Exploring Attention GAN for Vehicle Motion Prediction

The design of a safe and reliable Autonomous Driving stack (ADS) is one of the most challenging tasks of our era. These ADS are expected to be driven in highly dynamic environments with full autonomy, and a reliability greater than human beings. In that sense, to efficiently and safely navigate through arbitrarily complex traffic scenarios, ADS must have the ability to forecast the future trajectories of surrounding actors. Current state-of-the-art models are typically based on Recurrent, Graph and Convolutional networks, achieving noticeable results in the context of vehicle prediction. In this paper we explore the influence of attention in generative models for motion prediction, considering both physical and social context to compute the most plausible trajectories. First, the past trajectories are encoded using a LSTM network which feed a Multi-Head Self-Attention module to compute the social context. Then, plausible goal points are extracted from the driveable area of the HDMap information (physical context). Finally, the input of our generator is a white noise vector sampled from a multivariate normal distribution while the social and physical context are its conditions to predict plausible trajectories. We validate our method using the Argoverse Motion Forecasting Benchmark 1.1, achieving competitive unimodal results. Our code is publicly available at https://github.com/Cram3r95/mapfe4mp.