Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human Actions
Not on the map. Why?
Abstract (arXiv)
We propose a logic-informed knowledge-driven modeling framework for human movements by analyzing their trajectories. Our approach is inspired by the fact that human actions are usually driven by their intentions or desires, and are influenced by environmental factors such as the spatial relationships with surrounding objects. In this paper, we introduce a set of spatial-temporal logic rules as knowledge to explain human actions. These rules will be automatically discovered from observational data. To learn the model parameters and the rule content, we design an expectation-maximization (EM) algorithm, which treats the rule content as latent variables. The EM algorithm alternates between the E-step and M-step: in the E-step, the posterior distribution over the latent rule content is evaluated; in the M-step, the rule generator and model parameters are jointly optimized by maximizing the current expected log-likelihood. Our model may have a wide range of applications in areas such as sports analytics, robotics, and autonomous cars, where understanding human movements are essential. We demonstrate the model's superior interpretability and prediction performance on pedestrian and NBA basketball player datasets, both achieving promising results.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 21 Jun 2023.
Builds on
24 of 40 references.
References · 24
- 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
- 2018Neural Relational Inference for Interacting Systemscited by 339
- 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 236
- 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
- 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 185
- 2019DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphscited by 175
- 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 167
- 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
- 2019Self-Driving Cars: A Surveycited by 148
- 2022GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoningcited by 128
- 2020RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphscited by 118
- 2020Neural Spatio-Temporal Point Processescited by 93
12 more
- 2018Boolean Decision Rules via Column Generationcited by 80
- 2022SocialVAE: Human Trajectory Prediction using Timewise Latentscited by 67
- 2022Human Trajectory Prediction via Neural Social Physicscited by 66
- 2020Collaborative Motion Prediction via Neural Motion Message Passingcited by 55
- 2020CaSPR: Learning Canonical Spatiotemporal Point Cloud Representationscited by 51
- 2021Neural Point Process for Learning Spatiotemporal Event Dynamicscited by 42
- 2017A Review of Self-Exciting Spatio-Temporal Point Processes and Their Applicationscited by 40
- 2022Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimationcited by 40
- 2021Collaborative Uncertainty in Multi-Agent Trajectory Forecastingcited by 18
- 2022Action-based Contrastive Learning for Trajectory Predictioncited by 15
- 2021baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modelingcited by 14
- 2014Factorized Point Process Intensities: A Spatial Analysis of Professional Basketballcited by 8
Built on by
Citing papers per year: 2023: 2; 2024: 0; 2025: 0; 2026: 1.
3 papers.