Relation-Aware LNN-Transformer for Intersection-Centric Next-Step Prediction

• URL: http://arxiv.org/abs/2508.01368v1
• Date: Sat, 02 Aug 2025 13:47:12 GMT
• Title: Relation-Aware LNN-Transformer for Intersection-Centric Next-Step Prediction
• Authors: Zhehong Ren, Tianluo Zhang, Yiheng Lu, Yushen Liang, Promethee Spathis,
• Abstract summary: We introduce a road-node-centric framework that represents road-user trajectories on the city's road-intersection graph.<n>By combining these cues with structural graph embeddings, we obtain semantically grounded node representations.<n>Our model outperforms six state-of-the-art baselines by up to 17 percentage points in accuracy at one hop and 10 percentage points in MRR.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Next-step location prediction plays a pivotal role in modeling human mobility, underpinning applications from personalized navigation to strategic urban planning. However, approaches that assume a closed world - restricting choices to a predefined set of points of interest (POIs) - often fail to capture exploratory or target-agnostic behavior and the topological constraints of urban road networks. Hence, we introduce a road-node-centric framework that represents road-user trajectories on the city's road-intersection graph, thereby relaxing the closed-world constraint and supporting next-step forecasting beyond fixed POI sets. To encode environmental context, we introduce a sector-wise directional POI aggregation that produces compact features capturing distance, bearing, density and presence cues. By combining these cues with structural graph embeddings, we obtain semantically grounded node representations. For sequence modeling, we integrate a Relation-Aware LNN-Transformer - a hybrid of a Continuous-time Forgetting Cell CfC-LNN and a bearing-biased self-attention module - to capture both fine-grained temporal dynamics and long-range spatial dependencies. Evaluated on city-scale road-user trajectories, our model outperforms six state-of-the-art baselines by up to 17 percentage points in accuracy at one hop and 10 percentage points in MRR, and maintains high resilience under noise, losing only 2.4 percentage points in accuracy at one under 50 meter GPS perturbation and 8.9 percentage points in accuracy at one hop under 25 percent POI noise.

Related papers

• INSPIRE-GNN: Intelligent Sensor Placement to Improve Sparse Bicycling Network Prediction via Reinforcement Learning Boosted Graph Neural Networks [51.76364085699241]
  INSPIRE-GNN is a novel Reinforcement Learning-boosted hybrid Graph Neural Network (GNN) framework designed to optimize sensor placement and improve link-level bicycling volume estimation in data-sparse environments.<n>Our framework outperforms traditional methods for sensor placement such as betweenness centrality, closeness, observed bicycling activity and random placement, across key metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE)<n>Our experiments benchmark INSPIRE-GNN against standard machine learning and deep learning models in the bicycle volume estimation performance, underscoring its effectiveness
  arXiv  Detail & Related papers  (2025-07-31T20:00:35Z)
• POIFormer: A Transformer-Based Framework for Accurate and Scalable Point-of-Interest Attribution [3.729614737011418]
  textsfPOIFormer is a novel Transformer-based framework for accurate and efficient POI attribution.<n>textsfPOIFormer enables accurate, efficient attribution in large, noisy mobility datasets.
  arXiv  Detail & Related papers  (2025-07-12T04:37:52Z)
• NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments [56.35569661650558]
  We introduce NOVA, a fully onboard, object-centric framework that enables robust target tracking and collision-aware navigation.<n>Rather than constructing a global map, NOVA formulates perception, estimation, and control entirely in the target's reference frame.<n>We validate NOVA across challenging real-world scenarios, including urban mazes, forest trails, and repeated transitions through buildings with intermittent GPS loss.
  arXiv  Detail & Related papers  (2025-06-23T14:28:30Z)
• Planning with Adaptive World Models for Autonomous Driving [50.4439896514353]
  We present nuPlan, a real-world motion planning benchmark that captures multi-agent interactions.<n>We learn to model such unique behaviors with BehaviorNet, a graph convolutional neural network (GCNN)<n>We also present AdaptiveDriver, a model-predictive control (MPC) based planner that unrolls different world models conditioned on BehaviorNet's predictions.
  arXiv  Detail & Related papers  (2024-06-15T18:53:45Z)
• KI-GAN: Knowledge-Informed Generative Adversarial Networks for Enhanced Multi-Vehicle Trajectory Forecasting at Signalized Intersections [15.464952852717127]
  We present a novel model called Knowledge-Informed Generative Adversarial Network (KI-GAN), which integrates traffic signal information and multi-vehicle interactions to predict vehicle trajectories accurately. Based on the SinD dataset, our KI-GAN model is able to achieve an Average Displacement Error (ADE) of 0.05 and a Final Displacement Error (FDE) of 0.12 for a 6-second observation and 6-second prediction cycle.
  arXiv  Detail & Related papers  (2024-04-17T08:53:59Z)
• Adaptive Hierarchical SpatioTemporal Network for Traffic Forecasting [70.66710698485745]
  We propose an Adaptive Hierarchical SpatioTemporal Network (AHSTN) to promote traffic forecasting. AHSTN exploits the spatial hierarchy and modeling multi-scale spatial correlations. Experiments on two real-world datasets show that AHSTN achieves better performance over several strong baselines.
  arXiv  Detail & Related papers  (2023-06-15T14:50:27Z)
• D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights [68.76631399516823]
  We present a trajectory prediction approach with respect to traffic lights, D2-TPred, using a spatial dynamic interaction graph (SDG) and a behavior dependency graph (BDG) Our experimental results show that our model achieves more than 20.45% and 20.78% in terms of ADE and FDE, respectively, on VTP-TL.
  arXiv  Detail & Related papers  (2022-07-21T10:19:07Z)
• Trajectory Prediction with Graph-based Dual-scale Context Fusion [43.51107329748957]
  We present a graph-based trajectory prediction network named the Dual Scale Predictor. It encodes both the static and dynamical driving context in a hierarchical manner. Thanks to the proposed dual-scale context fusion network, our DSP is able to generate accurate and human-like multi-modal trajectories.
  arXiv  Detail & Related papers  (2021-11-02T13:42:16Z)
• SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction [64.16212996247943]
  We present a Sparse Graph Convolution Network(SGCN) for pedestrian trajectory prediction. Specifically, the SGCN explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians. visualizations indicate that our method can capture adaptive interactions between pedestrians and their effective motion tendencies.
  arXiv  Detail & Related papers  (2021-04-04T03:17:42Z)
• Robust GPS-Vision Localization via Integrity-Driven Landmark Attention [2.741266294612776]
  Integrity-driven Landmark Attention (ILA) for GPS-vision navigation in urban areas. Inspired by cognitive attention in humans, we perform convex optimization to select a subset of landmarks. We demonstrate improved localization accuracy and robust predicted availability for a pre-defined alert limit.
  arXiv  Detail & Related papers  (2021-01-13T02:16:13Z)
• Self-Growing Spatial Graph Network for Context-Aware Pedestrian Trajectory Prediction [11.716375199937568]
  Social Trajectory Recommender-Gated Graph Recurrent Neighborhood Network, (STR-GGRNN) STR-GGRNN uses data-driven adaptive online neighborhood recommendation based on contextual scene features and pedestrian visual cues. Our best performing model achieves 12 cm ADE and $sim$15 cm FDE on ETH-UCY dataset.
  arXiv  Detail & Related papers  (2020-12-11T13:25:58Z)
• It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction [59.027152973975575]
  We present Predicted Conditioned Network (PECNet) for flexible human trajectory prediction. PECNet infers distant endpoints to assist in long-range multi-modal trajectory prediction. We show that PECNet improves state-of-the-art performance on the Stanford Drone trajectory prediction benchmark by 20.9% and on the ETH/UCY benchmark by 40.8%.
  arXiv  Detail & Related papers  (2020-04-04T21:27:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.