Risk bounded nonlinear robot motion planning with integrated perception & control
(2023) In Artificial Intelligence 314.- Abstract
Robust autonomy stacks require tight integration of perception, motion planning, and control layers, but these layers often inadequately incorporate inherent perception and prediction uncertainties, either ignoring them altogether or making questionable assumptions of Gaussianity. Robots with nonlinear dynamics and complex sensing modalities operating in an uncertain environment demand more careful consideration of how uncertainties propagate across stack layers. We propose a framework to integrate perception, motion planning, and control by explicitly incorporating perception and prediction uncertainties into planning so that risks of constraint violation can be mitigated. Specifically, we use a nonlinear model predictive control based... (More)
Robust autonomy stacks require tight integration of perception, motion planning, and control layers, but these layers often inadequately incorporate inherent perception and prediction uncertainties, either ignoring them altogether or making questionable assumptions of Gaussianity. Robots with nonlinear dynamics and complex sensing modalities operating in an uncertain environment demand more careful consideration of how uncertainties propagate across stack layers. We propose a framework to integrate perception, motion planning, and control by explicitly incorporating perception and prediction uncertainties into planning so that risks of constraint violation can be mitigated. Specifically, we use a nonlinear model predictive control based steering law coupled with a decorrelation scheme based Unscented Kalman Filter for state and environment estimation to propagate the robot state and environment uncertainties. Subsequently, we use distributionally robust risk constraints to limit the risk in the presence of these uncertainties. Finally, we present a layered autonomy stack consisting of a nonlinear steering-based distributionally robust motion planning module and a reference trajectory tracking module. Our numerical experiments with nonlinear robot models and an urban driving simulator show the effectiveness of our proposed approaches.
(Less)
- author
- Renganathan, Venkatraman LU ; Safaoui, Sleiman ; Kothari, Aadi ; Gravell, Benjamin ; Shames, Iman and Summers, Tyler
- organization
- publishing date
- 2023
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Distributional robustness, Integrated perception & planning, Risk-bounded motion planning
- in
- Artificial Intelligence
- volume
- 314
- article number
- 103812
- publisher
- Elsevier
- external identifiers
-
- scopus:85143508347
- ISSN
- 0004-3702
- DOI
- 10.1016/j.artint.2022.103812
- language
- English
- LU publication?
- yes
- id
- a8b433ad-7620-4af3-9ef2-8fb227e73e9b
- date added to LUP
- 2023-02-07 15:12:28
- date last changed
- 2023-02-07 15:12:28
@article{a8b433ad-7620-4af3-9ef2-8fb227e73e9b,
abstract = {{<p>Robust autonomy stacks require tight integration of perception, motion planning, and control layers, but these layers often inadequately incorporate inherent perception and prediction uncertainties, either ignoring them altogether or making questionable assumptions of Gaussianity. Robots with nonlinear dynamics and complex sensing modalities operating in an uncertain environment demand more careful consideration of how uncertainties propagate across stack layers. We propose a framework to integrate perception, motion planning, and control by explicitly incorporating perception and prediction uncertainties into planning so that risks of constraint violation can be mitigated. Specifically, we use a nonlinear model predictive control based steering law coupled with a decorrelation scheme based Unscented Kalman Filter for state and environment estimation to propagate the robot state and environment uncertainties. Subsequently, we use distributionally robust risk constraints to limit the risk in the presence of these uncertainties. Finally, we present a layered autonomy stack consisting of a nonlinear steering-based distributionally robust motion planning module and a reference trajectory tracking module. Our numerical experiments with nonlinear robot models and an urban driving simulator show the effectiveness of our proposed approaches.</p>}},
author = {{Renganathan, Venkatraman and Safaoui, Sleiman and Kothari, Aadi and Gravell, Benjamin and Shames, Iman and Summers, Tyler}},
issn = {{0004-3702}},
keywords = {{Distributional robustness; Integrated perception & planning; Risk-bounded motion planning}},
language = {{eng}},
publisher = {{Elsevier}},
series = {{Artificial Intelligence}},
title = {{Risk bounded nonlinear robot motion planning with integrated perception & control}},
url = {{http://dx.doi.org/10.1016/j.artint.2022.103812}},
doi = {{10.1016/j.artint.2022.103812}},
volume = {{314}},
year = {{2023}},
}