Purpose for Open-Ended Learning Robots: A Computational Taxonomy, Definition, and Operationalisation

2024-03-04

arXiv.org

AI Summary

This work addresses the fundamental tension between autonomy and human-goal alignment in open-ended embodied learning (OEL) robots. We propose a purpose-driven autonomous learning framework that departs from conventional goal-oriented approaches by introducing a three-tiered motivational hierarchy—purpose → desire → state-level goal. We formally define three core challenges: purpose-desire alignment, purpose-to-goal embodiment, and desire arbitration. To address them, we integrate intrinsic motivation-driven learning, computational motivation modeling, and autonomous goal grounding. Experiments demonstrate that our framework preserves unsupervised, continual exploration capability while significantly improving the relevance and practical utility of acquired skills to users’ real-world tasks. The work establishes a computationally grounded theory of purpose representation and provides a deployable architectural foundation for developing trustworthy, controllable general-purpose embodied intelligence.

Technology Category

• Intelligent Robots: Embodied AI
• Multiagent Systems: Multiagent Learning
• Humans and AI: Learning Human Values and Preferences

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Autonomous open-ended learning (OEL) robots are able to cumulatively acquire new skills and knowledge through direct interaction with the environment, for example relying on the guidance of intrinsic motivations and self-generated goals. OEL robots have a high relevance for applications as they can use the autonomously acquired knowledge to accomplish tasks relevant for their human users. OEL robots, however, encounter an important limitation: this may lead to the acquisition of knowledge that is not so much relevant to accomplish the users' tasks. This work analyses a possible solution to this problem that pivots on the novel concept of `purpose'. Purposes indicate what the designers and/or users want from the robot. The robot should use internal representations of purposes, called here `desires', to focus its open-ended exploration towards the acquisition of knowledge relevant to accomplish them. This work contributes to develop a computational framework on purpose in two ways. First, it formalises a framework on purpose based on a three-level motivational hierarchy involving: (a) the purposes; (b) the desires, which are domain independent; (c) specific domain dependent state-goals. Second, the work highlights key challenges highlighted by the framework such as: the `purpose-desire alignment problem', the `purpose-goal grounding problem', and the `arbitration between desires'. Overall, the approach enables OEL robots to learn in an autonomous way but also to focus on acquiring goals and skills that meet the purposes of the designers and users.

Problem

• Addressing autonomy-alignment in open-ended learning robots
• Balancing robot autonomy with human purpose alignment
• Formalizing purpose framework for OEL robot design

Innovation

• Formal framework for autonomy-alignment in robots
• Purpose-driven OEL robot architecture design
• Decomposition into tractable sub-problems