The PILLAR-Robots consortium, consisting of 6 partners, focuses on revolutionizing the capabilities of robots. Their aim is to create a new generation of robots with enhanced autonomy, empowering them to establish goals, devise strategies, and leverage their accumulated experience to effectively meet the desires of their human designers and users in real-life scenarios.
To achieve this goal, the consortium is operationalizing the concept of Purpose, derived from cognitive sciences. This approach aims to bolster the robots’ autonomy and domain independence during autonomous learning while ensuring the acquisition of knowledge and skills that are highly relevant to operating in practical applications.
The project encompasses various aspects. Firstly, algorithms will be developed to facilitate the acquisition of purpose by the robots. Additionally, the perceptual, motivational, and decision systems of the robots’ cognitive architectures will be strategically biased towards fulfilling purposes. Furthermore, the project will focus on formulating strategies for learning representations, skills, and models that enable purpose-driven deliberative and reactive decision-making processes.
Project’s Main Objectives
- Operationalize the concept of Purpose to provide a structured way to bias autonomy toward achieving the desires of the designer/user in a domain-independent manner.
- Create a reference purposeful Intrinsically Motivated Cognitive Architecture for lifelong open-ended autonomy.
- Implement and validate demonstrators of purposeful lifelong open-ended autonomy in real applications within three application domains characterized by different types and levels of variability.
- Evaluate the possibilities and impacts of Purposeful Life Long Open-ended Autonomy in these application realms and in society in general (ethics, regulation, markets, and a societal perspective).
- Develop specific actions for fostering adoption and sustainability of the PILLAR-Robot framework across key stakeholders to maximize its impact by contributing to effective communication and training in AI – Data- Robotics.
By harnessing the power of Purpose, the PILLAR-Robots consortium is trying to develop a better way for intelligent and self-directed robots to adapt to real-world application use cases.