SAHRTA: A Supervisory-Based Adaptive Human-Robot Teaming Architecture

Abstract

Supervisory-based human-robot teams are deployed in various dynamic and extreme environments (e.g., space exploration). Achieving high task performance in such environments is critical, as a mistake may lead to significant monetary loss or human injury. Task performance may be augmented by adapting the supervisory interface's interactions or autonomy levels based on the human supervisor's workload level, as workload is related to task performance. Typical adaptive systems rely solely on the human's overall or cognitive workload state to select what adaptation strategy to implement; however, overall workload encompasses many dimensions (i.e., cognitive, physical, visual, auditory, and speech) called workload components. Selecting an appropriate adaptation strategy based on a complete human workload state (rather than a single workload dimension) may allow for more impactful adaptations that ensure high task performance. A Supervisory-Based Adaptive Human-Robot Teaming Architecture (SAHRTA) that selects an appropriate level of autonomy or system interaction based on a complete realtime multi-dimensional workload estimate and predicted future task performance is introduced. SAHRTA was shown to improve overall task performance in a physically expanded version of the NASA Multi-Attribute Task Battery.

Real-Time Speech Workload Estimation for Intelligent Human- Machine Systems

“…The speech workload algorithm was used to estimate workload in real-time during an adaptive human-machine system pilot evaluation (10 participants using the described foundational experimental design) (Heard, Fortune, and Adams, 2020) with a window size of 5s. There is no ground truth model to compare the speech-workload estimates against, due to the real-time and adaptive nature of the evaluation.…”

Model-Driven Requirements for Humans-on-the-Loop Multi-UAV Missions

“…The effectiveness of the HotL is highly dependent upon the human multi-agent interaction mechanisms built into the system as well as the flexibility of the autonomy models. To this end, several researchers have explored techniques for exposing the intent, actions, plans and associated rationales of an autonomous agent [34], while other researchers have explored ways to improve overall performance by dynamically adapting agents' autonomy levels based on the estimated cognitive workload of the human participants; however, they also observed that frequent changes in autonomy levels reduced situational awareness and forced operators to continually reevaluate the agents' behavior [35].…”