The future challenge for field robots is to increase the level of autonomy towards long distance (>1 km) and duration (>1h) applications. One of the key technologies is the ability to accurately estimate the properties of the traversed terrain to optimize onboard control strategies and energy efficient path-planning, ensuring safety and avoiding possible immobilization conditions that would lead to mission failure. Two main hypotheses are put forward in this research. The first hypothesis is that terrain can be effectively detected by relying exclusively on the measurement of quantities that pertain to the robot-ground interaction, i.e., on proprioceptive signals. Therefore, no visual or depth information is required. Then, artificial deep neural networks can provide an accurate and robust solution to the classification problem of different terrain types. Under these hypotheses, sensory signals are classified as time series directly by a Recurrent Neural Network or by a Convolutional Neural Network in the form of higher-level features or spectrograms resulting from additional processing. In both cases, results obtained from real experiments show comparable or better performance when contrasted with standard Support Vector Machine with the additional advantage of not requiring an a priori definition of the feature space.

Recurrent and convolutional neural networks for deep terrain classification by autonomous robots / Vulpi, F.; Milella, A.; Marani, R.; Reina, G.. - In: JOURNAL OF TERRAMECHANICS. - ISSN 0022-4898. - STAMPA. - 96:(2021), pp. 119-131. [10.1016/j.jterra.2020.12.002]

Recurrent and convolutional neural networks for deep terrain classification by autonomous robots

Vulpi F.
Methodology
;
Milella A.;Marani R.
Membro del Collaboration Group
;
Reina G.
Conceptualization
2021-01-01

Abstract

The future challenge for field robots is to increase the level of autonomy towards long distance (>1 km) and duration (>1h) applications. One of the key technologies is the ability to accurately estimate the properties of the traversed terrain to optimize onboard control strategies and energy efficient path-planning, ensuring safety and avoiding possible immobilization conditions that would lead to mission failure. Two main hypotheses are put forward in this research. The first hypothesis is that terrain can be effectively detected by relying exclusively on the measurement of quantities that pertain to the robot-ground interaction, i.e., on proprioceptive signals. Therefore, no visual or depth information is required. Then, artificial deep neural networks can provide an accurate and robust solution to the classification problem of different terrain types. Under these hypotheses, sensory signals are classified as time series directly by a Recurrent Neural Network or by a Convolutional Neural Network in the form of higher-level features or spectrograms resulting from additional processing. In both cases, results obtained from real experiments show comparable or better performance when contrasted with standard Support Vector Machine with the additional advantage of not requiring an a priori definition of the feature space.
2021
Recurrent and convolutional neural networks for deep terrain classification by autonomous robots / Vulpi, F.; Milella, A.; Marani, R.; Reina, G.. - In: JOURNAL OF TERRAMECHANICS. - ISSN 0022-4898. - STAMPA. - 96:(2021), pp. 119-131. [10.1016/j.jterra.2020.12.002]
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/11589/232236
Citazioni
  • Scopus 27
  • ???jsp.display-item.citation.isi??? 21
social impact