A Formalisation of the Purpose Framework: the Autonomy-Alignment Problem in Open-Ended Learning Robots
This addresses the challenge of ensuring autonomous robots learn and behave in ways that align with human purposes, particularly in unstructured environments, though it appears incremental as it builds on existing conceptual work.
The paper tackles the autonomy-alignment problem in open-ended learning robots by proposing a computational framework based on the concept of purpose to balance autonomy and control, decomposing it into sub-problems like alignment, arbitration, grounding, and competence acquisition.
The unprecedented advancement of artificial intelligence enables the development of increasingly autonomous robots. These robots hold significant potential, particularly in moving beyond engineered factory settings to operate in the unstructured environments inhabited by humans. However, this possibility also generates a relevant autonomy-alignment problem to ensure that robots' autonomous learning processes still focus on acquiring knowledge relevant to accomplish human practical purposes, while their behaviour still aligns with their broader purposes. The literature has only begun to address this problem, and a conceptual, terminological, and formal framework is still lacking. Here we address one of the most challenging instances of the problem: autonomous open-ended learning (OEL) robots, capable of cumulatively acquiring new skills and knowledge through direct interaction with the environment, guided by self-generated goals and intrinsic motivations. In particular, we propose a computational framework, first introduced qualitatively and then formalised, to support the design of OEL robot architectures that balance autonomy and control. The framework pivots on the novel concept of purpose. A human purpose specifies what humans (e.g., designers or users) want the robot to learn, do or not do, within a certain boundary of autonomy and independently of the domains in which it operates.The framework decomposes the autonomy-alignment problem into more tractable sub-problems: the alignment of `robot purposes' with human purposes, either by hardwiring or through learning; the arbitration between multiple purposes; the grounding of purposes into specific domain-dependent robot goals; and the competence acquisition needed to accomplish these goals. The framework and its potential utility are further elucidated through the discussion of hypothetical example scenarios framed within it.