# Online Adaptation of Neural Network Models by Modified Extended Kalman Filter for Customizable and Transferable Driving Behavior Prediction

arXiv: https://arxiv.org/abs/2112.06129 · HTML: https://mlsanity.com/paper/2112.06129/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 9 Dec 2021.

## Builds on (most cited first, 12 of 12)

- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Human Motion Trajectory Prediction: A Survey](https://mlsanity.com/paper/1905.06113/) (2019)
- [INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps](https://mlsanity.com/paper/1910.03088/) (2019)
- [TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents](https://mlsanity.com/paper/1811.02146/) (2018)
- [Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecture](https://mlsanity.com/paper/1802.06338/) (2018)
- [How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Prediction](https://mlsanity.com/paper/1801.06523/) (2018)
- [Neural Machine Translation and Sequence-to-sequence Models: A Tutorial](https://mlsanity.com/paper/1703.01619/) (2017)
- [Socially-Compatible Behavior Design of Autonomous Vehicles with Verification on Real Human Data](https://mlsanity.com/paper/2010.14712/) (2020)
- [Scenario-Transferable Semantic Graph Reasoning for Interaction-Aware Probabilistic Prediction](https://mlsanity.com/paper/2004.03053/) (2020)
- [Hierarchical Adaptable and Transferable Networks (HATN) for Driving Behavior Prediction](https://mlsanity.com/paper/2111.00788/) (2021)
- [Spatiotemporal Learning of Multivehicle Interaction Patterns in Lane-Change Scenarios](https://mlsanity.com/paper/2003.00759/) (2020)
- [A Framework for Probabilistic Generic Traffic Scene Prediction](https://mlsanity.com/paper/1810.12506/) (2018)

## Built on by (most cited first, 6 of 6)

- [Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer](https://mlsanity.com/paper/2207.14024/) (2022)
- [Transferable and Adaptable Driving Behavior Prediction](https://mlsanity.com/paper/2202.05140/) (2022)
- [T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory](https://mlsanity.com/paper/2403.10052/) (2024)
- [Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectives](https://mlsanity.com/paper/2505.09074/) (2025)
- [MetaTra: Meta-Learning for Generalized Trajectory Prediction in Unseen Domain](https://mlsanity.com/paper/2402.08221/) (2024)
- [MetaDAT: Generalizable Trajectory Prediction via Meta Pre-training and Data-Adaptive Test-Time Updating](https://mlsanity.com/paper/2603.09419/) (2026)

## Abstract (arXiv)

High fidelity behavior prediction of human drivers is crucial for efficient and safe deployment of autonomous vehicles, which is challenging due to the stochasticity, heterogeneity, and time-varying nature of human behaviors. On one hand, the trained prediction model can only capture the motion pattern in an average sense, while the nuances among individuals can hardly be reflected. On the other hand, the prediction model trained on the training set may not generalize to the testing set which may be in a different scenario or data distribution, resulting in low transferability and generalizability. In this paper, we applied a τ-step modified Extended Kalman Filter parameter adaptation algorithm (MEKFλ) to the driving behavior prediction task, which has not been studied before in literature. With the feedback of the observed trajectory, the algorithm is applied to neural-network-based models to improve the performance of driving behavior predictions across different human subjects and scenarios. A new set of metrics is proposed for systematic evaluation of online adaptation performance in reducing the prediction error for different individuals and scenarios. Empirical studies on the best layer in the model and steps of observation to adapt are also provided.