Human activity modelling and recognition for collaborative robotics based on hand-object interaction
| Main Authors: | Lucci, Niccolo, Monguzzi, Andrea, Zanchettin, Andrea Maria, Rocco, Paolo |
|---|---|
| Format: | Proceeding Journal |
| Terbitan: |
, 2021
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/6367908 |
Daftar Isi:
- With the future advent of Industry 5.0 it is necessary to develop and enhance collaborative robotics, introduced within the Industry 4.0 paradigm. This entails establishing a new paradigm to handle the communication and interaction between the actors of the workcell. Collaboration is then improved, making it more fluent, reliable, and able to correct workers' oversights. To this end, this paper introduces a new architecture that combines the reliability of PLC logic with the scalability of predicates tailored to a specific process. Such logic and predicates are masked to the operator through an interface that intervenes only when errors have to be notified. After giving a semantic meaning to each object of the workstation, the proposed architecture supervises the worker during the whole operation, modelling errors and recovering from them.