TORNADO will develop an innovative, multifunctional and adaptive cloud robotics platform, supporting advanced navigation of an autonomous mobile robot (AMR) within complex, time-varying, real-world, human-populated indoor environments. The TORNADO AMR will be able to manipulate small, soft or deformable objects (SSDs) to an unprecedented degree of success, as well as to naturally interact with humans via hand gestures or verbal conversation, by exploiting the zero-shot generalization abilities of deep neural Foundation Models (FMs) for robotics. The AMR's intelligence will rely on a pool of pretrained cloud-hosted FMs, which shall be further adjusted on-the-fly to the current situation via Out-of-Distribution Detection, Test-Time Adaptation and Few-Shot Adaptation subsystems. These will exploit human feedback if available, but will also support autonomous and dynamic cognitive adaptation. Additionally, the TORNADO system will be able to automatically select and set-up on-the-fly the most suitable combination of FMs and non-neural robotics algorithms during deployment, depending on the current situation. In cases of failure, on-the-fly skill acquisition will be supported via integrated, novel Learning-from-Demonstration methods facilitated by an innovative Augmented Reality (AR) interface and eXplainable AI (XAI) algorithms. The adaptive TORNADO system will allow the robot to perform difficult, non-repetitive manipulation tasks on previously unseen SSDs that may change shape during handling, as well as to flexibly adjust to SSDs of different sizes during operation. Measurement of human trust to interactive robots and human behavioral modeling will aid optimal integration/acceptance of TORNADO into society. Validation will take place at TRL-5 in 3 different industrial Use-Cases: flexible small gears manipulation and deformable ply-sheets handling (gears factory), palliative patient care (hospital) and product quality sampling/waste collection (dairy processing plant).

Collaborative robotics has established itself as a major force in pushing forward highly adaptive and flexible production paradigms in European large and small-medium enterprises. It is contributing to the sustainability and enhancement of Europe’s efficient and competitive manufacturing, to reshoring production, and to economic growth. However, still today the potential of collaborative technologies is largely underexploited. Indeed, collaborative robots are most often designed to coexist and to safely share a working space with humans. They are rarely thought to enter in direct socio-physical contact with humans to perceive, understand, and react to their distress or needs, and to enable them to work more productively and efficiently through better ergonomics. SOPHIA responds to this need by developing a new generation of socially cooperative human-robot systems in agile production. Its modular core technologies will enable dynamic state monitoring of the human-robot pair and anticipatory robot behaviours to: (1) improve human ergonomics, trust in automation, and productivity in manufacturing environments, and (2) achieve a reconfigurable, flexible, and resource-efficient production. By advancing the decisional autonomy and interaction ability of its innovative collaborative systems, SOPHIA will contribute to the reduction of work-related musculoskeletal disorders, the single largest category of work-related injuries and responsible for 30% of all workers’ compensation costs. SOPHIA’s societal relevance and the research groups’ experience in acceptability and standardization aspects of its core technologies will ensure their comfort-of-use by industrial workers, and the underlying design compliance to standards, thus strengthening the competitiveness in European manufacturing. We will illustrate and verify SOPHIA usability through the exploration of three real-world use-cases encouraging potential customers to integrate our core technologies in their workflow.