Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Preliminary Prototyping of Avoidance Behaviors Triggered by a User's Physical Approach to a Robot

Tomoko Yonezawa, Hirotake Yamazoe, Atsuo Fujino, Daigo Suhara, Takaya Tamamoto, Yuto Nishiguchi

TL;DR

The paper addresses how a robot can reject or avoid when approached by a person, by modeling an internal dislike state that accumulates with proximity as $n_t = a \cdot e^{b \cdot d_t}$ and decays/ accumulates into $s_t$ with $s_t = n_t + s_{t-1} \cdot c$. The approach defines a pair of thresholds $e_{th}$ and $e_{max}$ to govern endurance and a one-shot avoidance after limit-exceeding, with Dominance and relationship shaping behavior patterns. The implementation runs on an arm robot with a distance sensor, translating the internal state into motion patterns that vary in intensity and type. The work highlights a pipeline linking interior affective states to observable actions, discusses ethical/regulatory considerations, and identifies avenues for model validation and parameter fitting.

Abstract

Human-robot interaction frequently involves physical proximity or contact. In human-human settings, people flexibly accept, reject, or tolerate such approaches depending on the relationship and context. We explore the design of a robot's rejective internal state and corresponding avoidance behaviors, such as withdrawing or pushing away, when a person approaches. We model the accumulation and decay of discomfort as a function of interpersonal distance, and implement tolerance (endurance) and limit-exceeding avoidance driven by the Dominance axis of the PAD affect model. The behaviors and their intensities are realized on an arm robot. Results illustrate a coherent pipeline from internal state parameters to graded endurance motions and, once a limit is crossed, to avoidance actions.

Preliminary Prototyping of Avoidance Behaviors Triggered by a User's Physical Approach to a Robot

TL;DR

The paper addresses how a robot can reject or avoid when approached by a person, by modeling an internal dislike state that accumulates with proximity as and decays/ accumulates into with . The approach defines a pair of thresholds and to govern endurance and a one-shot avoidance after limit-exceeding, with Dominance and relationship shaping behavior patterns. The implementation runs on an arm robot with a distance sensor, translating the internal state into motion patterns that vary in intensity and type. The work highlights a pipeline linking interior affective states to observable actions, discusses ethical/regulatory considerations, and identifies avenues for model validation and parameter fitting.

Abstract

Human-robot interaction frequently involves physical proximity or contact. In human-human settings, people flexibly accept, reject, or tolerate such approaches depending on the relationship and context. We explore the design of a robot's rejective internal state and corresponding avoidance behaviors, such as withdrawing or pushing away, when a person approaches. We model the accumulation and decay of discomfort as a function of interpersonal distance, and implement tolerance (endurance) and limit-exceeding avoidance driven by the Dominance axis of the PAD affect model. The behaviors and their intensities are realized on an arm robot. Results illustrate a coherent pipeline from internal state parameters to graded endurance motions and, once a limit is crossed, to avoidance actions.

Paper Structure

This paper contains 14 sections, 2 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. System Design
  3. Internal State and Parameters
  4. Tolerance and Avoidance Logic
  5. Dominance- and Relationship-Dependent Patterns
  6. Internal Parameter Design
  7. Computing dislike at time $t$
  8. Decay and accumulation of dislike up to time $t$
  9. Thresholds for the intensity and timing of endurance/avoidance
  10. Robot Motion Generation
  11. Example Performance Flow
  12. Future Work
  13. Ethics and Regulation
  14. Conclusion

Figures (4)

  • Figure 1: Dislikeness model correspoinding to distance
  • Figure 2: Time-series model of dislike accumulation during endurance and the subsequent explosion. In this graph, the horizontal $t$-axis uses the current time as 0. As time passes, the plotted data flows rightward.
  • Figure 3: Avoidance motion set
  • Figure 4: Hardware structure. Ultrasonic distance sensor (bottom right) connected to the myCobot via an Arduino. The myCobot is covered with a stocking/stretch fabric to prevent a robot-like appearance.