Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Developing Situational Awareness for Joint Action with Autonomous Vehicles

Robert Kaufman, David Kirsh, Nadir Weibel

TL;DR

The paper tackles the problem of insufficient rider informational support in human-AV interactions, which hinders AV adoption. It introduces a systems-level framework that unifies joint-action theory and situational awareness to tailor real-time communications based on four factors: AV traits, action goals, subject-specific traits and states, and driving context. Key contributions include formalizing the notions of individual, shared, and distributed SA within a joint-action framework, detailing how communication strategies and XAI can satisfy goal-specific SA criteria, and outlining a practical design approach and research agenda. The framework aims to enable context-aware, bi-directional human-AV interactions that improve safety, trust, and learning, with potential applicability to other human-AI domains.

Abstract

Unanswered questions about how human-AV interaction designers can support rider's informational needs hinders Autonomous Vehicles (AV) adoption. To achieve joint human-AV action goals - such as safe transportation, trust, or learning from an AV - sufficient situational awareness must be held by the human, AV, and human-AV system collectively. We present a systems-level framework that integrates cognitive theories of joint action and situational awareness as a means to tailor communications that meet the criteria necessary for goal success. This framework is based on four components of the shared situation: AV traits, action goals, subject-specific traits and states, and the situated driving context. AV communications should be tailored to these factors and be sensitive when they change. This framework can be useful for understanding individual, shared, and distributed human-AV situational awareness and designing for future AV communications that meet the informational needs and goals of diverse groups and in diverse driving contexts.

Developing Situational Awareness for Joint Action with Autonomous Vehicles

TL;DR

The paper tackles the problem of insufficient rider informational support in human-AV interactions, which hinders AV adoption. It introduces a systems-level framework that unifies joint-action theory and situational awareness to tailor real-time communications based on four factors: AV traits, action goals, subject-specific traits and states, and driving context. Key contributions include formalizing the notions of individual, shared, and distributed SA within a joint-action framework, detailing how communication strategies and XAI can satisfy goal-specific SA criteria, and outlining a practical design approach and research agenda. The framework aims to enable context-aware, bi-directional human-AV interactions that improve safety, trust, and learning, with potential applicability to other human-AI domains.

Abstract

Unanswered questions about how human-AV interaction designers can support rider's informational needs hinders Autonomous Vehicles (AV) adoption. To achieve joint human-AV action goals - such as safe transportation, trust, or learning from an AV - sufficient situational awareness must be held by the human, AV, and human-AV system collectively. We present a systems-level framework that integrates cognitive theories of joint action and situational awareness as a means to tailor communications that meet the criteria necessary for goal success. This framework is based on four components of the shared situation: AV traits, action goals, subject-specific traits and states, and the situated driving context. AV communications should be tailored to these factors and be sensitive when they change. This framework can be useful for understanding individual, shared, and distributed human-AV situational awareness and designing for future AV communications that meet the informational needs and goals of diverse groups and in diverse driving contexts.
Paper Structure (9 sections, 2 figures)

This paper contains 9 sections, 2 figures.

Table of Contents

  1. Introduction
  2. Illustrative Example
  3. Framework for situated joint action within a human-AV system
  4. Discussion
  5. Human-AI teaming for Action Goal Success
  6. Developing Situational Awareness
  7. Wider System Factors Impacting Success Criteria and Communication Needs
  8. Applying the Framework
  9. Conclusion: Framework and System Summary

Figures (2)

  • Figure 1: Framework overview for situated joint action based on situational awareness within a human-AV system. Joint Action Goals and AV Traits are discussed in Section \ref{['goal']}, AV traits and the development of situational awareness through strategic communicative actions are discussed in Section \ref{['developing']}, and the driving context and human traits and states are discussed in Section \ref{['wider']}.
  • Figure 2: Example Success function for the goal of Safe Transportation. The success function for the goal of safe transportation is composed of sub-goals which need to be met for the overall goal to be achieved. Each of these subgoals have their own conditions, which themselves may have conditions, etc. Joint communicative action may be required between a human and an AV to achieve some goals or subgoals. This example is very simplified and for illustrative purposes only.