# Industrial Kinematic Trajectory Model (IKTM): Coordinate-Free Autoregressive Generator

arXiv: https://arxiv.org/abs/2609.22173 · HTML: https://mlsanity.com/paper/2609.22173/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 24 references that are in the map.
- First posted on arXiv 27 Aug 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook](https://mlsanity.com/paper/2310.10196/) (2023)
- [UrbanGPT: Spatio-Temporal Large Language Models](https://mlsanity.com/paper/2403.00813/) (2024)
- [UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction](https://mlsanity.com/paper/2403.15098/) (2024)
- [Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap](https://mlsanity.com/paper/2503.21411/) (2025)
- [Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey](https://mlsanity.com/paper/2503.13502/) (2025)
- [Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models](https://mlsanity.com/paper/2402.01749/) (2024)
- [UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces](https://mlsanity.com/paper/2411.03859/) (2024)
- [Large Language Models for Mobility Analysis in Transportation Systems: A Survey on Forecasting Tasks](https://mlsanity.com/paper/2405.02357/) (2024)
- [TrajFM: A Vehicle Trajectory Foundation Model for Region and Task Transferability](https://mlsanity.com/paper/2408.15251/) (2024)
- [Trajectory Prediction Meets Large Language Models: A Survey](https://mlsanity.com/paper/2506.03408/) (2025)
- [MobilityGPT: Enhanced Human Mobility Modeling with a GPT model](https://mlsanity.com/paper/2402.03264/) (2024)
- [Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review](https://mlsanity.com/paper/2506.01364/) (2025)
- [Self-Supervised Representation Learning for Geospatial Objects: A Survey](https://mlsanity.com/paper/2408.12133/) (2024)
- [Blurred Encoding for Trajectory Representation Learning](https://mlsanity.com/paper/2511.13741/) (2025)
- [Large Foundation Models for Trajectory Prediction in Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2509.10570/) (2025)
- [Urban Computing in the Era of Large Language Models](https://mlsanity.com/paper/2504.02009/) (2025)
- [MoveGPT: Scaling Mobility Foundation Models with Spatially-Aware Mixture of Experts](https://mlsanity.com/paper/2505.18670/) (2025)
- [MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning](https://mlsanity.com/paper/2509.22403/) (2025)
- [Building a Foundation Model for Trajectory from Scratch](https://mlsanity.com/paper/2511.20610/) (2025)
- [TrajTok: Adaptive Spatial Tokenization for Trajectory Representation Learning](https://mlsanity.com/paper/2605.20134/) (2026)

## Abstract (arXiv)

Mobility simulation supports logistics, safety, and communications planning in industrial environments such as ports, mines, and airports. Existing trajectory models, however, rely on absolute coordinates, road-network tokens, or semantic zones: representations that are site-specific and not well suited to unstructured industrial terrain. We introduce the Industrial Kinematic Trajectory Model (IKTM), a coordinate-free trajectory generator that represents industrial vehicle motion through kinematic sequences (speed and heading change) with no absolute spatial reference. IKTM uses an autoregressive causal transformer with probabilistic mixture heads and extends our prior coordinate-free Markovian model with deep sequence modelling and an explicit duration-conditioning signal. Trained on one site and evaluated zero-shot on three unseen sites, it matches the small-turn shape of the empirical turn-rate distributions of held-out telematics; across all four sites, the per-site mean Jensen-Shannon divergence over 100 sampling seeds spans approximately 0.035-0.050 bits under an oracle-length duration-target protocol and approximately 0.032-0.042 bits under a fully zero-shot prior-length protocol, with similar ranges whether out-of-distribution (OOD) duration targets are drawn from each held-out site's empirical length distribution or from the Site A prior. Both protocols stay above the metric's sampling-noise floor (<=0.0049 bits). Paired by site, the oracle-length values are 5.3-6.0x lower than those of a re-implementation of our prior Markovian model under the same 1 Hz protocol. Termination is duration-conditioned rather than spatial: rollouts stop on 100% of trials with a length-tracking error of +0.0 +/- 0.0 s against the sampled target (100 of 100 exactly on target; N=100, T=0.2, untouched in-distribution test split).