Combining Planning and Learning for Autonomous Vehicle Navigation

AG Richards; P. Boyle

Combining Planning and Learning for Autonomous Vehicle Navigation

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

5 Citations (Scopus)

Abstract

This paper develops a navigation algorithm for vehicles in complex environments, combining a hard guarantee of constraint satisfaction with the ability to learn from successive missions. The method uses receding horizon control for constrained short-term path planning and control, with the cost-to-go developed by reinforcement learning. Simulation results show that the algorithm learns to reproduce the shortest path through an environment with obstacles and can determine good behaviours for multiple surveillance tasks.

Translated title of the contribution	Combining Planning and Learning for Autonomous Vehicle Navigation
Original language	English
Title of host publication	AIAA Guidance Navigation and Control Conference, Toronto
Publication status	Published - Aug 2010

Bibliographical note

Conference Organiser: AIAA
Other identifier: AIAA-2010-7866

Cite this

@inproceedings{b86470627dae47ee80736d5462c92506,

title = "Combining Planning and Learning for Autonomous Vehicle Navigation",

abstract = "This paper develops a navigation algorithm for vehicles in complex environments, combining a hard guarantee of constraint satisfaction with the ability to learn from successive missions. The method uses receding horizon control for constrained short-term path planning and control, with the cost-to-go developed by reinforcement learning. Simulation results show that the algorithm learns to reproduce the shortest path through an environment with obstacles and can determine good behaviours for multiple surveillance tasks.",

author = "AG Richards and P. Boyle",

note = "Conference Organiser: AIAA Other identifier: AIAA-2010-7866 ",

year = "2010",

month = aug,

language = "English",

booktitle = "AIAA Guidance Navigation and Control Conference, Toronto",

}

TY - GEN

T1 - Combining Planning and Learning for Autonomous Vehicle Navigation

AU - Richards, AG

AU - Boyle, P.

N1 - Conference Organiser: AIAA Other identifier: AIAA-2010-7866

PY - 2010/8

Y1 - 2010/8

N2 - This paper develops a navigation algorithm for vehicles in complex environments, combining a hard guarantee of constraint satisfaction with the ability to learn from successive missions. The method uses receding horizon control for constrained short-term path planning and control, with the cost-to-go developed by reinforcement learning. Simulation results show that the algorithm learns to reproduce the shortest path through an environment with obstacles and can determine good behaviours for multiple surveillance tasks.

AB - This paper develops a navigation algorithm for vehicles in complex environments, combining a hard guarantee of constraint satisfaction with the ability to learn from successive missions. The method uses receding horizon control for constrained short-term path planning and control, with the cost-to-go developed by reinforcement learning. Simulation results show that the algorithm learns to reproduce the shortest path through an environment with obstacles and can determine good behaviours for multiple surveillance tasks.

M3 - Conference Contribution (Conference Proceeding)

BT - AIAA Guidance Navigation and Control Conference, Toronto

ER -

Combining Planning and Learning for Autonomous Vehicle Navigation

Abstract

Bibliographical note

Fingerprint

Cite this