Skip to content

Wayformer: Motion Forecasting via Simple & Efficient Attention Networks

Authors: Nigamaa Nayakanti, Rami Al-Rfou, Aurick Zhou, Kratarth Goel, Khaled S. Refaat, Benjamin Sapp

Published: 2022 (Conference Paper)

Source: IEEE International Conference on Robotics and Automation (ICRA)

Algorithm: Wayformer

arXiv: 2207.05844

DOI: 10.1109/ICRA48891.2023.10160609

Summary

Proposes a simple and efficient transformer-based architecture for motion forecasting, showing that a straightforward attention design over scene and agent context can match or surpass more complex architectures on standard benchmarks like Waymo Open Motion Dataset (WOMD).

Abstract

Motion forecasting for autonomous driving is a challenging task because complex driving scenarios involve a heterogeneous mix of static and dynamic inputs. It is an open problem how best to represent and fuse information about road geometry, lane connectivity, time-varying traffic light state, and history of a dynamic set of agents and their interactions into an effective encoding. To model this diverse set of input features, many approaches proposed to design an equally complex system with a diverse set of modality specific modules. This results in systems that are difficult to scale, extend, or tune in rigorous ways to trade off quality and efficiency. In this paper, we present Wayformer, a family of simple and homogeneous attention based architectures for motion forecasting. Wayformer offers a compact model description consisting of an attention based scene encoder and a decoder. In the scene encoder we study the choice of early, late and hierarchical fusion of input modalities. For each fusion type we explore strategies to trade off efficiency and quality via factorized attention or latent query attention. We show that early fusion, despite its simplicity, is not only modality agnostic but also achieves state-of-the-art results on both Waymo Open Motion Dataset (WOMD) and Argoverse leaderboards, demonstrating the effectiveness of our design philosophy.

Primary

Paper arxiv.org

Standard

arXiv Abstract 2207.05844 arXiv PDF 2207.05844 arXiv HTML 2207.05844 DOI 10.1109/ICRA48891.2023.10160609

Alternate

khaledrefaat.com PDF khaledrefaat.com ieeexplore.ieee.org ieeexplore.ieee.org

Tags

  • Motion forecasting

  • Transformer

  • Attention mechanism

  • Autonomous driving

  • Multi-modal prediction

  • Waymo

  • Wayformer