Improving Competence for Reliable Autonomy

  title={Improving Competence for Reliable Autonomy},
  author={Connor Basich and Justin Svegliato and Kyle Hollins Wray and S. Witwicki and S. Zilberstein},
  • Connor Basich, Justin Svegliato, +2 authors S. Zilberstein
  • Published in AREA@ECAI 2020
  • Computer Science
  • Given the complexity of real-world, unstructured domains, it is often impossible or impractical to design models that include every feature needed to handle all possible scenarios that an autonomous system may encounter. For an autonomous system to be reliable in such domains, it should have the ability to improve its competence online. In this paper, we propose a method for improving the competence of a system over the course of its deployment. We specifically focus on a class of semi… CONTINUE READING

    Figures and Topics from this paper


    Learning to Optimize Autonomy in Competence-Aware Systems
    • 5
    • PDF
    Interactive Policy Learning through Confidence-Based Autonomy
    • 225
    • PDF
    The STRANDS Project: Long-Term Autonomy in Everyday Environments
    • 130
    • PDF
    A Framework for Learning From Demonstration With Minimal Human Effort
    • 1
    • PDF
    Hierarchical Approach to Transfer of Control in Semi-Autonomous Systems: (Extended Abstract)
    • 23
    • PDF
    Belief Space Metareasoning for Exception Recovery
    • 9
    Do Not Make the Same Mistakes Again and Again: Learning Local Recovery Policies for Navigation From Human Demonstrations
    • 6
    • PDF
    Explainable Agents and Robots: Results from a Systematic Literature Review
    • 81
    • PDF
    Continual planning for search and rescue robots
    • 11
    • PDF
    Integrating Sample-Based Planning and Model-Based Reinforcement Learning
    • 106
    • PDF