Abstract
Methods to quantify the complexity of trajectory datasets are still a missing piece in benchmarking human trajectory prediction models. In order to gain a better understanding of the complexity of trajectory prediction tasks and following the intuition, that more complex datasets contain more information, an approach for quantifying the amount of information contained in a dataset from a prototype-based dataset representation is proposed. The dataset representation is obtained by first employing a non-trivial spatial sequence alignment, which enables a subsequent learning vector quantization (LVQ) stage. A large-scale complexity analysis is conducted on several human trajectory prediction benchmarking datasets, followed by a brief discussion on indications for human trajectory prediction and benchmarking.
Highlights
With the emergence of autonomous vehicles and advances in the field of intelligent robots in general, the task of human trajectory prediction gained a significant amount of research interest in recent years
The most common deep learning models either build around long short-term memory networks (e.g. [3]), convolutional neural networks (e.g. [4]), generative adversarial networks (e.g. [5]) or transformers (e.g. [6]) and vary in contextual cues considered for prediction
CONCLUDING REMARKS In the context of statistical learning, dataset complexity is closely related to the entropy of a given dataset
Summary
With the emergence of autonomous vehicles and advances in the field of intelligent robots in general, the task of human trajectory prediction gained a significant amount of research interest in recent years. Physics-based prediction approaches, e.g. building on the Kalman filter [1] or the social forces model [2], a range of deep learning approaches have been proposed to tackle the problem. The most common deep learning models either build around long short-term memory networks [6]) and vary in contextual cues considered for prediction. Due to the direct relation between dataset complexity and model capacity, creating a not too simple or too hard-to-solve benchmark for human trajectory prediction is still a difficult task.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
