This paper tackles the challenge of predicting grasp failures in soft hands before they happen, by combining deep learning with a sensing strategy based on distributed Inertial Measurement Units. We propose two neural architectures, which we implemented and tested with an articulated soft hand-the Pisa/IIT SoftHand-and a continuously deformable soft hand-the RBO Hand. The first architecture (Classifier) implements a-posteriori detection of the failure event, serving as a test-bench to assess the possibility of extracting failure information from the discussed input signals. This network reaches up to 100% of accuracy within our experimental validation. Motivated by these results, we introduce a second architecture (Predictor), which is the main contribution of the paper. This network works on-line and takes as input a multidimensional continuum stream of raw signals coming from the Inertial Measurement Units. The network is trained to predict the occurrence in the near future of a failure event. The Predictor detects 100% of failures with both hands, with the detection happening on average 1.96 seconds before the actual failing occurs-leaving plenty of time to an hypothetical controller to react.

To grasp or not to grasp: An end-to-end deep-learning approach for predicting grasping failures in soft hands / Arapi, V.; Zhang, Y.; Averta, G.; Catalano, M. G.; Rus, D.; Santina, C. D.; Bianchi, M.. - (2020), pp. 653-660. (Intervento presentato al convegno 3rd IEEE International Conference on Soft Robotics, RoboSoft 2020 tenutosi a usa nel 2020) [10.1109/RoboSoft48309.2020.9116041].

To grasp or not to grasp: An end-to-end deep-learning approach for predicting grasping failures in soft hands

Averta G.;
2020

Abstract

This paper tackles the challenge of predicting grasp failures in soft hands before they happen, by combining deep learning with a sensing strategy based on distributed Inertial Measurement Units. We propose two neural architectures, which we implemented and tested with an articulated soft hand-the Pisa/IIT SoftHand-and a continuously deformable soft hand-the RBO Hand. The first architecture (Classifier) implements a-posteriori detection of the failure event, serving as a test-bench to assess the possibility of extracting failure information from the discussed input signals. This network reaches up to 100% of accuracy within our experimental validation. Motivated by these results, we introduce a second architecture (Predictor), which is the main contribution of the paper. This network works on-line and takes as input a multidimensional continuum stream of raw signals coming from the Inertial Measurement Units. The network is trained to predict the occurrence in the near future of a failure event. The Predictor detects 100% of failures with both hands, with the detection happening on average 1.96 seconds before the actual failing occurs-leaving plenty of time to an hypothetical controller to react.
2020
978-1-7281-6570-7
File in questo prodotto:
File Dimensione Formato  
To_grasp_or_not_to_grasp_an_end-to-end_deep-learning_approach_for_predicting_grasping_failures_in_soft_hands.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.98 MB
Formato Adobe PDF
1.98 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
ROSO20_0057_FI_1.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 6.31 MB
Formato Adobe PDF
6.31 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2970280