Motion Perceiver: Real-Time Occupancy Forecasting for Embedded Systems

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ferenczi, Bryce, Burke, Michael, Drummond, Tom
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911769368199168
author Ferenczi, Bryce
Burke, Michael
Drummond, Tom
author_facet Ferenczi, Bryce
Burke, Michael
Drummond, Tom
contents This work introduces a novel and adaptable architecture designed for real-time occupancy forecasting that outperforms existing state-of-the-art models on the Waymo Open Motion Dataset in Soft IOU. The proposed model uses recursive latent state estimation with learned transformer-based functions to effectively update and evolve the state. This enables highly efficient real-time inference on embedded systems, as profiled on an Nvidia Xavier AGX. Our model, MotionPerceiver, achieves this by encoding a scene into a latent state that evolves in time through self-attention mechanisms. Additionally, it incorporates relevant scene observations, such as traffic signals, road topology and agent detections, through cross-attention mechanisms. This forms an efficient data-streaming architecture, that contrasts with the expensive, fixed-sequence input common in existing models. The architecture also offers the distinct advantage of generating occupancy predictions through localized querying based on a point-of-interest, as opposed to generating fixed-size occupancy images that render potentially irrelevant regions.
format Preprint
id arxiv_https___arxiv_org_abs_2306_08879
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Motion Perceiver: Real-Time Occupancy Forecasting for Embedded Systems
Ferenczi, Bryce
Burke, Michael
Drummond, Tom
Robotics
I.2.9; I.2.10
This work introduces a novel and adaptable architecture designed for real-time occupancy forecasting that outperforms existing state-of-the-art models on the Waymo Open Motion Dataset in Soft IOU. The proposed model uses recursive latent state estimation with learned transformer-based functions to effectively update and evolve the state. This enables highly efficient real-time inference on embedded systems, as profiled on an Nvidia Xavier AGX. Our model, MotionPerceiver, achieves this by encoding a scene into a latent state that evolves in time through self-attention mechanisms. Additionally, it incorporates relevant scene observations, such as traffic signals, road topology and agent detections, through cross-attention mechanisms. This forms an efficient data-streaming architecture, that contrasts with the expensive, fixed-sequence input common in existing models. The architecture also offers the distinct advantage of generating occupancy predictions through localized querying based on a point-of-interest, as opposed to generating fixed-size occupancy images that render potentially irrelevant regions.
title Motion Perceiver: Real-Time Occupancy Forecasting for Embedded Systems
topic Robotics
I.2.9; I.2.10
url https://arxiv.org/abs/2306.08879