Trajectory Prediction for Heterogeneous Agents A Performance Analysis on Small and Imbalanced Datasets
Loading...
Access rights
openAccess
acceptedVersion
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
2024-07-01
Major/Subject
Mcode
Degree programme
Language
en
Pages
8
Series
IEEE Robotics and Automation Letters, Volume 9, issue 7, pp. 6576-6583
Abstract
Robots and other intelligent systems navigating in complex dynamic environments should predict future actions and intentions of surrounding agents to reach their goals efficiently and avoid collisions. The dynamics of those agents strongly depends on their tasks, roles, or observable labels. Class-conditioned motion prediction is thus an appealing way to reduce forecast uncertainty and get more accurate predictions for heterogeneous agents. However, this is hardly explored in the prior art, especially for mobile robots and in limited data applications. In this paper, we analyse different class-conditioned trajectory prediction methods on two datasets. We propose a set of conditional pattern-based and efficient deep learning-based baselines, and evaluate their performance on robotics and outdoors datasets (THÖR-MAGNI and Stanford Drone Dataset). Our experiments show that all methods improve accuracy in most of the settings when considering class labels. More importantly, we observe that there are significant differences when learning from imbalanced datasets, or in new environments where sufficient data is not available. In particular, we find that deep learning methods perform better on balanced datasets, but in applications with limited data, e.g., cold start of a robot in a new environment, or imbalanced classes, pattern-based methods may be preferable.Description
Publisher Copyright: IEEE
Keywords
Datasets for Human Motion, Deep Learning Methods, Deep learning, Dynamics, Generative adversarial networks, Human Detection and Tracking, Human and Humanoid Motion Analysis and Synthesis, Navigation, Roads, Robots, Trajectory, human detection, tracking, human and humanoid motion analysis and synthesis, deep learning methods, Datasets for human motion
Other note
Citation
de Almeida, T R, Zhu, Y, Rudenko, A, Kucner, T P, Stork, J A, Magnusson, M & Lilienthal, A J 2024, ' Trajectory Prediction for Heterogeneous Agents A Performance Analysis on Small and Imbalanced Datasets ', IEEE Robotics and Automation Letters, vol. 9, no. 7, pp. 6576-6583 . https://doi.org/10.1109/LRA.2024.3408510