Attention-based Lane Change Prediction
This work addresses the need for interpretable lane change prediction models in autonomous driving, though it appears incremental by combining existing attention mechanisms with recurrent models.
The paper tackled the problem of lane change prediction for surrounding vehicles by proposing an attention-based recurrent model to improve both prediction quality and model understandability, showing encouraging results on public and proprietary datasets.
Lane change prediction of surrounding vehicles is a key building block of path planning. The focus has been on increasing the accuracy of prediction by posing it purely as a function estimation problem at the cost of model understandability. However, the efficacy of any lane change prediction model can be improved when both corner and failure cases are humanly understandable. We propose an attention-based recurrent model to tackle both understandability and prediction quality. We also propose metrics which reflect the discomfort felt by the driver. We show encouraging results on a publicly available dataset and proprietary fleet data.