Open-Set Object Recognition Using Mechanical Properties During Interaction
This addresses the challenge of enabling tactile robots to operate in open-set conditions where test objects are beyond their prior knowledge, representing an incremental improvement in domain-specific robotics.
The paper tackles the problem of open-set object recognition for tactile robots by proposing a framework that uses mechanical properties to recognize known objects and incrementally label novel ones, achieving better recognition and clustering performance than alternative methods.
while most of the tactile robots are operated in close-set conditions, it is challenging for them to operate in open-set conditions where test objects are beyond the robots' knowledge. We proposed an open-set recognition framework using mechanical properties to recongise known objects and incrementally label novel objects. The main contribution is a clustering algorithm that exploits knowledge of known objects to estimate cluster centre and sizes, unlike a typical algorithm that randomly selects them. The framework is validated with the mechanical properties estimated from a real object during interaction. The results show that the framework could recognise objects better than alternative methods contributed by the novelty detector. Importantly, our clustering algorithm yields better clustering performance than other methods. Furthermore, the hyperparameters studies show that cluster size is important to clustering results and needed to be tuned properly.