Outcomes
We in contrast Wise Agent to a standard, voice-controlled AR assistant baseline. We measured cognitive load utilizing the NASA Job Load Index (NASA-TLX), total usability with the System Usability Scale (SUS), person choice on a 7-point Likert scale, and complete interplay time.
Essentially the most important discovering was the discount in cognitive workload. The NASA-TLX information confirmed that on a 100-point scale for psychological demand, the typical rating for Wise Agent was 21.1, in comparison with 65.0 for the baseline with a statistically important distinction (𝑝 𝑝 = .0039), which means that the proactive system efficiently offloaded the psychological work of forming a question.
Relating to usability, each techniques carried out effectively, with no statistically important distinction between their SUS scores (𝑝 = .11). Nevertheless, individuals expressed a robust and statistically important choice for Wise Agent (𝑝 = .0074). On a 7-point scale, the typical choice ranking was 6.0 for Wise Agent, in comparison with 3.8 for the baseline.
For the interplay time, logged from the second a immediate was triggered to the ultimate system response to the person’s enter, the baseline was sooner (μ = 16.4s) in comparison with Wise Agent (μ = 28.5s). This distinction is an anticipated trade-off of the system’s two-step interplay stream, the place the agent first proposes an motion and the person then confirms it. The robust person choice for Wise Agent suggests this trade-off was acceptable, significantly in social contexts the place discretion and minimal person effort have been vital.
