Safe multi-channel communication for human–robot collaboration

Abstract

This paper presents a safe multi-channel communication and safety system for human–robot collaboration (HRC) in industrial applications enabled by the DiGeTac unit. This unit integrates gesture, distance, and custom-designed tactile sensors, with gesture and distance elements on the top and the tactile element on the bottom. This design provides enhanced multimodal safety and interaction, enabling both close proximity and long-distance perception, making the DiGeTac unit highly suitable for various collaborative scenarios. Unlike other multimodal sensors, DiGeTac offers contactless and touch-based interaction, and post- and pre-collision safety features for a broader range of tasks in HRC environments. The performance of each sensing element within the DiGeTac unit is thoroughly evaluated through a series of validation experiments with a robot arm. The distance sensor’s accuracy is assessed in pre-collision scenarios, ensuring reliable proximity detection for collision avoidance as part of the safety strategy. The tactile sensor is tested in a post-collision scenario, where it functions as a safety mechanism to detect impacts and trigger protective responses. The capability of hand gestures recognition to facilitate intuitive human–robot communication is evaluated using an artificial neural network (ANN). Additionally, the tactile sensor’s contact estimation is analysed with a convolutional neural network (CNN), enhancing the robot’s ability to interact with humans and perform collaborative tasks. Finally, both safety and interaction strategies are tested in HRC scenarios, where the human operator commands the robot to move to specific positions. The results show that the DiGeTac unit is effective and has potential to improve complex collaborative tasks. • Multimodal sensing module enabling dynamic safety and interaction modes. • Implementation of pre- and post-collision safety strategies. • Gesture and touch-based multimodal control for intuitive human–robot collaboration. • Real-time validation of safety and interaction in an assembly task.