Trajectory Prediction for Autonomous Driving based on Multi-Head Attention with Joint Agent-Map Representation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Trajectory Prediction for Autonomous Driving based on Multi-Head Attention with Joint Agent-Map Representation

Abstract

Predicting the trajectories of surrounding agents is an essential ability for autonomous vehicles navigating through complex traffic scenes. The future trajectories of agents can be inferred using two important cues: the locations and past motion of agents, and the static scene structure. Due to the high variability in scene structure and agent configurations, prior work has employed the attention mechanism, applied separately to the scene and agent configuration to learn the most salient parts of both cues. However, the two cues are tightly linked. The agent configuration can inform what part of the scene is most relevant to prediction. The static scene in turn can help determine the relative influence of agents on each others motion. Moreover, the distribution of future trajectories is multimodal, with modes corresponding to the agent's intent. The agent's intent also informs what part of the scene and agent configuration is relevant to prediction. We thus propose a novel approach applying multi-head attention by considering a joint representation of the static scene and surrounding agents. We use each attention head to generate a distinct future trajectory to address multimodality of future trajectories. Our model achieves state of the art results on the nuScenes prediction benchmark and generates diverse future trajectories compliant with scene structure and agent configuration.
Fichier principal
Vignette du fichier
2005.02545.pdf (924.54 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03145159 , version 1 (18-02-2021)

Identifiers

  • HAL Id : hal-03145159 , version 1

Cite

Kaouther Messaoud, Nachiket Deo, Mohan M Trivedi, Fawzi Nashashibi. Trajectory Prediction for Autonomous Driving based on Multi-Head Attention with Joint Agent-Map Representation. IV21 - IEEE Intelligent Vehicles Symposium 2021, Jun 2021, Nagoya, Japan. ⟨hal-03145159⟩

Collections

INRIA INRIA2
147 View
188 Download

Share

Gmail Mastodon Facebook X LinkedIn More