Supervised Representation Learning towards Generalizable Assembly State Recognition
This work addresses scalability and robustness challenges in assembly procedures for industrial workers, offering incremental improvements to enhance efficiency and reduce errors.
The paper tackles the problem of assembly state recognition in industrial settings, proposing a representation learning approach with a novel intermediate-state informed loss (ISIL) that improves clustering and classification performance across architectures and accurately distinguishes correct states from execution errors.
Assembly state recognition facilitates the execution of assembly procedures, offering feedback to enhance efficiency and minimize errors. However, recognizing assembly states poses challenges in scalability, since parts are frequently updated, and the robustness to execution errors remains underexplored. To address these challenges, this paper proposes an approach based on representation learning and the novel intermediate-state informed loss function modification (ISIL). ISIL leverages unlabeled transitions between states and demonstrates significant improvements in clustering and classification performance for all tested architectures and losses. Despite being trained exclusively on images without execution errors, thorough analysis on error states demonstrates that our approach accurately distinguishes between correct states and states with various types of execution errors. The integration of the proposed algorithm can offer meaningful assistance to workers and mitigate unexpected losses due to procedural mishaps in industrial settings. The code is available at: https://timschoonbeek.github.io/state_rec