Planetary micro-rover operations on Mars using a Bayesian framework for inference and control

Mark A. Post, Junquan Li, Brendan M. Quine

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

With the recent progress toward the application of commercially-available hardware to small-scale space missions, it is now becoming feasible for groups of small, efficient robots based on low-power embedded hardware to perform simple tasks on other planets in the place of large-scale, heavy and expensive robots. In this paper, we describe design and programming of the Beaver micro-rover developed for Northern Light, a Canadian initiative to send a small lander and rover to Mars to study the Martian surface and subsurface. For a small, hardware-limited rover to handle an uncertain and mostly unknown environment without constant management by human operators, we use a Bayesian network of discrete random variables as an abstraction of expert knowledge about the rover and its environment, and inference operations for control. A framework for efficient construction and inference into a Bayesian network using only the C language and fixed-point mathematics on embedded hardware has been developed for the Beaver to make intelligent decisions with minimal sensor data. We study the performance of the Beaver as it probabilistically maps a simple outdoor environment with sensor models that include uncertainty. Results indicate that the Beaver and other small and simple robotic platforms can make use of a Bayesian network to make intelligent decisions in uncertain planetary environments.
LanguageEnglish
Pages295-314
Number of pages20
JournalActa Astronautica
Volume120
Early online date25 Dec 2015
DOIs
Publication statusPublished - 26 Jan 2016

Fingerprint

Bayesian networks
Hardware
Robots
Sensors
Planets
Random variables
Robotics
Rodentia

Keywords

  • Rover
  • decision-making
  • probalistic
  • Bayesian
  • inference
  • Mars

Cite this

Post, Mark A. ; Li, Junquan ; Quine, Brendan M. / Planetary micro-rover operations on Mars using a Bayesian framework for inference and control. In: Acta Astronautica. 2016 ; Vol. 120. pp. 295-314.
@article{e339290ce29d41f6b30b40805c7a1b04,
title = "Planetary micro-rover operations on Mars using a Bayesian framework for inference and control",
abstract = "With the recent progress toward the application of commercially-available hardware to small-scale space missions, it is now becoming feasible for groups of small, efficient robots based on low-power embedded hardware to perform simple tasks on other planets in the place of large-scale, heavy and expensive robots. In this paper, we describe design and programming of the Beaver micro-rover developed for Northern Light, a Canadian initiative to send a small lander and rover to Mars to study the Martian surface and subsurface. For a small, hardware-limited rover to handle an uncertain and mostly unknown environment without constant management by human operators, we use a Bayesian network of discrete random variables as an abstraction of expert knowledge about the rover and its environment, and inference operations for control. A framework for efficient construction and inference into a Bayesian network using only the C language and fixed-point mathematics on embedded hardware has been developed for the Beaver to make intelligent decisions with minimal sensor data. We study the performance of the Beaver as it probabilistically maps a simple outdoor environment with sensor models that include uncertainty. Results indicate that the Beaver and other small and simple robotic platforms can make use of a Bayesian network to make intelligent decisions in uncertain planetary environments.",
keywords = "Rover, decision-making, probalistic, Bayesian, inference, Mars",
author = "Post, {Mark A.} and Junquan Li and Quine, {Brendan M.}",
year = "2016",
month = "1",
day = "26",
doi = "10.1016/j.actaastro.2015.12.019",
language = "English",
volume = "120",
pages = "295--314",
journal = "Acta Astronautica",
issn = "0094-5765",

}

Planetary micro-rover operations on Mars using a Bayesian framework for inference and control. / Post, Mark A.; Li, Junquan; Quine, Brendan M.

In: Acta Astronautica, Vol. 120, 26.01.2016, p. 295-314.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Planetary micro-rover operations on Mars using a Bayesian framework for inference and control

AU - Post, Mark A.

AU - Li, Junquan

AU - Quine, Brendan M.

PY - 2016/1/26

Y1 - 2016/1/26

N2 - With the recent progress toward the application of commercially-available hardware to small-scale space missions, it is now becoming feasible for groups of small, efficient robots based on low-power embedded hardware to perform simple tasks on other planets in the place of large-scale, heavy and expensive robots. In this paper, we describe design and programming of the Beaver micro-rover developed for Northern Light, a Canadian initiative to send a small lander and rover to Mars to study the Martian surface and subsurface. For a small, hardware-limited rover to handle an uncertain and mostly unknown environment without constant management by human operators, we use a Bayesian network of discrete random variables as an abstraction of expert knowledge about the rover and its environment, and inference operations for control. A framework for efficient construction and inference into a Bayesian network using only the C language and fixed-point mathematics on embedded hardware has been developed for the Beaver to make intelligent decisions with minimal sensor data. We study the performance of the Beaver as it probabilistically maps a simple outdoor environment with sensor models that include uncertainty. Results indicate that the Beaver and other small and simple robotic platforms can make use of a Bayesian network to make intelligent decisions in uncertain planetary environments.

AB - With the recent progress toward the application of commercially-available hardware to small-scale space missions, it is now becoming feasible for groups of small, efficient robots based on low-power embedded hardware to perform simple tasks on other planets in the place of large-scale, heavy and expensive robots. In this paper, we describe design and programming of the Beaver micro-rover developed for Northern Light, a Canadian initiative to send a small lander and rover to Mars to study the Martian surface and subsurface. For a small, hardware-limited rover to handle an uncertain and mostly unknown environment without constant management by human operators, we use a Bayesian network of discrete random variables as an abstraction of expert knowledge about the rover and its environment, and inference operations for control. A framework for efficient construction and inference into a Bayesian network using only the C language and fixed-point mathematics on embedded hardware has been developed for the Beaver to make intelligent decisions with minimal sensor data. We study the performance of the Beaver as it probabilistically maps a simple outdoor environment with sensor models that include uncertainty. Results indicate that the Beaver and other small and simple robotic platforms can make use of a Bayesian network to make intelligent decisions in uncertain planetary environments.

KW - Rover

KW - decision-making

KW - probalistic

KW - Bayesian

KW - inference

KW - Mars

U2 - 10.1016/j.actaastro.2015.12.019

DO - 10.1016/j.actaastro.2015.12.019

M3 - Article

VL - 120

SP - 295

EP - 314

JO - Acta Astronautica

T2 - Acta Astronautica

JF - Acta Astronautica

SN - 0094-5765

ER -