EN FR
EN FR
RITS - 2019
New Software and Platforms
Bilateral Contracts and Grants with Industry
Bibliography
New Software and Platforms
Bilateral Contracts and Grants with Industry
Bibliography


Section: New Results

Attention mechanisms for vehicle trajectory prediction

Participants : Kaouther Messaoud, Fawzi Nashashibi, Anne Verroust-Blondet, Itheri Yahiaoui.

Scene understanding and future motion prediction of surrounding vehicles are crucial to achieve safe and reliable decision-making and motion planning for autonomous driving in a highway environment. This is a challenging task considering the correlation between the drivers behaviors. Two methods using attention mechanisms have been introduced in this context:

  • In [18], we present a new approach based on an LSTM encoder-decoder that uses a social pooling mechanism to model the interactions between all the neighboring vehicles. This social pooling module combines both local and non-local operations: the non-local multi-head attention mechanism captures the relative importance of each vehicle despite the inter-vehicle distances to the target vehicle, while the local blocks represent nearby interactions between vehicles. Evaluations have been performed using two naturalistic driving datasets: Next Generation Simulation (NGSIM) and the highD Dataset (https://www.highd-dataset.com/). The proposed method outperforms existing ones in terms of RMS values of prediction error, which shows the effectiveness of combining local and non-local operations in such a context.

  • In [19] we propose an RRNNs based encoder-decoder architecture where the encoder analyzes the patterns underlying in the past trajectories and the decoder generates the future trajectory sequence. The originality of this network is that it combines the advantages of the LSTM blocks in representing the temporal evolution of trajectories and the attention mechanism to model the relative interactions between vehicles. The proposed method outperforms LSTM encoder decoder in terms of RMSE values of the predicted trajectories on the large scaled naturalistic driving highD dataset.