论文/arXiv 2610.20867·14 天前

面向运动物体的预测性常识：基于ASP的交互轨迹预测推理框架

提出混合声明式框架，结合ASP、语义引导预测与能量优化，在Argoverse 2上验证交互运动轨迹的预测推理。

AI 整理

• 本体 SDK 与控制
• 评测与安全

原文链接：Anticipatory Commonsense with Moving Objects: An ASP-Based Framework for Predictive Reasoning with Interacting Trajectories（arXiv 2610.20867 · 发布日期：2026-10-14）

Anticipatory Commonsense with Moving Objects: An ASP-Based Framework for Predictive Reasoning with Interacting Trajectories

提出混合声明式框架，结合ASP、语义引导预测与能量优化，在Argoverse 2上验证交互运动轨迹的预测推理。

核心要点

• 面向复杂动态环境中的交互运动，构建可解释的语义级预期时空心理模型。
• 方法整合ASP交互轨迹动态模型、语义引导的分支未来预测和能量优化排序过滤。
• 在Argoverse 2 benchmark上评估，每条预期轨迹带有显式可检查的事件级假设。
• 相较端到端随机预测，该框架强调声明式、模块化和可扩展的预测推理表示。

验证范围与局限：验证范围为Argoverse 2 benchmark。

英文摘要 (Abstract)

We present a general declarative framework for anticipatory reasoning about interactive motion in complex dynamic environments. Our focus is on (explainable) anticipatory space-time mental model formation at a semantic level to heuristically guide low-level motion computation. Our method is hybrid, modular and elaboration tolerant integrating: 1) An ASP model characterising the dynamics of interactive motion trajectories; 2) Semantically-guided prediction for deriving `branching trajectory futures'; and 3) An energy-based {optimisation} model to evaluate, rank and filter anticipations. We evaluate with the Argoverse 2 benchmark, where each anticipated trajectory carries an explicit, inspectable event-level hypothesis, unlike end-to-end stochastic prediction.

作者：Julius Monsen, Jakob Suchan, Mehul Bhatt

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.20867：Anticipatory Commonsense with Moving Objects: An ASP-Based Framework for Predictive Reasoning with Interacting Trajectories访问 2026-10-21