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

by   Letian Wang, et al.

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 (MEKF_λ) 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.


page 1

page 2

page 3

page 4


Robust Online Model Adaptation by Extended Kalman Filter with Exponential Moving Average and Dynamic Multi-Epoch Strategy

High fidelity behavior prediction of intelligent agents is critical in m...

Transferable and Adaptable Driving Behavior Prediction

While autonomous vehicles still struggle to solve challenging situations...

Hierarchical Adaptable and Transferable Networks (HATN) for Driving Behavior Prediction

When autonomous vehicles still struggle to solve challenging situations ...

Adaptable Human Intention and Trajectory Prediction for Human-Robot Collaboration

To engender safe and efficient human-robot collaboration, it is critical...

Training Algorithm Matters for the Performance of Neural Network Potential

One hidden yet important issue for developing neural network potentials ...

Target State Estimation and Prediction for High Speed Interception

Accurate estimation and prediction of trajectory is essential for interc...

Please sign up or login with your details

Forgot password? Click here to reset