Hybrid Approach for Vehicle Trajectory Prediction Using Weighted Integration of Multiple Models
Open Access
- 26 May 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 78715-78723
Abstract
Prediction of surrounding vehicles accurately is an essential prerequisite for safe autonomous driving. Trajectory prediction methods can be classified into physics-, maneuver-, or learning-based methods. Learning-based methods have been studied extensively in recent years because it effectively exploits the road information and interactions among vehicles. However, learning-based methods perform poorly in unseen environments that were not considered during training and provide unreasonable results such as inconsistent trajectories according to road geometry. In this paper, to address this problem, a hybrid model that combines a learning-based model with physics- and maneuver-based models according to their uncertainties is proposed. The deep ensemble technique is also used to estimate the uncertainty of the learning-based method. Because the deep ensemble tends to show a large variance in unseen environments, this method is used to determine whether to use a hybrid model. The proposed method is trained and validated using the Lyft l5 dataset, the real environment vehicle driving data containing several types of intersections.Keywords
Funding Information
- Korea Evaluation Institute of Industrial Technology
This publication has 23 references indexed in Scilit:
- Tracking and Behavior Reasoning of Moving Vehicles Based on Roadway Geometry ConstraintsIEEE Transactions on Intelligent Transportation Systems, 2016
- Deep Residual Learning for Image Recognition2016
- Trajectory prediction of cyclists using a physical model and an artificial neural network2016
- An Integrated Approach to Maneuver-Based Trajectory Prediction and Criticality Assessment in Arbitrary Road EnvironmentsIEEE Transactions on Intelligent Transportation Systems, 2016
- A survey on motion prediction and risk assessment for intelligent vehiclesROBOMECH Journal, 2014
- Model-Based Threat Assessment for Avoiding Arbitrary Vehicle CollisionsIEEE Transactions on Intelligent Transportation Systems, 2010
- Maneuver-Based Trajectory Planning for Highly Autonomous Vehicles on Real Road With Traffic and Driver InteractionIEEE Transactions on Intelligent Transportation Systems, 2010
- The unscented Kalman filter for nonlinear estimation2002
- Scaling up dynamic time warping for datamining applications2000
- Vehicle dynamics and external disturbance estimation for vehicle path predictionIEEE Transactions on Control Systems Technology, 2000