Task HCAAM: Conversation analysis to measure and manage trust in virtual assistants
Last Published:  11/23/20 11:55:12 AM (Central)
Short Title: Conversation Trust Analysis
Responsible HRP Element: Human Factors and Behavioral Performance
Collaborating Org(s):
Funding Status: Active - Currently funded and in progress
Procurement Mechanism(s):
Solicited
Aims:

This task is part of the Human Capabilities Assessments for Autonomous Missions (HCAAM) Virtual NASA Specialized Center of Research (VNSCOR) deliverable. This task aims to create conversational measures and mechanisms that allow virtual agents to use an unobtrusive approach to determine if a user is over/under trusting and mitigate this miss calibration with corrective actions and indications within the conversation.

  • Aim 1: Develop real-time conversational indicators of trust.
    • TOCA aid (Total Organic Carbon Analyze)—As a prototypical virtual assistant
    • Develop conversational indicators of trust from the AMO TOCA study data
    • Develop and validate TOCA as a microworld testbed
  •  Aim 2: Assess robustness of real-time conversational indicators of trust under long duration mission stresses.
    • Data collected in a manner that mirrors the experiment from Aim 1 that used the TOCA microworld
  •  Aim 3: Develop and evaluate conversational affordances for managing trust. Similar to Aim 1, this evaluation will be a ground-based study using participants from University of Wisconsin-Madison and NASA JSC who will work with an intelligent virtual agent in the TOCA microworld.
    • Validation in the HERA environment
    • Develop principles and guidelines for trust measurement and calibration
Mappings
RiskRisk of Adverse Outcome Due to Inadequate Human Systems Integration Architecture
GapHSIA-101: We need to identify the Human Systems Integration (HSI) – relevant crew health and performance outcomes, measures, and metrics, needed to characterize and mitigate risk, for future exploration missions.
GapHSIA-201: We need to evaluate the demands of future exploration habitat/vehicle systems and mission scenarios (e.g. increased automation, multi-modal communication) on individuals and teams, and determine the risks these demands pose to crew health and performance.
GapHSIA-401: We need to determine how HSI can be applied in the vehicle/habitat and computer interface Design Phase to mitigate potential decrements in operationally-relevant performance (e.g. problem-solving, execution procedures), during increasingly earth-independent, future exploration missions (including in-mission and at landing).
GapHSIA-501: We need to determine how HSI will be used in the development of dynamic and adaptive mission procedures and processes, to mitigate individual and team performance decrements during increasingly earth-independent, future exploration missions (including in-mission and at landing).
GapHSIA-701: We need to determine how human-automation-robotic systems can be optimized for effective enhancement and monitoring of crew capabilities, health, and performance, during increasingly earth-independent, future exploration missions (including in-mission and at landing).
You are here!TaskHCAAM: Conversation analysis to measure and manage trust in virtual assistants