Multi-Class Human/Object Detection on Robot Manipulators using Proprioceptive Sensing
This work addresses safety and workflow efficiency in human-robot collaboration, but it is incremental as it extends prior binary classification to three classes.
The study tackled the problem of identifying contacted objects in physical human-robot collaboration by developing multi-class detection models, achieving 91.11% accuracy in real-time testing.
In physical human-robot collaboration (pHRC) settings, humans and robots collaborate directly in shared environments. Robots must analyze interactions with objects to ensure safety and facilitate meaningful workflows. One critical aspect is human/object detection, where the contacted object is identified. Past research introduced binary machine learning classifiers to distinguish between soft and hard objects. This study improves upon those results by evaluating three-class human/object detection models, offering more detailed contact analysis. A dataset was collected using the Franka Emika Panda robot manipulator, exploring preprocessing strategies for time-series analysis. Models including LSTM, GRU, and Transformers were trained on these datasets. The best-performing model achieved 91.11\% accuracy during real-time testing, demonstrating the feasibility of multi-class detection models. Additionally, a comparison of preprocessing strategies suggests a sliding window approach is optimal for this task.