Moving Horizon Planning and Control for Autonomous Vehicles with Active Exploration and Fallback Strategies

Mohamed Soliman, Rolf Findeisen

2024

Abstract

Navigating autonomous vehicles within a partially known environment to achieve a specific goal is an impor- tant yet challenging problem. It necessitates ensuring the safety of the vehicle along its trajectory, accounting for potentially unknown obstacles while maintaining the vehicle’s capability to navigate the path at all times. Conventionally, a safe path is devised based on the available offline information. This does not exploit ad- ditional environmental information that can be obtained during movement. In a hierarchical moving horizon planning and control framework, we recast the lower-level vehicle control problem as a dual control prob- lem, where the objective extends beyond merely following a given path to include active exploration. This exploration involves acquiring additional information to reduce the uncertainty about obstacles encountered, potentially improving overall performance. Recognizing that active exploration can incur additional costs or lead the vehicle into situations where obstacles impede the traveled path, we propose a fallback strategy that involves returning to a known, possibly suboptimal, path. The approach is illustrated through simulations.

Paper Citation

in Harvard Style

Soliman M. and Findeisen R. (2024). Moving Horizon Planning and Control for Autonomous Vehicles with Active Exploration and Fallback Strategies. In Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO; ISBN 978-989-758-717-7, SciTePress, pages 359-367. DOI: 10.5220/0012996200003822

in Bibtex Style

@conference{icinco24,
author={Mohamed Soliman and Rolf Findeisen},
title={Moving Horizon Planning and Control for Autonomous Vehicles with Active Exploration and Fallback Strategies},
booktitle={Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO},
year={2024},
pages={359-367},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012996200003822},
isbn={978-989-758-717-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO
TI - Moving Horizon Planning and Control for Autonomous Vehicles with Active Exploration and Fallback Strategies
SN - 978-989-758-717-7
AU - Soliman M.
AU - Findeisen R.
PY - 2024
SP - 359
EP - 367
DO - 10.5220/0012996200003822
PB - SciTePress