J. Eilbrecht, M. Bieshaar, S. Zernetsch, K. Doll, B. Sick, and O. Stursberg, “Model-predictive Planning for Autonomous Vehicles Anticipating Intentions of Vulnerable Road Users by Artificial Neural Networks,” in 2017 IEEE Symposium Series on Computational Intelligence (SSCI), Institute of Electrical and Electronics Engineers, Ed. Piscataway, NJ: IEEE, 2017, pp. 1–8.
Abstract
This article presents a hierarchical path planning framework that allows to generate plans for autonomous vehicles in the presence of vulnerable road users (VRUs), such as pedestrians and cyclists. Contrasting many existing approaches, the hierarchical approach allows not only to resolve emergency situations, but also to consider regular settings. Planning is based on model predictive control (MPC), which allows to make optimal, anticipatory decisions based on forecasts of the intentions of VRUs while explicitly accounting for constraints. The VRU trajectory forecast is based on a polynomial least-squares approximation of the VRU's trajectories in combination with a multilayer perceptron artificial neural network for prediction over a future horizon. The efficacy of the proposed framework is demonstrated for two example scenarios.
BibTex
@INPROCEEDINGS{ES17c,
AUTHOR={J. Eilbrecht and M. Bieshaar and S. Zernetsch and K. Doll and B. Sick and O. Stursberg},
TITLE={{Model-Predictive Planning for Autonomous Vehicles Anticipating Intentions of Vulnerable Road Users by Artificial Neural Networks}},
BOOKTITLE={Proc. IEEE Symposium Series on Computational Intelligence},
YEAR={2017},
PAGES={1-8},
COMMENT={noch nicht gemeldet, ISBN: ?, ? Normseiten}}
URL