Actual Achieved Gain and Optimal Perceived Gain: Modeling Human Take-over Decisions Towards Automated Vehicles' Suggestions

• DOI: 10.48550/arxiv.2502.06179
• Publication Date: 2025-02-10
• Authors: Shuning Zhang; Yi Xin; Shixuan Li; Chuye Hong; Gujun Chen; Jiarui Liu; Xueyang Wang; Yongquan Hu; Yuntao Wang; Hewu Li
• Keywords: FOS: Computer and information sciences; Computer Science - Human-Computer Interaction; Human-Computer Interaction (cs.HC)

Driver decision quality in take-overs is critical for effective human-Autonomous Driving System (ADS) collaboration. However, current research lacks detailed analysis of its variations. This paper introduces two metrics--Actual Achieved Gain (AAG) and Optimal Perceived (OPG)--to assess quality, with OPG representing optimal decisions AAG reflecting actual outcomes. Both are calculated as weighted averages perceived gains losses, influenced by ADS accuracy. Study 1 (N=315) used a 21-point Thurstone scale to measure losses-key components OPG-across typical tasks: route selection, overtaking, collision avoidance. Studies 2 (N=54) 3 modeled under varying accuracy time. Results show sufficient time (>3.5s), converges towards OPG, indicating rational decision-making, while limited leads intuitive deterministic choices. also linked AAG-OPG deviations irrational behaviors. An intervention study (N=8) pilot (N=4) employing voice alarms multi-modal based on these demonstrated AAG's potential improve quality.