Abstract

The mechatronic paradigm adopted today, although successful, may prevent a wider use of robotic systems. For example, system complexity increases with functions, leading to more than linearly increasing costs and power usage and decreasing robustness. RoboCom++ will pursue a radically new design paradigm, grounded in the scientific studies of intelligence in nature. This approach will allow achieving complex functionalities in a new bodyware with limited use of computing resources, mass and energy, with the aim of exploiting compliance instead of fighting it. Simplification mechanisms will be based on the concepts of embodied intelligence, morphological computation, simplexity, and evolutionary and developmental approaches. Exploring these concepts in order to develop new scientific knowledge and new robots that can effectively negotiate natural environments, better interact with human beings, and provide services and support in a variety of real-world, real-life activities, requires a coordinated and federated initiative. Ultimately, the Companion Robots conceived in RoboCom++ may foster a new wave of economic growth in Europe.

Objectives

The main objective of the RoboCom++ project is to lay the foundation for a future global interdisciplinary research programme on a new science-based transformative Robotics, to be launched by the end of the H2020 Programme. RoboCom++ will gather the community and organize the knowledge necessary to rethink the design principles and fabrication technologies of future robots. RoboCom++ will aim at developing the cooperative robots (or Companion Robots) of the year 2030. The RoboCom++ community will pursue these ambitious objectives by cooperating along three main lines of action: 1) building the community and the tools for research reproducibility (benchmarks, metrics, data sharing protocols, test platforms, standards); 2) proof-of-concept research pilots; and 3) defining the long-term S&T roadmap, competitiveness strategy, governing and financing structure, and the ethical, legal, economic and social framework of a future FET Flagship –like initiative on Robotics . RoboCom++ will actively pursue collaboration with industry, along with dissemination, community outreach and participation of EU citizens and stakeholders, with particular attention to the issue of robots and jobs.

Estimated results

Employment of computational processes inspired by natural evolution to design effective and adaptive robot bodies and brains for complex tasks and environments. Research questions that will answered are: to what extent do evolutionary methods capture the complexity of designing soft bodies and their behaviour? Do evolutionary methods design soft robots with morphological computation? How to simultaneously evolve and develop body and behaviour? What is the level of robot autonomy that can be reached? Specifically deep learning technologies will be exploited to improve today’s robots. As such, data-driven nonheuristic subject-specific alternative architectures will be designed based on the concepts from deep learning to enhance the information from the raw physiological (EEG) signal in Brain-Computer-Interface applications.