Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ye, Sean, Gombolay, Matthew
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.10809
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913572949327872
author Ye, Sean
Gombolay, Matthew
author_facet Ye, Sean
Gombolay, Matthew
contents Trajectory prediction and generation are crucial for autonomous robots in dynamic environments. While prior research has typically focused on either prediction or generation, our approach unifies these tasks to provide a versatile framework and achieve state-of-the-art performance. While diffusion models excel in trajectory generation, their iterative sampling process is computationally intensive, hindering robotic systems' dynamic capabilities. We introduce Trajectory Conditional Flow Matching (T-CFM), a novel approach using flow matching techniques to learn a solver time-varying vector field for efficient, fast trajectory generation. T-CFM demonstrates effectiveness in adversarial tracking, real-world aircraft trajectory forecasting, and long-horizon planning, outperforming state-of-the-art baselines with 35% higher predictive accuracy and 142% improved planning performance. Crucially, T-CFM achieves up to 100$\times$ speed-up compared to diffusion models without sacrificing accuracy, enabling real-time decision making in robotics. Codebase: https://github.com/CORE-Robotics-Lab/TCFM
format Preprint
id arxiv_https___arxiv_org_abs_2403_10809
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Trajectory Forecasting and Generation with Conditional Flow Matching
Ye, Sean
Gombolay, Matthew
Robotics
Trajectory prediction and generation are crucial for autonomous robots in dynamic environments. While prior research has typically focused on either prediction or generation, our approach unifies these tasks to provide a versatile framework and achieve state-of-the-art performance. While diffusion models excel in trajectory generation, their iterative sampling process is computationally intensive, hindering robotic systems' dynamic capabilities. We introduce Trajectory Conditional Flow Matching (T-CFM), a novel approach using flow matching techniques to learn a solver time-varying vector field for efficient, fast trajectory generation. T-CFM demonstrates effectiveness in adversarial tracking, real-world aircraft trajectory forecasting, and long-horizon planning, outperforming state-of-the-art baselines with 35% higher predictive accuracy and 142% improved planning performance. Crucially, T-CFM achieves up to 100$\times$ speed-up compared to diffusion models without sacrificing accuracy, enabling real-time decision making in robotics. Codebase: https://github.com/CORE-Robotics-Lab/TCFM
title Efficient Trajectory Forecasting and Generation with Conditional Flow Matching
topic Robotics
url https://arxiv.org/abs/2403.10809