# TPK: Trustworthy Trajectory Prediction Integrating Prior Knowledge For Interpretability and Kinematic Feasibility

arXiv: https://arxiv.org/abs/2505.06743 · HTML: https://mlsanity.com/paper/2505.06743/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 10 May 2025.

## Builds on (most cited first, 21 of 21)

- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation](https://mlsanity.com/paper/2005.04259/) (2020)
- [Learning Lane Graph Representations for Motion Forecasting](https://mlsanity.com/paper/2007.13732/) (2020)
- [Motion Transformer with Global Intention Localization and Local Movement Refinement](https://mlsanity.com/paper/2209.13508/) (2022)
- [Human Motion Trajectory Prediction: A Survey](https://mlsanity.com/paper/1905.06113/) (2019)
- [SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies](https://mlsanity.com/paper/2109.13602/) (2021)
- [Bayesian Attention Modules](https://mlsanity.com/paper/2010.10604/) (2020)
- [Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding](https://mlsanity.com/paper/2310.12970/) (2023)
- [Social Interactions for Autonomous Driving: A Review and Perspectives](https://mlsanity.com/paper/2208.07541/) (2022)
- [Pedestrian Models for Autonomous Driving Part II: High-Level Models of Human Behavior](https://mlsanity.com/paper/2003.11959/) (2020)
- [Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks](https://mlsanity.com/paper/2102.10934/) (2021)
- [Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Review](https://mlsanity.com/paper/2308.06419/) (2023)
- [Granger-causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks](https://mlsanity.com/paper/1802.02195/) (2018)
- [Towards Explainable Motion Prediction using Heterogeneous Graph Representations](https://mlsanity.com/paper/2212.03806/) (2022)
- [Self-Supervised Action-Space Prediction for Automated Driving](https://mlsanity.com/paper/2109.10024/) (2021)
- [Attention-based Conditioning Methods for External Knowledge Integration](https://mlsanity.com/paper/1906.03674/) (2019)
- [Physically Feasible Vehicle Trajectory Prediction](https://mlsanity.com/paper/2104.14679/) (2021)
- [ForceFormer: Exploring Social Force and Transformer for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2302.07583/) (2023)
- [An Empirical Bayes Analysis of Object Trajectory Representation Models](https://mlsanity.com/paper/2211.01696/) (2022)
- [Towards trustworthy multi-modal motion prediction: Holistic evaluation and interpretability of outputs](https://mlsanity.com/paper/2210.16144/) (2022)

## Built on by (most cited first, 1 of 1)

- [Behavior-Centric Extraction of Scenarios from Highway Traffic Data and their Domain-Knowledge-Guided Clustering using CVQ-VAE](https://mlsanity.com/paper/2603.16964/) (2026)

## Abstract (arXiv)

Trajectory prediction is crucial for autonomous driving, enabling vehicles to navigate safely by anticipating the movements of surrounding road users. However, current deep learning models often lack trustworthiness as their predictions can be physically infeasible and illogical to humans. To make predictions more trustworthy, recent research has incorporated prior knowledge, like the social force model for modeling interactions and kinematic models for physical realism. However, these approaches focus on priors that suit either vehicles or pedestrians and do not generalize to traffic with mixed agent classes. We propose incorporating interaction and kinematic priors of all agent classes--vehicles, pedestrians, and cyclists with class-specific interaction layers to capture agent behavioral differences. To improve the interpretability of the agent interactions, we introduce DG-SFM, a rule-based interaction importance score that guides the interaction layer. To ensure physically feasible predictions, we proposed suitable kinematic models for all agent classes with a novel pedestrian kinematic model. We benchmark our approach on the Argoverse 2 dataset, using the state-of-the-art transformer HPTR as our baseline. Experiments demonstrate that our method improves interaction interpretability, revealing a correlation between incorrect predictions and divergence from our interaction prior. Even though incorporating the kinematic models causes a slight decrease in accuracy, they eliminate infeasible trajectories found in the dataset and the baseline model. Thus, our approach fosters trust in trajectory prediction as its interaction reasoning is interpretable, and its predictions adhere to physics.