Cooperative social robots to accompany groups of people

Abstract

This study proposes a new model for guiding people in urban settings using multiple robots that work cooperatively. More specifically, this investigation describes the circumstances in which people might stray from the formation when following different robots' instructions. To this end, we introduce a "Prediction and Anticipation Model" that predicts the position of the group using a Particle Filter, while determining the optimal robot behavior to help people stay in the group in areas where they may become distracted. As a result, this article presents a novel approach to locally optimizing the work performed by robots and people using the minimum robots' work criterion and determining human-friendly types of movements. The guidance missions were carried out in urban areas that included multiple conflict areas and obstacles. This study also provides an analysis of robots' behavioral reactions to people by simulating different situations in the locations that were used for the investigation. The method was tested through simulations that took into account the difficulties and technological constraints derived from real-life situations. Despites these problematic issues, we were able to demonstrate the robots' effect on people in real-life situations in terms of pushing and dragging forces.

Social interactive robot navigation based on human intention analysis from face orientation and human path prediction

“…Zender et al [22] presents people following motion by considering socially acceptable distances from target human, and also provide social cues such as gaze or speech to indicate how the robot tries to maintain following motion. Recently, Garrell et al [23] proposed multiple robots navigation model that cooperatively guiding group of people in urban area. The prediction and anticipation model is used to predicts the position of a group of human as well as the robot behavior to control people to remain as a group.…”

Continuous real time POMCP to find-and-follow people by a humanoid service robot

“…Robust and reliable systems for navigation [6], obstacle avoidance [7], and localization [8] have been successfully integrated into several kinds of robotic platforms [9]. A number of methods have been developed to allow robots to navigate safely around people in specific, typically nongeneralizable tasks [10].…”

“…When executing the find-and-follow task using the CR-POMCP method, our real robot Dabo [9] moved too slowly, not being able to follow the person in real-time. This was caused by the slightly deviating discrete actions due to the random Monte-Carlo simulations; for example first an action north, and then the action northeast.…”

“…To evaluate the methods, more than one week of experiments were done with our mobile robot Dabo [9] in the two environments shown in Fig. 4.…”

Social-aware robot navigation in urban environments

“…As stated before, we aim to obtain a social robot model capable of dealing with navigation issues in a more human-oriented manner. Consequently, we make use of a variation of the classical definition of work applied to socialforces, similarly to the social work proposed in [25]. The amount of social work corresponding to a time step ∆t at time t:…”