2026-10-07T22:26:48Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33956433 2026-09-21T17:32:47Z category_21 category_272 category_734 category_931 category_106 portal_5 item_type_3 month_year_09_2026

<p>Scenarios in HighD dataset.</p> Sidra Rashid (25084581) Muazzam A. Khan (3350624) Usman Akram (5412755) Raheel Mumtaz (25084584) It Ee Lee (19649086) Toqeer Ali Syed (24416043) Biotechnology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified Science Policy predefined spatial neighborhood narrow temporal window longer prediction horizons detailed ablation study complex traffic scenarios aware interaction representations assign context weights term memory model proposed model outperforms different attention mechanisms relevant neighbor vehicles range spatiotemporal dependencies range dependencies model long model emphasizes best model attention mechanism attention heads varying numbers use recurrent target vehicle systematically evaluate primary part neural networks neighboring vehicles local multi influential vehicles implicitly assuming formulate position error accumulation equal influence control pipeline comprehensive set capture long autonomous driving art methods <div><p>Vehicle trajectory prediction (VTP) is the primary part of the perception-planning-control pipeline in autonomous driving. The inter-vehicle interactions strongly shape the trajectory of vehicles in complex traffic scenarios. Neural networks that use recurrent or convolutional architectures often exhibit performance degradation in longer prediction horizons. Many existing approaches confine interaction modeling to a predefined spatial neighborhood and a narrow temporal window, while implicitly assuming that all neighboring vehicles have equal influence on the future trajectory of target vehicle. This results in error accumulation and the inability to capture long-range spatiotemporal dependencies. To overcome these limitations, a non-local multi-head spatiotemporal attention based long short-term memory model (NL-MHA-LSTM) is introduced which employs an attention mechanism to assign context weights to relevant neighbor vehicles. It extends beyond pairwise effects to model long-range dependencies. The model emphasizes the most influential vehicles and formulate position-aware interaction representations. A comprehensive set of experiments is conducted on the pubicly available HighD dataset. The results demonstrate that the proposed model outperforms all state-of-the-art methods, achieving a 53.4% reduction in RMSE at the 5s prediction horizon relative to the next-best model. In addition, a detailed ablation study is conducted to systematically evaluate the impact of different attention mechanisms and varying numbers of attention heads on prediction accuracy across multiple horizons.</p></div> 2026-09-21T17:32:34Z Dataset Dataset 10.1371/journal.pone.0357735.t006 https://figshare.com/articles/dataset/_p_Scenarios_in_HighD_dataset_p_/33956433 CC BY 4.0