Accelerating Online Mapping and Behavior Prediction via Direct BEV Feature Attention

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gu, Xunjiang, Song, Guanyu, Gilitschenski, Igor, Pavone, Marco, Ivanovic, Boris
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917716312457216
author Gu, Xunjiang
Song, Guanyu
Gilitschenski, Igor
Pavone, Marco
Ivanovic, Boris
author_facet Gu, Xunjiang
Song, Guanyu
Gilitschenski, Igor
Pavone, Marco
Ivanovic, Boris
contents Understanding road geometry is a critical component of the autonomous vehicle (AV) stack. While high-definition (HD) maps can readily provide such information, they suffer from high labeling and maintenance costs. Accordingly, many recent works have proposed methods for estimating HD maps online from sensor data. The vast majority of recent approaches encode multi-camera observations into an intermediate representation, e.g., a bird's eye view (BEV) grid, and produce vector map elements via a decoder. While this architecture is performant, it decimates much of the information encoded in the intermediate representation, preventing downstream tasks (e.g., behavior prediction) from leveraging them. In this work, we propose exposing the rich internal features of online map estimation methods and show how they enable more tightly integrating online mapping with trajectory forecasting. In doing so, we find that directly accessing internal BEV features yields up to 73% faster inference speeds and up to 29% more accurate predictions on the real-world nuScenes dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2407_06683
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Accelerating Online Mapping and Behavior Prediction via Direct BEV Feature Attention
Gu, Xunjiang
Song, Guanyu
Gilitschenski, Igor
Pavone, Marco
Ivanovic, Boris
Robotics
Computer Vision and Pattern Recognition
Machine Learning
Understanding road geometry is a critical component of the autonomous vehicle (AV) stack. While high-definition (HD) maps can readily provide such information, they suffer from high labeling and maintenance costs. Accordingly, many recent works have proposed methods for estimating HD maps online from sensor data. The vast majority of recent approaches encode multi-camera observations into an intermediate representation, e.g., a bird's eye view (BEV) grid, and produce vector map elements via a decoder. While this architecture is performant, it decimates much of the information encoded in the intermediate representation, preventing downstream tasks (e.g., behavior prediction) from leveraging them. In this work, we propose exposing the rich internal features of online map estimation methods and show how they enable more tightly integrating online mapping with trajectory forecasting. In doing so, we find that directly accessing internal BEV features yields up to 73% faster inference speeds and up to 29% more accurate predictions on the real-world nuScenes dataset.
title Accelerating Online Mapping and Behavior Prediction via Direct BEV Feature Attention
topic Robotics
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2407.06683