Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Model of Spatial Human-Agent Interaction with Consideration for Others

Takafumi Sakamoto, Yugo Takeuchi

TL;DR

This work tackles the challenge of enabling communication robots to initiate conversations in public spaces without disturbing pedestrians. It introduces a computational spatial interaction model in which social consideration is quantified by a single parameter $\psi$ that governs how a robot adjusts its internal state toward a human’s inferred state, with estimation via observed behavior and state updates via a function $g$. Through VR experiments, the study shows that low $\psi$ can inhibit human movement toward a target, while higher $\psi$ mitigates interference, and that robots following the model can still engage when appropriate. The findings demonstrate the model’s potential to guide sociable robot navigation by balancing engagement and non-disturbance, with practical implications for robot roles and context-aware parameter tuning.

Abstract

Communication robots often need to initiate conversations with people in public spaces. At the same time, such robots must not disturb pedestrians. To handle these two requirements, an agent needs to estimate the communication desires of others based on their behavior and then adjust its own communication activities accordingly. In this study, we construct a computational spatial interaction model that considers others. Consideration is expressed as a quantitative parameter: the amount of adjustment of one's internal state to the estimated internal state of the other. To validate the model, we experimented with a human and a virtual robot interacting in a VR environment. The results show that when the participant moves to the target, a virtual robot with a low consideration value inhibits the participant's movement, while a robot with a higher consideration value did not inhibit the participant's movement. When the participant approached the robot, the robot also exhibited approaching behavior, regardless of the consideration value, thus decreasing the participant's movement. These results appear to verify the proposed model's ability to clarify interactions with consideration for others.

Model of Spatial Human-Agent Interaction with Consideration for Others

TL;DR

This work tackles the challenge of enabling communication robots to initiate conversations in public spaces without disturbing pedestrians. It introduces a computational spatial interaction model in which social consideration is quantified by a single parameter that governs how a robot adjusts its internal state toward a human’s inferred state, with estimation via observed behavior and state updates via a function . Through VR experiments, the study shows that low can inhibit human movement toward a target, while higher mitigates interference, and that robots following the model can still engage when appropriate. The findings demonstrate the model’s potential to guide sociable robot navigation by balancing engagement and non-disturbance, with practical implications for robot roles and context-aware parameter tuning.

Abstract

Communication robots often need to initiate conversations with people in public spaces. At the same time, such robots must not disturb pedestrians. To handle these two requirements, an agent needs to estimate the communication desires of others based on their behavior and then adjust its own communication activities accordingly. In this study, we construct a computational spatial interaction model that considers others. Consideration is expressed as a quantitative parameter: the amount of adjustment of one's internal state to the estimated internal state of the other. To validate the model, we experimented with a human and a virtual robot interacting in a VR environment. The results show that when the participant moves to the target, a virtual robot with a low consideration value inhibits the participant's movement, while a robot with a higher consideration value did not inhibit the participant's movement. When the participant approached the robot, the robot also exhibited approaching behavior, regardless of the consideration value, thus decreasing the participant's movement. These results appear to verify the proposed model's ability to clarify interactions with consideration for others.
Paper Structure (18 sections, 8 equations, 13 figures)

This paper contains 18 sections, 8 equations, 13 figures.

Table of Contents

  1. Introduction
  2. Model of interaction with social consideration for others
  3. Internal Condition and Behavior Generation
  4. Estimation Function of Internal Condition
  5. Function Representing the Change in Internal Condition
  6. Parameters for Consideration of Others
  7. Interaction Experiments in VR Environment
  8. Experiment Environment
  9. Procedure
  10. Experimental Conditions
  11. Working Hypotheses
  12. Measurement and Analysis
  13. Results and Discussion
  14. Interaction when a pole was the target
  15. Interaction when an object held by the robot was the target
  16. ...and 3 more sections

Figures (13)

  • Figure 1: Functions and variables required to describe interactions with consideration for others
  • Figure 2: Examples of approach and avoidance actions generated according to internal state values sakamoto2018simulation
  • Figure 3: Experiment environment
  • Figure 4: Experimental tasks
  • Figure 5: Simulated trajectories when participants reject the robot in each condition
  • ...and 8 more figures