Haptic support systems have been widely used for supporting human operators when performing a control task. These systems are commonly designed to track known target trajectories. However, knowledge of the desired trajectory can not be assumed in many realistic cases. This paper proposes a possible approach to design a haptic shared control system for helicopter control tasks, when the target trajectory is not known a priori. First, a Pilot Intent Estimator (PIE) is developed to infer pilot intent. Then, the corresponding intended trajectory is generated. Eventually, a haptic feedback is designed to track the estimated intended trajectory. The designed PIE was evaluated in a preliminary test with an experienced helicopter pilot. Then, a human-in-the-loop experiment with minimal-trained participants was conducted to assess the proposed shared control system. Results showed the effectiveness of the PIE to correctly estimate pilot intent and to generate a good estimate of the intended trajectory. Moreover, the haptic feedback helped participants to accomplish the control task with lower tracking error (i.e, better performance) compared to manual control.

A 2-DoF Haptic Support System for Helicopter Control Tasks based on Pilot Intent Estimation

Giulia D’Intino
;
Mario Olivari;Lorenzo Pollini
2019-01-01

Abstract

Haptic support systems have been widely used for supporting human operators when performing a control task. These systems are commonly designed to track known target trajectories. However, knowledge of the desired trajectory can not be assumed in many realistic cases. This paper proposes a possible approach to design a haptic shared control system for helicopter control tasks, when the target trajectory is not known a priori. First, a Pilot Intent Estimator (PIE) is developed to infer pilot intent. Then, the corresponding intended trajectory is generated. Eventually, a haptic feedback is designed to track the estimated intended trajectory. The designed PIE was evaluated in a preliminary test with an experienced helicopter pilot. Then, a human-in-the-loop experiment with minimal-trained participants was conducted to assess the proposed shared control system. Results showed the effectiveness of the PIE to correctly estimate pilot intent and to generate a good estimate of the intended trajectory. Moreover, the haptic feedback helped participants to accomplish the control task with lower tracking error (i.e, better performance) compared to manual control.
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/11568/940980
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact