Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ROSA: A Knowledge-based Solution for Robot Self-Adaptation

Gustavo Rezende Silva, Juliane Päßler, S. Lizeth Tapia Tarifa, Einar Broch Johnsen, Carlos Hernández Corbato

TL;DR

ROSA tackles the challenge of robust robot operation across diverse tasks and environments by introducing a knowledge-based framework that enables runtime task-and-architecture co-adaptation (TACA). It centralizes all adaptation knowledge in a reusable knowledge model and uses runtime reasoning (via TypeDB) to decide when and how to reconfigure both task execution and software architecture, interfacing with ROS 2, BTs, and PDDL planners. The paper contributes a modular ROSA architecture, a reusable knowledge model capturing architectural, heuristic, and reconfiguration knowledge, and an open-source ROS 2-based implementation validated on the SUAVE underwater exemplar, demonstrating feasibility, reusability across domains, and scalable development effort. The results show ROSA can achieve effective TACA with competitive performance, enabling reuse across robotic systems and reducing bespoke adaptation effort, with future directions including learning-based adaptations and broader decision-making integrations.

Abstract

Autonomous robots must operate in diverse environments and handle multiple tasks despite uncertainties. This creates challenges in designing software architectures and task decision-making algorithms, as different contexts may require distinct task logic and architectural configurations. To address this, robotic systems can be designed as self-adaptive systems capable of adapting their task execution and software architecture at runtime based on their context.This paper introduces ROSA, a novel knowledge-based framework for RObot Self-Adaptation, which enables task-and-architecture co-adaptation (TACA) in robotic systems. ROSA achieves this by providing a knowledge model that captures all application-specific knowledge required for adaptation and by reasoning over this knowledge at runtime to determine when and how adaptation should occur. In addition to a conceptual framework, this work provides an open-source ROS 2-based reference implementation of ROSA and evaluates its feasibility and performance in an underwater robotics application. Experimental results highlight ROSA's advantages in reusability and development effort for designing self-adaptive robotic systems.

ROSA: A Knowledge-based Solution for Robot Self-Adaptation

TL;DR

ROSA tackles the challenge of robust robot operation across diverse tasks and environments by introducing a knowledge-based framework that enables runtime task-and-architecture co-adaptation (TACA). It centralizes all adaptation knowledge in a reusable knowledge model and uses runtime reasoning (via TypeDB) to decide when and how to reconfigure both task execution and software architecture, interfacing with ROS 2, BTs, and PDDL planners. The paper contributes a modular ROSA architecture, a reusable knowledge model capturing architectural, heuristic, and reconfiguration knowledge, and an open-source ROS 2-based implementation validated on the SUAVE underwater exemplar, demonstrating feasibility, reusability across domains, and scalable development effort. The results show ROSA can achieve effective TACA with competitive performance, enabling reuse across robotic systems and reducing bespoke adaptation effort, with future directions including learning-based adaptations and broader decision-making integrations.

Abstract

Autonomous robots must operate in diverse environments and handle multiple tasks despite uncertainties. This creates challenges in designing software architectures and task decision-making algorithms, as different contexts may require distinct task logic and architectural configurations. To address this, robotic systems can be designed as self-adaptive systems capable of adapting their task execution and software architecture at runtime based on their context.This paper introduces ROSA, a novel knowledge-based framework for RObot Self-Adaptation, which enables task-and-architecture co-adaptation (TACA) in robotic systems. ROSA achieves this by providing a knowledge model that captures all application-specific knowledge required for adaptation and by reasoning over this knowledge at runtime to determine when and how adaptation should occur. In addition to a conceptual framework, this work provides an open-source ROS 2-based reference implementation of ROSA and evaluates its feasibility and performance in an underwater robotics application. Experimental results highlight ROSA's advantages in reusability and development effort for designing self-adaptive robotic systems.
Paper Structure (46 sections, 7 figures, 7 tables)

This paper contains 46 sections, 7 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Running example
  3. Related work
  4. Robotics Architectures
  5. Self-adaptive robotic systems
  6. Architecture
  7. Robotics architecture
  8. ROSA architecture
  9. Knowledge base
  10. Knowledge model
  11. Architectural knowledge
  12. Adaptation heuristic knowledge
  13. Reconfiguration plan knowledge
  14. Rules
  15. Architecture realization
  16. ...and 31 more sections

Figures (7)

  • Figure 1: The upper layer depicts ROSA's architecture and the bottom layer depicts the robotic system.
  • Figure 4: ROS specific knowledge
  • Figure 5: BT pattern for TACA with ROSA. The IsActionFeasible condition node takes the action name as a parameter. The MyAction node derives from the proposed RosaAction node and implements the action execution. The action names in the BT must match the names defined in the KB.
  • Figure 6: ROSA model for SUAVE.
  • Figure 7: Behavior tree for the extended SUAVE use case
  • ...and 2 more figures