GPU-Accelerated Interaction-Aware Motion Prediction
Before their massive deployment, autonomous vehicles need to prove in complex scenarios such that they can reach human driving proficiency while guaranteeing higher safety levels. One of the most important human traits to negotiating traffic is the ability to predict the future behavior of surroundi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/18/3751 |
| _version_ | 1797580460054806528 |
|---|---|
| author | Juan Luis Hortelano Vinicius Trentin Antonio Artuñedo Jorge Villagra |
| author_facet | Juan Luis Hortelano Vinicius Trentin Antonio Artuñedo Jorge Villagra |
| author_sort | Juan Luis Hortelano |
| collection | DOAJ |
| description | Before their massive deployment, autonomous vehicles need to prove in complex scenarios such that they can reach human driving proficiency while guaranteeing higher safety levels. One of the most important human traits to negotiating traffic is the ability to predict the future behavior of surrounding vehicles as a basis for agile and safe navigation. This capability is particularly challenging for an autonomous system in highly interactive driving situations, such as intersections or roundabouts. In this paper, a set of techniques to bring a computationally expensive state-of-the-art motion prediction algorithm to real-time execution are presented with the goal of meeting a standard motion-planning algorithm execution frequency of 5 Hz, which is the primary consumer of motion predictions. This is achieved by applying novel and existing parallelization algorithms that take advantage of graphic processing units (GPUs) through the compute unified device architecture (CUDA) programming language and managing to produce an average 5× speedup over raw C++ in the cases studied. The optimizations are then evaluated in public datasets and a real vehicle on a test track. |
| first_indexed | 2024-03-10T22:51:15Z |
| format | Article |
| id | doaj.art-78184e647deb43cbb1847bccd65e5f82 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T22:51:15Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-78184e647deb43cbb1847bccd65e5f822023-11-19T10:20:51ZengMDPI AGElectronics2079-92922023-09-011218375110.3390/electronics12183751GPU-Accelerated Interaction-Aware Motion PredictionJuan Luis Hortelano0Vinicius Trentin1Antonio Artuñedo2Jorge Villagra3Centro de Automática y Robótica, CSIC—Universidad Politécnica de Madrid, Ctra. Campo Real, Km 0.200, Arganda del Rey, 28500 Madrid, SpainCentro de Automática y Robótica, CSIC—Universidad Politécnica de Madrid, Ctra. Campo Real, Km 0.200, Arganda del Rey, 28500 Madrid, SpainCentro de Automática y Robótica, CSIC—Universidad Politécnica de Madrid, Ctra. Campo Real, Km 0.200, Arganda del Rey, 28500 Madrid, SpainCentro de Automática y Robótica, CSIC—Universidad Politécnica de Madrid, Ctra. Campo Real, Km 0.200, Arganda del Rey, 28500 Madrid, SpainBefore their massive deployment, autonomous vehicles need to prove in complex scenarios such that they can reach human driving proficiency while guaranteeing higher safety levels. One of the most important human traits to negotiating traffic is the ability to predict the future behavior of surrounding vehicles as a basis for agile and safe navigation. This capability is particularly challenging for an autonomous system in highly interactive driving situations, such as intersections or roundabouts. In this paper, a set of techniques to bring a computationally expensive state-of-the-art motion prediction algorithm to real-time execution are presented with the goal of meeting a standard motion-planning algorithm execution frequency of 5 Hz, which is the primary consumer of motion predictions. This is achieved by applying novel and existing parallelization algorithms that take advantage of graphic processing units (GPUs) through the compute unified device architecture (CUDA) programming language and managing to produce an average 5× speedup over raw C++ in the cases studied. The optimizations are then evaluated in public datasets and a real vehicle on a test track.https://www.mdpi.com/2079-9292/12/18/3751autonomous vehiclesmotion predictioninteraction awareGPUCUDA |
| spellingShingle | Juan Luis Hortelano Vinicius Trentin Antonio Artuñedo Jorge Villagra GPU-Accelerated Interaction-Aware Motion Prediction Electronics autonomous vehicles motion prediction interaction aware GPU CUDA |
| title | GPU-Accelerated Interaction-Aware Motion Prediction |
| title_full | GPU-Accelerated Interaction-Aware Motion Prediction |
| title_fullStr | GPU-Accelerated Interaction-Aware Motion Prediction |
| title_full_unstemmed | GPU-Accelerated Interaction-Aware Motion Prediction |
| title_short | GPU-Accelerated Interaction-Aware Motion Prediction |
| title_sort | gpu accelerated interaction aware motion prediction |
| topic | autonomous vehicles motion prediction interaction aware GPU CUDA |
| url | https://www.mdpi.com/2079-9292/12/18/3751 |
| work_keys_str_mv | AT juanluishortelano gpuacceleratedinteractionawaremotionprediction AT viniciustrentin gpuacceleratedinteractionawaremotionprediction AT antonioartunedo gpuacceleratedinteractionawaremotionprediction AT jorgevillagra gpuacceleratedinteractionawaremotionprediction |