Multi-stream social-aware transformers for deterministic trajectory prediction

With the development of artificial intelligence technology, intelligent robots are being used more widely in daily life. For any delivery robot operating in crowded environments, accurate and fast pedestrian trajectory prediction is the basis of autonomous tasks and poses considerable challenges. (...

Full description

Saved in:
Bibliographic Details
Main Author: Chen, Xun
Other Authors: Wang Dan Wei
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/172974
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-172974
record_format dspace
spelling sg-ntu-dr.10356-1729742024-01-12T15:45:36Z Multi-stream social-aware transformers for deterministic trajectory prediction Chen, Xun Wang Dan Wei School of Electrical and Electronic Engineering Continental-NTU Corporate Lab EDWWANG@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence With the development of artificial intelligence technology, intelligent robots are being used more widely in daily life. For any delivery robot operating in crowded environments, accurate and fast pedestrian trajectory prediction is the basis of autonomous tasks and poses considerable challenges. (1) For the pedestrian trajectory prediction task, most previous works use probabilistic generative models (such as CVAE/Diffusion) to model the problem and use evaluation metrics like the best result out of 20 samples to measure model accuracy. This has a considerable gap from actual deployment applications. In this work, the task is modeled as a seq2seq translation model, outputting only one accurate prediction, which is more amenable to real-world deployment while also reducing model complexity. (2) The difficulty of this task lies in its inherent spatio-temporal and social dimensions. Simply modeling the temporal dimension alone would miss interactions between agents. Most solutions alternate information exchange across the two dimensions and achieve decent results, but this may lead to information loss. Approaches that exchange information simultaneously in both dimensions incur high computational complexity (quadratic in total length). Drawing inspiration from multi-modal fusion network architectures, a novel multi-stream Transformer architecture is proposed that fuses information from multiple input streams into a single stream and then decodes it back to multiple output streams. This multi-stream Transformer architecture significantly reduces computational complexity for real-time deployment while achieving results very close to state-of-the-art on well-established datasets. Keywords: Trajectory prediction, seq2seq model, multi-stream Transformer, Real-time. Master of Science (Computer Control and Automation) 2024-01-08T07:40:57Z 2024-01-08T07:40:57Z 2023 Thesis-Master by Coursework Chen, X. (2023). Multi-stream social-aware transformers for deterministic trajectory prediction. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/172974 https://hdl.handle.net/10356/172974 en ISM-DISS-03234 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
spellingShingle Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Chen, Xun
Multi-stream social-aware transformers for deterministic trajectory prediction
description With the development of artificial intelligence technology, intelligent robots are being used more widely in daily life. For any delivery robot operating in crowded environments, accurate and fast pedestrian trajectory prediction is the basis of autonomous tasks and poses considerable challenges. (1) For the pedestrian trajectory prediction task, most previous works use probabilistic generative models (such as CVAE/Diffusion) to model the problem and use evaluation metrics like the best result out of 20 samples to measure model accuracy. This has a considerable gap from actual deployment applications. In this work, the task is modeled as a seq2seq translation model, outputting only one accurate prediction, which is more amenable to real-world deployment while also reducing model complexity. (2) The difficulty of this task lies in its inherent spatio-temporal and social dimensions. Simply modeling the temporal dimension alone would miss interactions between agents. Most solutions alternate information exchange across the two dimensions and achieve decent results, but this may lead to information loss. Approaches that exchange information simultaneously in both dimensions incur high computational complexity (quadratic in total length). Drawing inspiration from multi-modal fusion network architectures, a novel multi-stream Transformer architecture is proposed that fuses information from multiple input streams into a single stream and then decodes it back to multiple output streams. This multi-stream Transformer architecture significantly reduces computational complexity for real-time deployment while achieving results very close to state-of-the-art on well-established datasets. Keywords: Trajectory prediction, seq2seq model, multi-stream Transformer, Real-time.
author2 Wang Dan Wei
author_facet Wang Dan Wei
Chen, Xun
format Thesis-Master by Coursework
author Chen, Xun
author_sort Chen, Xun
title Multi-stream social-aware transformers for deterministic trajectory prediction
title_short Multi-stream social-aware transformers for deterministic trajectory prediction
title_full Multi-stream social-aware transformers for deterministic trajectory prediction
title_fullStr Multi-stream social-aware transformers for deterministic trajectory prediction
title_full_unstemmed Multi-stream social-aware transformers for deterministic trajectory prediction
title_sort multi-stream social-aware transformers for deterministic trajectory prediction
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/172974
_version_ 1789483051249565696