Skip to content
2019 Renault internship. A RNN_RBM model for vehicule trajectory patterns learning
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Unsupervised Vehicle Trajectory learning in multi-lanes highway

by Yingjie Jiang

This is an adapted variaiton of RNN-RBM for unsupervised vehicle trajectory pattern learning on a multi-lanes highway. The dataset used is US Highway 101.

fig1. trajectory dataset captured by camera set in US highway 101

Unlike the original RNN-RBM, this is a model which performs well for real-valued dataset. After training, it can memorize a given vehicle trajectories pattern on a specific route, which can be used to reconstruct vehicle trajectories based on a input dataset polluted by noise.


The structure of RNN-RBM(Nicolas Boulanger-Lewandowski et al.) is illustred below: RNN_RBM

fig2. structure of RNN_RBM

Put the input trajectories dataset (eg. "trajectories-0750am-0805am.csv" of US Highway 101) in the directory "./ngsim_data/ "

  1. python # pretreatement of dataset

  2. python # pre-training of RBM Neural networks

  3. python <num_epoch> # training, num_epoch can be about 10

  4. python ./parameter_checkpoints/<fichier .ckpt> # reconstruction of trajectories

The output picture is stocked in "./picture_folder".

There are different versions of ngsim_manipulation, as well as for rnn_rbm, RBM, draw, they deal with different situations. For using them, rename them(delete the version notation).

One demonstration of noise reduction:

fig3. The red lines are noised trajectories, and the lines with other colors are reconstructed trajectories by RNN-RBM.

Further work can be conducted, for example, changing the standard RNN by LSTM, or changing RBM by DBN, etc.

You can’t perform that action at this time.