Investigating the Integration of Human-Like and Machine-Like Robot Behaviors in a Shared Elevator Scenario Danilo Gallo ∗ Prescillia Bioche ∗ NAVER LABS Europe Meylan, France stname.lastname@naverlabs.com Jutta Willamowski Tommaso Colombino ∗ Shreepriya Gonzalez-Jimenez NAVER LABS Europe Meylan, France frstname.lastname@naverlabs.com ∗ Herve Poirier Cecile Boulard NAVER LABS Europe Meylan, France frstname.lastname@naverlabs.com fr Figure 1: Cameras a, b, and c showing a participant sharing the waiting area and elevator in the Machine-Like waiting condition. ABSTRACT This paper examines the advantages and disadvantages of combin- ing Human-Like and Machine-Like behaviors for a robot taking a shared elevator with a bystander as part of an ofce delivery service scenario. We present fndings of an in-person wizard-of-oz experi- ment that builds on and implements behavior policies developed in a previous study. In this experiment, we found that the combination of Machine-Like and Human-Like behaviors was perceived as bet- ter than Human-Like behaviors alone. We discuss possible reasons and point to key capabilities that a socially competent robot should have to achieve better Human-Like behaviors in order to seamlessly negotiate a social encounter with bystanders in a shared elevator or similar scenario. We found that establishing and maintaining a shared transactional space is one of these key requirements. CCS CONCEPTS • Computer systems organization → Robotics;• Human-centered computing → User studies. KEYWORDS Social norms, User studies, Robot navigation ∗ These authors contributed equally to this paper. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for proft or commercial advantage and that copies bear this notice and the full citation on the frst page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specifc permission and/or a fee. Request permissions from permissions@acm.org. HRI ’23, March 13–16, 2023, Stockholm, Sweden © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM. ACM ISBN 978-1-4503-9964-7/23/03. . . $15.00 https://doi.org/10.1145/3568162.3576974 ACM Reference Format: Danilo Gallo, Prescillia Bioche, Jutta Willamowski, Tommaso Colombino, Shreepriya Gonzalez-Jimenez, Herve Poirier, and Cecile Boulard. 2023. In- vestigating the Integration of Human-Like and Machine-Like Robot Behav- iors in a Shared Elevator Scenario. In Proceedings of the 2023 ACM/IEEE International Conference on Human-Robot Interaction (HRI ’23), March 13– 16, 2023, Stockholm, Sweden. ACM, New York, NY, USA, 10 pages. https: //doi.org/10.1145/3568162.3576974 1 INTRODUCTION Robots are increasingly present in everyday spaces, such as homes, ofces, hospitals, or streets. They are now capable of autonomously navigating and co-inhabiting with humans to provide services. Due to their mobility and interactivity, they are perceived as social enti- ties [8, 15]. No matter what their embodiment and real capabilities are, they are expected to comply to social norms, e.g. letting people exit an elevator before entering [23]. Studies show that the social attributes displayed by a robot infuence the willingness to interact with it [28]. However, the usage of robots in a social context is still at its beginnings [28, 36]. Even the design of seemingly simple social activities such as moving in shared spaces is a topic under research. Yet, understanding the impact of this social component is crucial in human-aware navigation, considering the impact of social constraints on the perception of the interaction [23]. Furthermore, while many studies have focused on direct inter- action, less attention has been devoted to studying the interaction with bystanders [27]. Still, this is relevant as it is possible to con- sider the fact of being distracted by a robot passing-by as an implicit interaction [23]. Interacting with people could be a secondary task for a robot sharing space with humans but its behavior could have a great impact on people’s attitude and perception toward the robot [36]. This implies the need to consider bystanders as more than 192