A non-deterministic planner for planetary rovers

M. Ceriotti, Nicolas Croisard, Massimiliano Vasile

Research output: Contribution to conferencePaper

Abstract

This paper presents an integrated planning and scheduling algorithm based on co-evolutionary algorithms. This planner is the core of the delibera-tive level of a three-layer autonomous system (called Wisdom) for planetary rovers. The planner operates at two different levels: at a higher level reallocates and transforms mission goals, based on contingent events, in order to reach scientifically interesting targets and minimize the risk of a failure, at a lower level it generates scheduled sequences of actions that optimize a number of objectives. A particular implementation of co-evolutionary algorithms is used to generate sets of Pareto-optimal plans for every given sequence of goals. Some tests will illustrate the main characteristics of the algorithm.

Conference

ConferenceInternational Joint Conference on Artificial Intelligence (IJCAI)
CityHyderabad, India
Period6/01/0712/01/07

Fingerprint

Evolutionary algorithms
Scheduling algorithms
Planning

Keywords

  • planning and scheduling algorithm
  • planetary rovers
  • co-evolutionary algorithms
  • pareto-optimal plans
  • mission goals

Cite this

Ceriotti, M., Croisard, N., & Vasile, M. (2007). A non-deterministic planner for planetary rovers. Paper presented at International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, .
Ceriotti, M. ; Croisard, Nicolas ; Vasile, Massimiliano. / A non-deterministic planner for planetary rovers. Paper presented at International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, .
@conference{4497ab712b604f1f8209e3a32f56bcdd,
title = "A non-deterministic planner for planetary rovers",
abstract = "This paper presents an integrated planning and scheduling algorithm based on co-evolutionary algorithms. This planner is the core of the delibera-tive level of a three-layer autonomous system (called Wisdom) for planetary rovers. The planner operates at two different levels: at a higher level reallocates and transforms mission goals, based on contingent events, in order to reach scientifically interesting targets and minimize the risk of a failure, at a lower level it generates scheduled sequences of actions that optimize a number of objectives. A particular implementation of co-evolutionary algorithms is used to generate sets of Pareto-optimal plans for every given sequence of goals. Some tests will illustrate the main characteristics of the algorithm.",
keywords = "planning and scheduling algorithm, planetary rovers, co-evolutionary algorithms, pareto-optimal plans, mission goals",
author = "M. Ceriotti and Nicolas Croisard and Massimiliano Vasile",
year = "2007",
month = "1",
day = "6",
language = "English",
note = "International Joint Conference on Artificial Intelligence (IJCAI) ; Conference date: 06-01-2007 Through 12-01-2007",

}

Ceriotti, M, Croisard, N & Vasile, M 2007, 'A non-deterministic planner for planetary rovers' Paper presented at International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, 6/01/07 - 12/01/07, .

A non-deterministic planner for planetary rovers. / Ceriotti, M.; Croisard, Nicolas; Vasile, Massimiliano.

2007. Paper presented at International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - A non-deterministic planner for planetary rovers

AU - Ceriotti, M.

AU - Croisard, Nicolas

AU - Vasile, Massimiliano

PY - 2007/1/6

Y1 - 2007/1/6

N2 - This paper presents an integrated planning and scheduling algorithm based on co-evolutionary algorithms. This planner is the core of the delibera-tive level of a three-layer autonomous system (called Wisdom) for planetary rovers. The planner operates at two different levels: at a higher level reallocates and transforms mission goals, based on contingent events, in order to reach scientifically interesting targets and minimize the risk of a failure, at a lower level it generates scheduled sequences of actions that optimize a number of objectives. A particular implementation of co-evolutionary algorithms is used to generate sets of Pareto-optimal plans for every given sequence of goals. Some tests will illustrate the main characteristics of the algorithm.

AB - This paper presents an integrated planning and scheduling algorithm based on co-evolutionary algorithms. This planner is the core of the delibera-tive level of a three-layer autonomous system (called Wisdom) for planetary rovers. The planner operates at two different levels: at a higher level reallocates and transforms mission goals, based on contingent events, in order to reach scientifically interesting targets and minimize the risk of a failure, at a lower level it generates scheduled sequences of actions that optimize a number of objectives. A particular implementation of co-evolutionary algorithms is used to generate sets of Pareto-optimal plans for every given sequence of goals. Some tests will illustrate the main characteristics of the algorithm.

KW - planning and scheduling algorithm

KW - planetary rovers

KW - co-evolutionary algorithms

KW - pareto-optimal plans

KW - mission goals

M3 - Paper

ER -

Ceriotti M, Croisard N, Vasile M. A non-deterministic planner for planetary rovers. 2007. Paper presented at International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, .