PANDORA: Persistent Autonomy through Learning, Adaptation, Observation and Re-planning

David Michael Lane; Francesco Maurelli; Thomas Larkworthy; Darwin Caldwell; Joaquim Salvi; Maria Fox; Kostas Kyriakopoulos

PANDORA: Persistent Autonomy through Learning, Adaptation, Observation and Re-planning

David Michael Lane, Francesco Maurelli, Thomas Larkworthy, Darwin Caldwell, Joaquim Salvi, Maria Fox, Kostas Kyriakopoulos

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Autonomous robots are not very good at being autonomous. Operating in real environments, they easily get stuck, often ask for help, and generally succeed only when attempting simple tasks in well-known situations. PANDORA is a three year project that will develop and evaluate new computational methods to make underwater robots Persistently Autonomous, significantly reducing the frequency of assistance requests. The key to this is an ability to recognise failure and respond to it, at all levels of abstraction and time constant. Under the guidance of major industrial players, validation tasks of Inspection, cleaning and valve turning will be trialled with partners’ AUVs in Scotland and Spain.

Original language	English
Title of host publication	Proc IFAC Int Conference on Navigation, Guidance and Control of Underwater Vehicles, Porto, Portugal
Publisher	International Federation of Automatic Control (IFAC)
Publication status	Published - 10 Apr 2012

Cite this

@inproceedings{b15c7c1e65794fdabdd4df2f351d6449,

title = "PANDORA: Persistent Autonomy through Learning, Adaptation, Observation and Re-planning",

abstract = "Autonomous robots are not very good at being autonomous. Operating in real environments, they easily get stuck, often ask for help, and generally succeed only when attempting simple tasks in well-known situations. PANDORA is a three year project that will develop and evaluate new computational methods to make underwater robots Persistently Autonomous, significantly reducing the frequency of assistance requests. The key to this is an ability to recognise failure and respond to it, at all levels of abstraction and time constant. Under the guidance of major industrial players, validation tasks of Inspection, cleaning and valve turning will be trialled with partners{\textquoteright} AUVs in Scotland and Spain.",

author = "Lane, {David Michael} and Francesco Maurelli and Thomas Larkworthy and Darwin Caldwell and Joaquim Salvi and Maria Fox and Kostas Kyriakopoulos",

year = "2012",

month = apr,

day = "10",

language = "English",

booktitle = "Proc IFAC Int Conference on Navigation, Guidance and Control of Underwater Vehicles, Porto, Portugal",

publisher = "International Federation of Automatic Control (IFAC)",

}

PANDORA: Persistent Autonomy through Learning, Adaptation, Observation and Re-planning. / Lane, David Michael; Maurelli, Francesco; Larkworthy, Thomas et al.
Proc IFAC Int Conference on Navigation, Guidance and Control of Underwater Vehicles, Porto, Portugal. International Federation of Automatic Control (IFAC), 2012.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - PANDORA: Persistent Autonomy through Learning, Adaptation, Observation and Re-planning

AU - Lane, David Michael

AU - Maurelli, Francesco

AU - Larkworthy, Thomas

AU - Caldwell, Darwin

AU - Salvi, Joaquim

AU - Fox, Maria

AU - Kyriakopoulos, Kostas

PY - 2012/4/10

Y1 - 2012/4/10

N2 - Autonomous robots are not very good at being autonomous. Operating in real environments, they easily get stuck, often ask for help, and generally succeed only when attempting simple tasks in well-known situations. PANDORA is a three year project that will develop and evaluate new computational methods to make underwater robots Persistently Autonomous, significantly reducing the frequency of assistance requests. The key to this is an ability to recognise failure and respond to it, at all levels of abstraction and time constant. Under the guidance of major industrial players, validation tasks of Inspection, cleaning and valve turning will be trialled with partners’ AUVs in Scotland and Spain.

AB - Autonomous robots are not very good at being autonomous. Operating in real environments, they easily get stuck, often ask for help, and generally succeed only when attempting simple tasks in well-known situations. PANDORA is a three year project that will develop and evaluate new computational methods to make underwater robots Persistently Autonomous, significantly reducing the frequency of assistance requests. The key to this is an ability to recognise failure and respond to it, at all levels of abstraction and time constant. Under the guidance of major industrial players, validation tasks of Inspection, cleaning and valve turning will be trialled with partners’ AUVs in Scotland and Spain.

M3 - Conference contribution

BT - Proc IFAC Int Conference on Navigation, Guidance and Control of Underwater Vehicles, Porto, Portugal

PB - International Federation of Automatic Control (IFAC)

ER -

PANDORA: Persistent Autonomy through Learning, Adaptation, Observation and Re-planning

Abstract

Fingerprint

Cite this