This paper addresses the problem of robust plan execution in the context of exploration mission plans carried on by planetary rovers. In order to deal with limited computational resources, and with limited rover’s autonomy (the rover is not allowed to change its plan), the paper proposes a novelmethodology to cope with contingencies rising at execution time. The approach aims at reconfiguring on the fly the plan by changing the parameter configuration of the actions still to be executed. By exploiting an enriched action representation based on the notion of execution modalities, the ReCon system is able to (i) early detect the violation of mission resource constraints, (ii) find (if any) a new assignment of modalities to preserve the mission plan constraints. ReCon uses constraint satisfaction techniques both for plan consistency and plan reconfiguration. Finally, the paper reports a preliminary set of experimental results which in practice confirms the feasibility and the advantages of the approach.

Satisfying Resource Constraints in Space Missions by On-line Task Reconfiguration

MICALIZIO, ROBERTO;SCALA, ENRICO;TORASSO, Pietro
2012-01-01

Abstract

This paper addresses the problem of robust plan execution in the context of exploration mission plans carried on by planetary rovers. In order to deal with limited computational resources, and with limited rover’s autonomy (the rover is not allowed to change its plan), the paper proposes a novelmethodology to cope with contingencies rising at execution time. The approach aims at reconfiguring on the fly the plan by changing the parameter configuration of the actions still to be executed. By exploiting an enriched action representation based on the notion of execution modalities, the ReCon system is able to (i) early detect the violation of mission resource constraints, (ii) find (if any) a new assignment of modalities to preserve the mission plan constraints. ReCon uses constraint satisfaction techniques both for plan consistency and plan reconfiguration. Finally, the paper reports a preliminary set of experimental results which in practice confirms the feasibility and the advantages of the approach.
2012
11th International Symposium on Artificial Intelligence, Robotics and Automation in Space (i-SAIRAS)
Torino (Italy)
September 4 - 6, 2012
Proceedings of the 11th International Symposium on Artificial Intelligence, Robotics and Automation in Space (i-SAIRAS)
ESA (European Space Agency)
1
8
http://robotics.estec.esa.int/i-SAIRAS/isairas2012/i-SAIRAS2012.pdf
Plan execution; Artifical Intelligence; Robotics; Space exploration
Roberto Micalizio; Enrico Scala; and Pietro Torasso
File in questo prodotto:
File Dimensione Formato  
ISAIRAS12.pdf

Accesso aperto

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 158.86 kB
Formato Adobe PDF
158.86 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/129613
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact