Home   Research Publications Members Related Software
IndexBrowse   BibliographiesMy selection
 Search: in   (word length ≥ 3)
      Login
Publication no #592   Download bibtex file Type :   Html | Bib | Both
Add to my selection
Machine Learning Meets Quantitative Planning: Enabling Self-adaptation in Autonomous Robots

Pooyan Jamshidi, Javier Cámara, Bradley Schmerl, Christian Kästner and David Garlan.


In Proceedings of the 14th Symposium on Software Engineering for Adaptive and Self-Managing Systems, Montreal, Canada, 25-26 May 2019.

Online links: PDF

Abstract
Modern cyber-physical systems (e.g., robotics systems) are typically composed of physical and software components, the characteristics of which are likely to change over time. Assumptions about parts of the system made at design time may not hold at run time, especially when a system is deployed for long periods (e.g., over decades). Self-adaptation is designed to find reconfigurations of systems to handle such run-time inconsistencies. Planners can be used to find and enact optimal reconfigurations in such an evolving context. However, for systems that are highly configurable, such planning becomes intractable due to the size of the adaptation space. To overcome this challenge, in this paper we explore an approach that (a) uses machine learning to find Pareto-optimal configurations without needing to explore every configuration, and (b) restricts the search space to such configurations to make planning tractable. We explore this in the context of robot missions that need to consider task timeliness and energy consumption. An independent evaluation shows that our approach results in high quality adaptation plans in uncertain and adversarial environments.

Keywords: Cyberphysical Systems, Self-adaptation.  
@InProceedings{2019/Jamshidi/ML,
      AUTHOR = {Jamshidi, Pooyan and C\'{a}mara, Javier and Schmerl, Bradley and K\"astner, Christian and Garlan, David},
      TITLE = {Machine Learning Meets Quantitative Planning: Enabling Self-adaptation in Autonomous Robots},
      YEAR = {2019},
      MONTH = {25-26 May},
      BOOKTITLE = {Proceedings of the 14th Symposium on Software Engineering for Adaptive and Self-Managing Systems},
      ADDRESS = {Montreal, Canada},
      PDF = {http://acme.able.cs.cmu.edu/pubs/uploads/pdf/SEAMS2019-ML.pdf},
      ABSTRACT = {Modern cyber-physical systems (e.g., robotics systems) are typically composed of physical and software components, the characteristics of which are likely to change over time. Assumptions about parts of the system made at design time may not hold at run time, especially when a system is deployed for long periods (e.g., over decades). Self-adaptation is designed to find reconfigurations of systems to handle such run-time inconsistencies. Planners can be used to find and enact optimal reconfigurations in such an evolving context. However, for systems that are highly configurable, such planning becomes intractable due to the size of the adaptation space. To overcome this challenge, in this paper we explore an approach that (a) uses machine learning to find Pareto-optimal configurations without needing to explore every configuration, and (b) restricts the search space to such configurations to make planning tractable. We explore this in the context of robot missions that need to consider task timeliness and energy consumption. An independent evaluation shows that our approach results in high quality adaptation plans in uncertain and adversarial environments. },
      KEYWORDS = {Cyberphysical Systems, Self-adaptation}
}
    Created: 2019-01-17 14:04:46     Modified: 2020-01-29 15:39:50
Feedback: ABLE Webmaster
Last modified: Sat October 12 2019 16:15:32
        BibAdmin