1. Goal-Driven Autonomy Learning for Long-Duration Missions Héctor Muñoz-Avila

2. Goal-Driven Autonomy (GDA) Key concepts: Expectation: the expected state after executing an action. Discrepancy: A mismatch between expected state and actual state. Explanation: A reason for the mismatch. Goal: State or desired states. GDA is a model of introspective reasoning in which an agent revises its own goals Where the GDA knowledge is coming from?

3. Objectives Enable greater autonomy and flexibility for unmanned systems  A key requirement of the project is for autonomous systems to be robust over long periods of time  Very difficult to encode for all possible circumstances in advance (i.e., months ahead).  Changes (e.g., environmental) over time Need for learning: adapt to a changing environment.  GDA knowledge needs to adapt to uncertain and dynamic environments while performing long-duration activities

4. Goal-Driven Autonomy (GDA) Concrete Objective: Learn/adapt the GDA knowledge elements for each of the four components Three levels:  At the object (TREX) level,  At the meta-cognition (MIDCA) level, and  At the integrative object and meta-reasoning (MIDCA+TREX) level

5. Goal Management Learning An initial set of priorities can be set at the beginning of the deployment But for a long-term mission such priorities will need to be adjusted automatically as a function of changes in the environment. For example, by default we might prioritize sonar sensory goals  E.g., to determine potential hazardous conditions surrounding the UUV

6. Goal Management Learning - Example Situation: four unknown contacts in area Default: identification of each contact can be set as a goal  Each goal can be associated with a priority as a function of the distance to the UUV  Unknown contact has some initial sensor readings Adaptation: once the contact have been identified, system might change the priority of future contacts with same sensor readings  E.g., giving higher priority to contact that could be a rapid moving vessel  Initial sensor readings for same target might change as a result of changing environmental conditions

7. Goal Formulation Learning New goals can be formulated depending on:  the discrepancies encountered  the explanation generated and  the observations from state Example:  As before, unknown contact has some initial sensor readings  Contact turns out to be a large mass that moves very close to the vehicle forcing trajectory change  New goal: keep distance from contact with initial readings

8. Explanation Learning Explanations are assumed to be deterministic:  Discrepancy  Explanation But these frequently assume perfect observability Need to relax this assumption to handle sensor information Associate priorities to explanations  Need to be adapted over time  Prior work studied underpinnings  Need to consider sensor readings

9. Expectation Learning Expectations need to consider time intervals. Must take into account the plan look-ahead and latency These two factors can be adapted over time by reasoning at the integrative object and meta-reasoning (MIDCA+TREX) level

10. Conclusions Operating autonomously over long periods of time is a challenging task:  Too difficult to pre-define all circumstances in advance.  Conditions change over time Our vision is for UUVs that adapt to uncertain and dynamic environments while performing long- duration activities  By learning and refining GDA knowledge