PV-WM: A Heterogeneous Micro-Macro World Model for Articulated Pedestrian-Vehicle Co-Rollout

• URL: http://arxiv.org/abs/2609.07328v1
• Date: Mon, 07 Sep 2026 10:45:26 GMT
• Title: PV-WM: A Heterogeneous Micro-Macro World Model for Articulated Pedestrian-Vehicle Co-Rollout
• Abstract summary: We introduce PV-WM, a history-only world model over structured post-perception tracks.<n>It recurrently advances pedestrian root motion, 15-joint articulation, and learned vehicle states within a synchronized heterogeneous state.<n>Across 824 contexts, with 797 providing valid future vehicle support, PV-WM reduces Root ADE by 5.2%, MPJPE by 7.6%, P-V distance error by 11.9%, and oriented-box closest-approach error by 5.8%.
• Score: 36.25772061017794
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Local pedestrian-vehicle forecasting spans heterogeneous physical scales: pedestrians combine root locomotion with articulated motion, whereas vehicles are rigid bodies described by kinematic state and oriented extent. Existing road-agent forecasters typically omit pedestrian articulation, while pose forecasters leave vehicle futures outside the learned rollout. We introduce PV-WM, a history-only world model over structured post-perception tracks. It recurrently advances pedestrian root motion, 15-joint articulation, and learned vehicle states within a synchronized heterogeneous state. The generated pedestrian and vehicle chunks supply the next recurrent boundary; vehicle boxes are reconstructed from predicted center and heading with observed extent, and P-V geometry is recomputed after every transition. Relative to a matched one-shot complete-state predictor, recurrent execution reduces Root ADE by 12.7% and MPJPE by 14.8%. Feedback interventions show that later predictions depend on the content, temporal order, and pedestrian identity of generated articulation. Across 824 aligned Waymo contexts, with 797 providing valid future vehicle support, PV-WM reduces Root ADE by 5.2%, MPJPE by 7.6%, P-V distance error by 11.9%, and oriented-box closest-approach error by 5.8% relative to a validation-selected Modular Specialist. The single-network model uses 57.1% fewer parameters, 96.5% lower average FLOPs per local scene, and 25.5% lower measured p95 latency. PV-WM unifies this heterogeneous future state while preserving type-specific pedestrian and vehicle dynamics.

Related papers

• SevDiff: Severity-Conditioned Diffusion for Long-Tail Conflict Trajectory Generation [0.0]
  This paper introduces SevDiff, a severity-conditioned denoising diffusion probabilistic model (DDPM)<n>It generates paired vehicle interaction trajectories whose realized conflict severity matches the request, evaluated through a hit-rate metric.<n>It achieves 100% hit-rate within +/-0.5 s for TTC targets of 0.5-1.5 s and 97-99% at 2.0-2.5 s, with graceful degradation to 39% at TTC = 5.0 s.
  arXiv  Detail & Related papers  (2026-07-13T22:17:48Z)
• A Dynamic Scene Interaction Reasoning Framework for Scene-level Lane-Change Intention and Trajectory Prediction of Multiple Interacting Vehicles [6.830580384536778]
  This study proposes a dynamic scene graph attention framework that predicts the lane-change intention and future trajectory of every relevant vehicle within a local traffic scene.<n> Experiments on the NGSIM I-80, NGSIM US-101, and highD datasets demonstrate consistent improvements over competing baselines.
  arXiv  Detail & Related papers  (2026-07-02T23:55:53Z)
• NOVA: Symbolic Regression Discovery of Interpretable Car-Following and Lane-Change Models with Driver Heterogeneity [1.889930012459364]
  NOVA is an autonomous symbolic regression framework for car-following and lane-change structures.<n>It is applied to 4,765,788 active driving observations from the NGSIM I-80 and US-101 datasets.<n>NOVA achieves 67.4% balanced accuracy under strict vehicle-ID holdout on 502 unseen drivers.
  arXiv  Detail & Related papers  (2026-06-09T08:47:39Z)
• HetroD: A High-Fidelity Drone Dataset and Benchmark for Autonomous Driving in Heterogeneous Traffic [49.31491001465465]
  HetroD is a dataset and benchmark for developing autonomous driving systems in heterogeneous environments.<n>HetroD targets the critical challenge of navi- gating real-world heterogeneous traffic dominated by vulner- able road users (VRUs)
  arXiv  Detail & Related papers  (2026-02-03T12:12:47Z)
• Relation-Aware LNN-Transformer for Intersection-Centric Next-Step Prediction [0.0]
  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.
  arXiv  Detail & Related papers  (2025-08-02T13:47:12Z)
• LTMSformer: A Local Trend-Aware Attention and Motion State Encoding Transformer for Multi-Agent Trajectory Prediction [6.520837230073969]
  We propose a lightweight framework, LTMSformer, to extract temporal-spatial interaction features for trajectory prediction.<n>We also build a Motion State to incorporate high-order motion state attributes, such as acceleration, jerk, heading, etc.<n>Experiment results show that our method outperforms the baseline HiVT-64, reducing the minADE by approximately 4.35%, the minFDE by 8.74%, and the MR by 20%.
  arXiv  Detail & Related papers  (2025-07-07T03:33:14Z)
• Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion [87.77727495366702]
  We introduce the new task of pedestrian stop and go forecasting. Considering the lack of suitable existing datasets for it, we release TRANS, a benchmark for explicitly studying the stop and go behaviors of pedestrians in urban traffic. We build it from several existing datasets annotated with pedestrians' walking motions, in order to have various scenarios and behaviors.
  arXiv  Detail & Related papers  (2022-03-04T18:39:31Z)
• Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers [126.81938540470847]
  We propose Euro-PVI, a dataset of pedestrian and bicyclist trajectories. In this work, we develop a joint inference model that learns an expressive multi-modal shared latent space across agents in the urban scene. We achieve state of the art results on the nuScenes and Euro-PVI datasets demonstrating the importance of capturing interactions between ego-vehicle and pedestrians (bicyclists) for accurate predictions.
  arXiv  Detail & Related papers  (2021-06-22T15:40:21Z)
• 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)
• What-If Motion Prediction for Autonomous Driving [58.338520347197765]
  Viable solutions must account for both the static geometric context, such as road lanes, and dynamic social interactions arising from multiple actors. We propose a recurrent graph-based attentional approach with interpretable geometric (actor-lane) and social (actor-actor) relationships. Our model can produce diverse predictions conditioned on hypothetical or "what-if" road lanes and multi-actor interactions.
  arXiv  Detail & Related papers  (2020-08-24T17:49:30Z)
• Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction [57.56466850377598]
  Reasoning over visual data is a desirable capability for robotics and vision-based applications. In this paper, we present a framework on graph to uncover relationships in different objects in the scene for reasoning about pedestrian intent. Pedestrian intent, defined as the future action of crossing or not-crossing the street, is a very crucial piece of information for autonomous vehicles.
  arXiv  Detail & Related papers  (2020-02-20T18:50:44Z)

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.