5Kit's [implementation](https://github.com/woven-planet/l5kit/blob/master/l5kit/l5kit/planning/vectorized/open_loop_model.py)
35
+
of ["Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients"](https://woven-planet.github.io/l5kit/urban_driver.html)
36
+
adapted to the nuPlan framework.
37
+
38
+
The model processes vectorized agent and map inputs into local feature descriptors that
39
+
are passed to a global attention mechanism for yielding a predicted ego trajectory. The model is trained using imitation
40
+
learning to match expert trajectories available in the nuPlan dataset. Some amount of data augmentation is performed on
41
+
the agents and expert trajectory provided during training to mitigate data distribution drift encountered during
42
+
closed-loop simulation.
43
+
44
+
Link to the [code](https://github.com/motional/nuplan-devkit/blob/master/nuplan/planning/training/modeling/models/urban_driver_open_loop_model.py)
Copy file name to clipboardExpand all lines: docs/competition.md
+5-5Lines changed: 5 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -12,10 +12,10 @@ The main focus of the nuPlan planning challenge is to evaluate a motion planning
12
12
### Competition Timeline
13
13
14
14
* January 30th, 2023 - Warm-up phase and Test phase opens for submission
15
-
* May 18th, 2023 - Competition closes
16
-
* May 19th, 2023 - Finalists are announced and invited to share their code with us for verification
15
+
* May 19th, 2023 - Competition closes
16
+
* May 26th, 2023 - Finalists are announced and invited to share their code with us for verification
17
17
* June 2th, 2023 - Winners are announced
18
-
* June 18th, 2023 - The competition results are presented at the [New Advances On Autonomous Driving](https://opendrivelab.com/event/cvpr23_ADworkshop) workshop at CVPR 2023
18
+
* June 18th, 2023 - The competition results are presented at the [End-to-End Autonomous Driving](https://opendrivelab.com/event/cvpr23_ADworkshop) workshop at CVPR 2023
19
19
20
20
21
21
### How to enter
@@ -76,7 +76,7 @@ and the data is not taken from the test split. The metrics and the overall score
76
76
77
77
Start: January 30th, 2023
78
78
79
-
End: May 18th, 2023
79
+
End: May 19th, 2023
80
80
81
81
#### Test Phase
82
82
The results from the test phase will be used to determine the winners of each challenge. All submissions will be evaluated on a
@@ -87,7 +87,7 @@ submit a maximum of three submissions.
Copy file name to clipboardExpand all lines: docs/dataset_setup.md
+34-10Lines changed: 34 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -33,16 +33,40 @@ The final hierarchy should look as follows (depending on the splits downloaded a
33
33
│ └── 9.17.1937
34
34
│ └── map.gpkg
35
35
└── nuplan-v1.1
36
-
├── mini
37
-
│ ├── 2021.05.12.22.00.38_veh-35_01008_01518.db
38
-
│ ├── 2021.06.09.17.23.18_veh-38_00773_01140.db
39
-
│ ├── ...
40
-
│ └── 2021.10.11.08.31.07_veh-50_01750_01948.db
41
-
└── trainval
42
-
├── 2021.05.12.22.00.38_veh-35_01008_01518.db
43
-
├── 2021.06.09.17.23.18_veh-38_00773_01140.db
44
-
├── ...
45
-
└── 2021.10.11.08.31.07_veh-50_01750_01948.db
36
+
├── splits
37
+
│ ├── mini
38
+
│ │ ├── 2021.05.12.22.00.38_veh-35_01008_01518.db
39
+
│ │ ├── 2021.06.09.17.23.18_veh-38_00773_01140.db
40
+
│ │ ├── ...
41
+
│ │ └── 2021.10.11.08.31.07_veh-50_01750_01948.db
42
+
│ └── trainval
43
+
│ ├── 2021.05.12.22.00.38_veh-35_01008_01518.db
44
+
│ ├── 2021.06.09.17.23.18_veh-38_00773_01140.db
45
+
│ ├── ...
46
+
│ └── 2021.10.11.08.31.07_veh-50_01750_01948.db
47
+
└── sensor_blobs
48
+
├── 2021.05.12.22.00.38_veh-35_01008_01518
49
+
│ ├── CAM_F0
50
+
│ │ ├── c082c104b7ac5a71.jpg
51
+
│ │ ├── af380db4b4ca5d63.jpg
52
+
│ │ ├── ...
53
+
│ │ └── 2270fccfb44858b3.jpg
54
+
│ ├── CAM_B0
55
+
│ ├── CAM_L0
56
+
│ ├── CAM_L1
57
+
│ ├── CAM_L2
58
+
│ ├── CAM_R0
59
+
│ ├── CAM_R1
60
+
│ ├── CAM_R2
61
+
│ └──MergedPointCloud
62
+
│ ├── 03fafcf2c0865668.pcd
63
+
│ ├── 5aee37ce29665f1b.pcd
64
+
│ ├── ...
65
+
│ └── 5fe65ef6a97f5caf.pcd
66
+
│
67
+
├── 2021.06.09.17.23.18_veh-38_00773_01140
68
+
├── ...
69
+
└── 2021.10.11.08.31.07_veh-50_01750_01948
46
70
```
47
71
48
72
If you want to use another folder, you can set the corresponding [environment variable](https://github.com/motional/nuplan-devkit/blob/master/docs/installation.md).
0 commit comments