TY - CONF ID - mergarsal_APPIS_2019_appro T1 - Socially Acceptable Approach to Humans by a Mobile Robot A1 - Garcia-Salguero, Mercedes A1 - Monroy, Javier A1 - Solano, Alejandro A1 - Gonzalez-Jimenez, Javier TI - International Conference on Applications of Intelligent Systems (APPIS) Y1 - 2019 CY - Las Palmas de Gran Canaria (Spain) M2 - doi: 10.1145/3309772.3309793 KW - Computer Vision KW - Human Pose Estimation KW - Human-Robot Interaction KW - mobile robot KW - OpenPose KW - People Approach KW - People Detector KW - Proxemic KW - ROS N2 - In this paper we propose a solution to endow a mobile robot with the ability to approach humans in a safe and ocially acceptable way. Our proposal focuses on real world indoor environments where the usual presence of ultiple humans and obstacles notably rise the complexity of the approach action. We first deal with the problem of accurately estimating the 3D poses of all humans in the work space (positions and orientations), to then focus on the estimation of the most appropriate navigation goal from which the robot should start the interaction with the user. For the latter, we define a cost function that, accounting for multiple proxemic parameters and complying with the restrictions inherent of a robot navigating in a human environment, enables ascertaining an optimal solution. Different experiments are presented to demonstrate the feasibility of our proposal to work under real world conditions. M1 - img_url= M1 - rank_indexname= M1 - rank_pos_in_category= M1 - rank_num_in_category= M1 - rank_cat_name= M1 - impact_factor= ER -