The Advantage of Using Traffic Rules for Motion Prediction in Intersections (TRMPI)

The autonomous driving motion prediction is essential to have a correct and reliable planning. The influence of the road agents on each other makes it even more challenging. However, most prior works have not considered these interactions and planning against the predictions would decrease the ability of representing the possibilities of the future interactions among the different agents. In this work, we propose a model that predicts the agents’ behavior in a jointly manner. We take advantage of using the strategy of masking to our model as the query. Our model architecture employ attention across, agent interactions, traffic rules in intersections, and the road elements. The evaluation of our model is done on autonomous driving datasets for behavior prediction and test it on Carla simulator. Our work demonstrates that motion prediction by a model with a masking strategy and having attention and traffic rules can …