跳到正文
arXiv cs.AI· Almog Anschel, Sarah Keren·· 2 小时前AI 评分41

WoRD:基于扩散模型后验推断的在线目标识别

WoRD: Diffusion-Based Posterior Inference for Online Goal Recognition

AI 导读

WoRD(Waypoint Recognition with Diffusion)利用学习到的轨迹先验,从部分观测中推断智能体的目标。该方法为每个候选目标运行一条热启动去噪链,通过闭式对数似然梯度引导采样,并按贝叶斯规则加权得到校准的目标后验。

正文 · 原文

View PDF HTML (experimental)

Abstract:Goal recognition is the task of inferring an agent's intended goal from its observed behavior. Most existing work focuses on high-level symbolic recognition, abstracting away the continuous motion through which agents reach their goal. Methods that do reason over continuous trajectories rely on an explicit dynamics model that is hard to acquire and rarely transfers across settings. Neither approach explicitly learns how agents move toward each candidate goal, limiting accuracy on ambiguous trajectory prefixes where such knowledge is most needed.
We present WoRD (Waypoint Recognition with Diffusion), which uses a learned trajectory prior to infer the agent's goal from partial observations. At each step, WoRD runs one warm-started denoising chain per candidate goal, steers each chain toward the observed trajectory through a closed-form log-likelihood gradient, and reweights the resulting samples by Bayes' rule into a calibrated posterior over goals. We evaluate WoRD on simulated robot settings, pedestrian trajectories, and vehicle trajectories using four metrics targeting distinct failure modes. Across all three settings, the same inference procedure preserves calibrated multimodal beliefs through ambiguous prefixes where filter- and classifier-based observers collapse to a single mode or grow overconfident.
Comments: Accepted at the 40th Annual Conference on Neural Information Processing Systems (NeurIPS 2026)
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
Cite as: arXiv:2611.23192 [cs.AI]
  (or arXiv:2611.23192v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.23192

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Almog Anschel [view email]
[v1] Tue, 17 Nov 2026 18:35:53 UTC (1,227 KB)

来源:arXiv cs.AI · arxiv.org