Nombre: IGOR BATISTA VIEIRA
Fecha de publicación: 06/10/2025
Junta de examinadores:
Nombre |
Papel |
|---|---|
| ANSELMO FRIZERA NETO | Presidente |
| CAMILO ARTURO RODRIGUEZ DIAZ | Examinador Interno |
| PABLO JAVIER ALSINA | Examinador Externo |
| RICARDO CARMINATI DE MELLO | Coorientador |
Sumario: Conventional teleoperation interfaces, based on two-dimensional monitors and non-
immersive controllers, present significant limitations for human-robot interaction.
The absence of depth perception, restricted field of view, and high cognitive load
hinder the operator’s ability to build an accurate mental model of the remote envi-
ronment, reducing the effectiveness of robot control. In this context, the integration
of immersive technologies and haptic devices emerges as an alternative to enhance
the user’s sense of presence, overcome perceptual barriers, and make teleoperation
more natural and efficient.
To address these challenges, this dissertation proposes the development of a multi-
modal teleoperation system, composed of a mobile robotic platform equipped with
perception sensors, a simultaneous localization and mapping (SLAM) module, and
an immersive interface based on Virtual Reality integrated with a haptic device.
The architecture was designed to operate in a distributed manner, with processing
shared between the robot and the operator station, enabling the construction of a
low-latency digital twin. Two experimental studies were conducted: the first vali-
dated the accuracy of the visual mapping system compared to classical approaches,
while the second evaluated the haptic interface in user teleoperation tasks.
The results obtained confirmed the hypothesis that the combination between Vir-
tual Reality and haptic feedback provides a telepresence experience superior to tra-
ditional solutions. The system demonstrated robustness in environment mapping,
low response time in data transmission, and an increased sense of immersion re-
ported by the users. Specifically, the user study demonstrated that the immersive
interface was able to reduce the average number of collisions from 3.00 to less than
0.3 and decrease the perceived workload (NASA-TLX) by more than 50%. These
findings highlight the potential of the proposed approach as a relevant contribution
to the advancement of robotic teleoperation, with possible applications in remote
inspection, hazardous environments, and human-robot collaboration systems.
