Machine Morality: From Harm-Avoidance to Human-Robot Cooperation

摘要

We present a new computational framework for modeling moral decision-making in artificial agents based on the notion of 'Machine Morality as Cooperation'. This framework integrates recent advances from cross-disciplinary moral decision-making literature into a single architecture. We build upon previous work outlining cognitive elements that an artificial agent would need for exhibiting latent morality, and we extend it by providing a computational realization of the cognitive architecture of such an agent. Our work has implications for cognitive and social robotics. Recent studies in human neuroimaging have pointed to three different decision-making processes, Pavlovian, model-free and model-based, that are defined by distinct neural substrates in the brain. Here, we describe how computational models of these three cognitive processes can be implemented in a single cognitive architecture by using the distributed and hierarchical organization proposed by the DAC theoretical framework. Moreover, we propose that a pro-social drive to cooperate exists at the Pavlovian level that can also bias the rest of the decision system, thus extending current state-of-the-art descriptive models based on harm-aversion.