Home

Awesome

GRIP

This repository is the code of GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving on the Baidu Apollo Trajectory dataset. GRIP++ is an enhanced version of our GRIP (GRIP: Graph-based Interaction-aware Trajectory Prediction).


License

This code is shared only for research purposes, and this cannot be used for any commercial purposes.


Training

  1. Modify "data_root" in data_process.py and then run the script to preprocess the data.
$ python data_process.py
  1. Train the model. We trained the model on a single Nvidia Titan Xp GPU. If your GPU has the same precision, you should get the exact same results. The "training_log.txt" is my training log. If you download the code and run it directly, you should see similar outputs.
$ python main.py

# The following are the first 10 training iterations:
#######################################Train
# |2019-09-20 16:50:43.146035|     Epoch:   0/ 500|	Iteration:    0|	Loss:2.69767785|lr: 0.001|
# |2019-09-20 16:50:43.247776|     Epoch:   0/ 500|	Iteration:    0|	Loss:1.39082634|lr: 0.001|
# |2019-09-20 16:50:43.327926|     Epoch:   0/ 500|	Iteration:    0|	Loss:1.42024708|lr: 0.001|
# |2019-09-20 16:50:43.394658|     Epoch:   0/ 500|	Iteration:    0|	Loss:1.32363927|lr: 0.001|
# |2019-09-20 16:50:43.454833|     Epoch:   0/ 500|	Iteration:    0|	Loss:1.15358388|lr: 0.001|
# |2019-09-20 16:50:43.515517|     Epoch:   0/ 500|	Iteration:    0|	Loss:1.15672326|lr: 0.001|
# |2019-09-20 16:50:43.575027|     Epoch:   0/ 500|	Iteration:    0|	Loss:0.93675584|lr: 0.001|
# |2019-09-20 16:50:43.634769|     Epoch:   0/ 500|	Iteration:    0|	Loss:0.90181452|lr: 0.001|
# |2019-09-20 16:50:43.694374|     Epoch:   0/ 500|	Iteration:    0|	Loss:0.75979233|lr: 0.001|

Submission

Once you trained the model, you can test the trained models on the testing subset.

MethodEpochWSADEADEvADEpADEbWSFDEFDEvFDEpFDEb
TrafficPredict8.58817.94677.181112.880524.226212.775711.12122.7912
GRIPEpoch161.26322.25110.7181.80242.37134.08631.38383.4155
GRIPEpoch181.26482.25150.71421.81932.36774.08631.37323.4274
GRIPEpoch201.27212.240.7171.85582.39214.07621.37913.5318
GRIPCombine1.25882.24000.71421.80242.36314.07621.37323.4155

We use the following way to combine multiple results.


Citation

Please cite our papers if you used our code. Thanks.

@inproceedings{2019itsc_grip,
 author = {Li, Xin and Ying, Xiaowen and Chuah, Mooi Choo},
 booktitle = {2019 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC)},
 organization = {IEEE},
 title = {GRIP: Graph-based Interaction-aware Trajectory Prediction},
 year = {2019}
}

@article{li2020gripplus,
  title={GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving},
  author={Li, Xin and Ying, Xiaowen and Chuah, Mooi Choo},
  journal={arXiv preprint arXiv:1907.07792},
  year={2020}
}