A Multisensory Edge-Cloud Platform for Opportunistic Radio Sensing in Cobot Environments

Worker monitoring and protection in collaborative robot (cobots) industrialenvironments requires advanced sensing capabilities and flexible solutionsto monitor the movements of the operator in close proximity of movingrobots. Collaborative robotics is an active %represents a mushrooming research area where Internet of Things (IoT) and novel sensing technologies areexpected to play a critical role. Considering that no single technologycan currently solve the problem of continuous worker monitoring, thepaper targets the development of an IoT multisensor data fusion (MDF) platform.It is based on an edge-cloud architecture that supports the combination and transformation of multiple sensing technologies to enable the passive and anonymous detection of workers.Multidimensional data acquisition from different IoT sources, signalpre-processing, feature extraction, data distribution and fusion,along with machine learning (ML) and computing methods are described. Theproposed IoT platform also comprises a practical solution for datafusion and analytics. It is able to perform opportunistic and real-time perceptionof workers by fusing and analyzing radio signals obtainedfrom several interconnected IoT components, namely a multi-antenna WiFi installation (2.4-5 GHz), a sub-THz imaging camera (100 GHz), a network of radars (122 GHz) and infrared sensors (8-13 µm). The performance of the proposed IoT platform is validated through real use case scenarios inside a pilot industrial plant in which protective human--robot distance must be guaranteed considering latency and detection uncertainties.