Virtualização de ambientes em tempo real para interação multimodal : teleoperação com uso de realidade mista e feedback háptico

• Ano de defesa: 2025
• Autor(a) principal: Vieira, Igor Batista
• Orientador(a): Frizera Neto, Anselmo
• Banca de defesa: Rodríguez Díaz, Camilo Arturo , Alsina, Pablo Javier
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Espírito Santo; Mestrado em Engenharia Elétrica
• Programa de Pós-Graduação: Programa de Pós-Graduação em Engenharia Elétrica
• Departamento: Centro Tecnológico
• País: BR
• Palavras-chave em Português: Teleoperação; Interface multimodal; Realidade virtual; Feedback háptico; Robótica móvel; Teleoperation; Multimodal interface; Virtual reality; Haptic feedback; Mobile robotics
• Área do conhecimento CNPq: Engenharia Elétrica
• Link de acesso: http://repositorio.ufes.br/handle/10/20522

Conventionalteleoperationinterfaces, basedontwo-dimensionalmonitorsandnon 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 f indings 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.