Socially interactive robots acting in public environments

• Grant number: 20/07074-3
• Support Opportunities: Regular Research Grants
• Start date: December 01, 2021
• End date: July 31, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Josué Junior Guimarães Ramos
• Grantee: Josué Junior Guimarães Ramos
• Host Institution: Centro de Pesquisas Renato Archer (CENPRA). Ministério da Ciência, Tecnologia e Inovação (Brasil). Campinas , SP, Brazil
• Associated researchers: Artemis Maria Francelin Sanchez Moroni ; Guilherme Bitencourt Nunes ; Helio Azevedo ; Marco Antonio Garcia de Carvalho ; Marcos Vinicius Cruz ; Murillo Rehder Batista ; Pedro Victor Vieira de Paiva ; Reid Gordon Simmons ; Roseli Aparecida Francelin Romero

Abstract

Robots' use in direct contact with humans in public environments, respecting social rules, represents a challenge for robotics, particularly for the area of human-robot interaction, whose main objective is to increase robots' acceptability by people. Research results with these characteristics provide robots' use increasingly acceptable in environments such as homes, industries, or public buildings such as hospitals and offices. The Brazilian context provides the mastery of technologies for proactive human-robot interaction that is the base for the still-nascent 5.0 industry. In this context, this research project, which has the participation of Brazilian and international partners, addresses the ability to detect complex emotions based on multimodal information and robotic navigation with social awareness in guide and reception tasks in public spaces, with studies carried out using datasets and experiments. Among the proposed contributions is developing approaches including techniques, evaluation, and datasets for detecting complex emotions from images and an unified framework for use in socially acceptable navigation. Case studies of the system will occur at the CTI Renato Archer facilities, where a robot will act as a receptionist. The robot will receive and guide leading visitors to meeting points with the person being visited, using information about the person's location and emotion to promote more acceptable interactions for people who will be received or guided. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

JOSHI, NEELAKSHI; PAIVA, PEDRO V. V.; BATISTA, MURILLO; CRUZ, MARCOS V.; RAMOS, JOSUE J. G.; IEEE. Improvements in Brazilian Portuguese Speech Emotion Recognition and its extension to Latin Corpora. 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), v. N/A, p. 8-pg., 2022-01-01. (20/07074-3)

PAIVA, PEDRO V. V.; RAMOS, JOSUE J. G.; GAVRILOVA, MARINA; CARVALHO, MARCO A. G.. Attention to Emotions: Body Emotion Recognition In-the-Wild Using Self-attention Transformer Network. COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VISIGRAPP 2023, v. 2103, p. 23-pg., 2024-01-01. (20/07074-3)

BATISTA, MURILLO REHDER; CRUZ, MARCOS VINICIUS; NUNES, GUILHERME BITTENCOURT; GUIMARAES RAMOS, JOSUE JUNIOR. Defining a Navigation Goal for Social Robots to Approach People. 2023 LATIN AMERICAN ROBOTICS SYMPOSIUM, LARS, 2023 BRAZILIAN SYMPOSIUM ON ROBOTICS, SBR, AND 2023 WORKSHOP ON ROBOTICS IN EDUCATION, WRE, v. N/A, p. 6-pg., 2023-01-01. (20/07074-3)