Transferable Pedestrian Motion Prediction Models at Intersections
This work addresses the need for accurate pedestrian prediction in autonomous driving, but it is incremental as it builds on existing transfer learning and IRL methods.
The paper tackled the problem of predicting pedestrian motion at intersections for autonomous vehicles by developing a transfer learning algorithm based on Inverse Reinforcement Learning, which improved baseline accuracy by 40% in non-transfer tasks and 16% in transfer tasks.
One desirable capability of autonomous cars is to accurately predict the pedestrian motion near intersections for safe and efficient trajectory planning. We are interested in developing transfer learning algorithms that can be trained on the pedestrian trajectories collected at one intersection and yet still provide accurate predictions of the trajectories at another, previously unseen intersection. We first discussed the feature selection for transferable pedestrian motion models in general. Following this discussion, we developed one transferable pedestrian motion prediction algorithm based on Inverse Reinforcement Learning (IRL) that infers pedestrian intentions and predicts future trajectories based on observed trajectory. We evaluated our algorithm on a dataset collected at two intersections, trained at one intersection and tested at the other intersection. We used the accuracy of augmented semi-nonnegative sparse coding (ASNSC), trained and tested at the same intersection as a baseline. The result shows that the proposed algorithm improves the baseline accuracy by 40% in the non-transfer task, and 16% in the transfer task.