SHAGE: A Framework for SHAGE: A Framework for Self- -managed Robot - PDF document

SHAGE: A Framework for SHAGE: A Framework for Self- -managed Robot managed Robot Self Software Software Sooyong Park <sypark@sogang.ac.kr> Software Systems Engineering Lab. Sogang University May. 21~22, 2006 ICSE 2006 Workshop on Software Engineering for Adaptive and Self-Managing Systems(SEAMS), Shanghai, China May 21~22, 2006 SEAMS, Shanghai, China Outline Outline • Introduction • An Approach • SHAGE Framework • Demonstration • Research Issues • Conclusions 2 May 21~22, 2006 SEAMS, Shanghai, China 1

Home Service Robots for the Elderly Home Service Robots for the Elderly • Home service robots(HSR) provide useful services such as – Face recognition – Navigation – Bringing an object – Conversation – … • CIR(the Center for Intelligent Robotics) at KIST(the Korea Institute of Science and Technology) has been developed various home service robots. – T-Rot(High-end), Infotainment robot, H-Robot(Healthcare robot) 3 May 21~22, 2006 SEAMS, Shanghai, China Overall S/W Architecture 1) 1) of HSR of HSR Overall S/W Architecture Task Manager Deliberative Layer Sequencing Layer … Behavior Control Behavior Control Behavior Control Component Component Component SHAGE Framework Functional Unit Functional Unit Functional Unit Component Component Component Functional Unit Functional Unit Component Functional Unit Component Component Reactive Layer Action Components Action Components Action Components Action Components 1) E. Gat, “On three-layer architectures,” in Artificial Intelligence and Mobile Robots (D. Kortenkamp, R. P. Bonnasso, and R. Murphy, eds.), MIT/AAAI, 1997. 4 May 21~22, 2006 SEAMS, Shanghai, China 2

Research Motivation Research Motivation Malfunction User’s new needs new Environment Limited Resources Self-Healing, Adaptive, and Growing Technologies for Intelligent Robots Self-Healing, Adaptive, and Growing Technologies for Intelligent Robots 5 May 21~22, 2006 SEAMS, Shanghai, China Example – – (1) (1) Example • Need for safety: an old man says “ move carefully! ” – During a party: a lot of unrecorded moving objects Quality requirement: Quality requirement: Don’t care execution time, but avoid Don’t care execution time, but avoid all possible collisions all possible collisions Montion Controller Reconfigured Architecture: Reconfigured Architecture: ready to use various sensors and to ready to use various sensors and to make a map by using the sensors. make a map by using the sensors. AutoMove MapBuilder Localizer PathPlanner SkinProxy SonarProxy LaserProxy VisionProxy 6 May 21~22, 2006 SEAMS, Shanghai, China 3

Example – – (2) (2) Example • Need for agility: an old man says “ move quickly! ” – The old man is home alone: no unrecorded object Quality requirement: Quality requirement: Short response time, Short Short response time, Short execution time, optimize use of execution time, optimize use of batteries. batteries. Montion Controller Reconfigured Architecture: Reconfigured Architecture: ready to use one sensor(laser). ready to use one sensor(laser). It cannot avoid (unrecorded) moving objects It cannot avoid (unrecorded) moving objects AutoMove MapBuilder Localizer PathPlanner LaserProxy 7 May 21~22, 2006 SEAMS, Shanghai, China Our Approach Our Approach Monitoring Monitoring Brokering Brokering Learning Learning Decision Decision Reconfigu Reconfigu- - Making Making ration ration 8 May 21~22, 2006 SEAMS, Shanghai, China 4

SHAGE Framework SHAGE Framework • SHAGE(Self-Healing, Adaptive, and Growing SoftwarE) Framework integrates following technologies – Monitoring – Brokering: Ontology(authoring relations between environmental information and architectural information) – Decision & Learning: Case-Based Decision Theory – Reconfiguration: Slot-based architectural style • This framework provides a test bed for self-managed software. 9 May 21~22, 2006 SEAMS, Shanghai, China SHAGE Overall Architecture SHAGE Overall Architecture 10 May 21~22, 2006 SEAMS, Shanghai, China 5

Architecture/Component Broker Architecture/Component Broker Current Situation A set of Inclination-Situation Pairs (given by the Candidate Set Task Manager) <i 1 , s 1 > (reduced by the Architecture Broker) <i 1 , s 2 > … <i n , s m > … A set of architecture configurations (Abstract Level Architectures) 11 May 21~22, 2006 SEAMS, Shanghai, China Architecture/Component Broker Architecture/Component Broker • Role – Searching abstract-level architecture configurations related to the current situation. • Technology – Ontological descriptions. • Current Status – It can only search in a small set of configurations related to the navigation subsystem. – Rule-based search: it cannot relax rules. 12 May 21~22, 2006 SEAMS, Shanghai, China 6

Decision Maker & Learner Decision Maker & Learner Candidate Set (reduced by the Architecture Broker) Selected Concrete Component (Selected by the Decision Maker) Selected Architecture Configuration (Selected by the Decision Maker) … A set of architecture configurations (Abstract Level Architectures) 13 May 21~22, 2006 SEAMS, Shanghai, China Decision Maker & Learner Decision Maker & Learner • Role – Selecting exactly one configuration and one component for each slot from the candidate set retrieved by the architecture broker. • Technology – Case-Based Decision Theory • Current Status – It only carries out in limited scope. – Limited search space: only in the navigation subsystem. – Limited learning time: few scenarios. 14 May 21~22, 2006 SEAMS, Shanghai, China 7

Reconfigurator Reconfigurator Before Reconfiguration After Reconfiguration Before Reconfiguration After Reconfiguration Slot: MotionControl Slot: Coordinator Slot: Localizer Slot: MotionControl Slot: Coordinator Slot: SLAM Slot: PathPlanner Slot: PathPlanner Slot: MapBuilder Abstract Level Concrete Level Slot: MotionControl Slot: Coordinator Slot: SLAM Slot: MotionControl Slot: Coordinator Slot: Localizer B A.1 C1 C2 F A B C C1 C1 C1 C1 C2 D E Slot: PathPlanner G Slot: PathPlanner Slot: MapBuilder 15 May 21~22, 2006 SEAMS, Shanghai, China Reconfigurator Reconfigurator • Role – Reconfiguring the current software architecture dynamically. • Technology – Slot-based two-level software architectural style. • Current Status – It has reconfigured only the navigation subsystem. All configurations for the subsystem were verified in the demonstration. • – It can manage components distributed in SBCs(Single Board Computers) by RMI. – It supports components implemented in Java and C++(through JNI). 16 May 21~22, 2006 SEAMS, Shanghai, China 8

Demonstration Demonstration 17 May 21~22, 2006 SEAMS, Shanghai, China Research Issues Research Issues • Internal monitoring • Ontology construction • Learning speed • Run-time measurement and validation • Componentization • Domain Knowledge 18 May 21~22, 2006 SEAMS, Shanghai, China 9

Conclusions Conclusions SHAGE Framework has been developed to provide ‘ self-managing • capabilities ’ to robot software. The framework integrated ontology, decision theory, and dynamic • architecture and comprises Monitor – Architecture/Component Broker – Decision Maker & Learner – Reconfigurator – In the experiment, we showed a simple scenario. • The robot managed its architecture to adapt its changing requirements. – The second phase(three years) of our research just launched to • improve key technologies. 19 May 21~22, 2006 SEAMS, Shanghai, China 10