Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Agent Autonomy to Casual Collaboration: A Design Investigation on Help-Seeking Urban Robots

Xinyan Yu, Marius Hoggenmueller, Martin Tomitsch

TL;DR

The paper addresses how urban intelligent agents can solicit help from bystanders when they encounter operational challenges in public spaces. It adopts a design-through-body exploration using four bodystorming focus groups (n=17) where participants role-play as robots and pedestrians to elicit nonverbal help-seeking strategies and understand bystander responses. Key findings show that addressing bystanders, cueing intentions, displaying emotions, and recognizable repetitive patterns facilitate help, while bystander decisions hinge on autonomy expectations, responsibility, unfamiliarity with robotics, and intrinsic/extrinsic motivations. The authors propose design considerations—emphasizing expressiveness, alignment with agent social categories, and practical incentives—to foster casual, mutually beneficial human-agent collaboration in uncontrolled environments. This work informs urban robot design and offers a pathway for validating bystander-driven assistive strategies in real-world deployments.

Abstract

As intelligent agents transition from controlled to uncontrolled environments, they face challenges that sometimes exceed their operational capabilities. In many scenarios, they rely on assistance from bystanders to overcome those challenges. Using robots that get stuck in urban settings as an example, we investigate how agents can prompt bystanders into providing assistance. We conducted four focus group sessions with 17 participants that involved bodystorming, where participants assumed the role of robots and bystander pedestrians in role-playing activities. Generating insights from both assumed robot and bystander perspectives, we were able to identify potential non-verbal help-seeking strategies (i.e., addressing bystanders, cueing intentions, and displaying emotions) and factors shaping the assistive behaviours of bystanders. Drawing on these findings, we offer design considerations for help-seeking urban robots and other agents operating in uncontrolled environments to foster casual collaboration, encompass expressiveness, align with agent social categories, and curate appropriate incentives.

From Agent Autonomy to Casual Collaboration: A Design Investigation on Help-Seeking Urban Robots

TL;DR

The paper addresses how urban intelligent agents can solicit help from bystanders when they encounter operational challenges in public spaces. It adopts a design-through-body exploration using four bodystorming focus groups (n=17) where participants role-play as robots and pedestrians to elicit nonverbal help-seeking strategies and understand bystander responses. Key findings show that addressing bystanders, cueing intentions, displaying emotions, and recognizable repetitive patterns facilitate help, while bystander decisions hinge on autonomy expectations, responsibility, unfamiliarity with robotics, and intrinsic/extrinsic motivations. The authors propose design considerations—emphasizing expressiveness, alignment with agent social categories, and practical incentives—to foster casual, mutually beneficial human-agent collaboration in uncontrolled environments. This work informs urban robot design and offers a pathway for validating bystander-driven assistive strategies in real-world deployments.

Abstract

As intelligent agents transition from controlled to uncontrolled environments, they face challenges that sometimes exceed their operational capabilities. In many scenarios, they rely on assistance from bystanders to overcome those challenges. Using robots that get stuck in urban settings as an example, we investigate how agents can prompt bystanders into providing assistance. We conducted four focus group sessions with 17 participants that involved bodystorming, where participants assumed the role of robots and bystander pedestrians in role-playing activities. Generating insights from both assumed robot and bystander perspectives, we were able to identify potential non-verbal help-seeking strategies (i.e., addressing bystanders, cueing intentions, and displaying emotions) and factors shaping the assistive behaviours of bystanders. Drawing on these findings, we offer design considerations for help-seeking urban robots and other agents operating in uncontrolled environments to foster casual collaboration, encompass expressiveness, align with agent social categories, and curate appropriate incentives.
Paper Structure (37 sections, 5 figures, 1 table)

This paper contains 37 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Human-agent collaboration
  4. Robot help-seeking strategies
  5. Service robots in urban spaces
  6. Summary
  7. Methodology
  8. Bodystorming scenarios
  9. Scenario set-ups and robot costume
  10. Participants
  11. Study procedure
  12. Warm-up activity
  13. Mystery-solving style role-play bodystorming
  14. Post-activity reflection
  15. Data collection and analysis
  16. ...and 22 more sections

Figures (5)

  • Figure 1: Study setup overview: A detailed view of the robot costume (left) juxtaposed with the Starship delivery robot; Site setting (middle); Screenshot of session recording (right).
  • Figure 2: The overview of study procedure
  • Figure 3: Screenshots from the bodystorming session capturing interactions between robot and pedestrian players: Robot player P9 tilts his box costume towards P11, making contact (left); Pedestrian player P1 gestures towards the button, seeking robot player P4's confirmation (middle); Pedestrian player P17 waves in response to robot player P15's spinning motion (right).
  • Figure 4: Communication between robot and pedestrian players: P8 inquires about robot player P6's needs, while P6 responds by pointing with the pole (left); Robot player P14 adopts a 'bow' gesture towards the pedestrian player, eliciting a corresponding bow in return (right).
  • Figure 5: Digital transcription of the word sorting results