Conference Paper

How to approach humans?: strategies for social robots to initiate interaction.

DOI: 10.1145/1514095.1514117 Conference: Proceedings of the 4th ACM/IEEE International Conference on Human Robot Interaction, HRI 2009, La Jolla, California, USA, March 9-13, 2009
Source: DBLP

ABSTRACT ABSTRACT This paper proposes a model,of approach,behavior with which a robot can initiate conversation with people who,are walking. We developed,the model by learning,from the failures in a simplistic approach,behavior ,used in a ,real shopping ,mall. Sometimes people were unaware of the robot’s presence, even when it spoke tothem. Sometimes, people were not sure whether the robot was really trying to start a conversation, and they did not start talking with it even ,though ,they displayed interest. To prevent ,such failures, our model includes the following functions: predicting the walking behavior of people, choosing a target person, planning its approaching path, and nonverbally indicating its intention to initiate ,a conversation. ,The approach ,model ,was implemented,and ,used in a ,real shopping ,mall. The field trial demonstrated,that our model ,significantly improves ,the robot’s performance,in initiating conversations. Categories and Subject Descriptors H.5.2 [Information Interfaces and Presentation]: User Interfaces-Interaction styles General Terms

  • [Show abstract] [Hide abstract]
    ABSTRACT: Walking side by side is a common situation when we go from one place to another with another person while talking. Our previous study reported a basic mechanism for side-by-side walking, but in the previous model it was crucial that each agent knew where he or she was going, i.e. the route to the destination. However, we have recognized the need to model the situation where one of the agents does not know the destination. The extended model presented in this work has two states: leader-follower state and collaborative state. Depending on whether the follower agent has obtained a reliable estimate of the route to follow, the walking agents transition between the two states. The model is calibrated with trajectories acquired from pairs of people walking side by side, and then it is tested in a human-robot interaction scenario. The results demonstrate that the new extended model achieves better side-by-side performance than a standard method without knowledge of the subgoal.
    Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction; 03/2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper formulates a generic framework for the social path planning problem. Previous works deal with very specific cases of socially-aware motion planning. Instead, here we propose a mathematical formulation that can be considered the preliminary steps towards a general theoretical setting, incorporating previous work as sub-cases. Social path planning is analyzed into 6 different subproblems. Furthermore, a review of the state of the art about the different aspects of the social path planning problem is included. Most importantly, an extended model for the O-space for groups of people engaged in a social interaction is proposed. Preliminary results for actual social path planning solutions under the proposed formulation are shown, proving the powerfulness of the approach and its generalization. Finally, a concrete discussion about future work is provided.
    Cognitive Robotics Systems: Replicating Human Actions and Activities, Workshop of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'13), Tokyo, Japan; 11/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Traditional path planning for robots is a well studied problem. However, the classical setting of the problem is simple to state: plan a path for a robot, starting from an initial point, and ending at a desired target point, given an environmental map, usually in the form of an occupancy grid. In this setting though, no special consideration is given to humans; they are thought of simply, as being obstacles in the environment, equivalent to chairs or walls. However, with more robots entering human spaces, special consideration needs to be given: humans need special treatment as obstacles, and furthermore humans can also serve the goal of goal points, towards starting a social interaction; either individual humans or groups of humans. Also, special mechanisms are required for engaging and disengaging in such interactions, taking into account psychological considerations of proxemics. In this paper, we first introduce our unifying theoretical framework for all the subproblems of social path planning; then, we propose an extended mode for engaging groups of people; and then, by using a special version of the fast-marching square planning method, we present and demonstrate actual algorithmic solutions for the social path planning subproblems. Our results prove the strengths of our approach and its generalizability. Finally, concrete further steps are discussed.
    IEEE International Conference on Robotics and Automation (ICRA 2014); 06/2014

Full-text (2 Sources)

Available from
Jun 6, 2014