Adaptive Meta-Learning for Identification of Rover-Terrain Dynamics

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Banerjee, S., Harrison, J., Furlong, P. M., Pavone, M.
Natura: Preprint
Pubblicazione: 2020
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909603570122752
author Banerjee, S.
Harrison, J.
Furlong, P. M.
Pavone, M.
author_facet Banerjee, S.
Harrison, J.
Furlong, P. M.
Pavone, M.
contents Rovers require knowledge of terrain to plan trajectories that maximize safety and efficiency. Terrain type classification relies on input from human operators or machine learning-based image classification algorithms. However, high level terrain classification is typically not sufficient to prevent incidents such as rovers becoming unexpectedly stuck in a sand trap; in these situations, online rover-terrain interaction data can be leveraged to accurately predict future dynamics and prevent further damage to the rover. This paper presents a meta-learning-based approach to adapt probabilistic predictions of rover dynamics by augmenting a nominal model affine in parameters with a Bayesian regression algorithm (P-ALPaCA). A regularization scheme is introduced to encourage orthogonality of nominal and learned features, leading to interpretable probabilistic estimates of terrain parameters in varying terrain conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2009_10191
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Adaptive Meta-Learning for Identification of Rover-Terrain Dynamics
Banerjee, S.
Harrison, J.
Furlong, P. M.
Pavone, M.
Robotics
Machine Learning
Rovers require knowledge of terrain to plan trajectories that maximize safety and efficiency. Terrain type classification relies on input from human operators or machine learning-based image classification algorithms. However, high level terrain classification is typically not sufficient to prevent incidents such as rovers becoming unexpectedly stuck in a sand trap; in these situations, online rover-terrain interaction data can be leveraged to accurately predict future dynamics and prevent further damage to the rover. This paper presents a meta-learning-based approach to adapt probabilistic predictions of rover dynamics by augmenting a nominal model affine in parameters with a Bayesian regression algorithm (P-ALPaCA). A regularization scheme is introduced to encourage orthogonality of nominal and learned features, leading to interpretable probabilistic estimates of terrain parameters in varying terrain conditions.
title Adaptive Meta-Learning for Identification of Rover-Terrain Dynamics
topic Robotics
Machine Learning
url https://arxiv.org/abs/2009.10191