Technology Category
Humans and AI: Human-Aware Planning and Behavior PredictionComputer Vision: Learning & Optimization for CVSearch and Optimization: Sampling/Simulation-based Search
OptiCarVis: Improving Automated Vehicle Functionality Visualizations Using Bayesian Optimization to Enhance User Experience
🤖 AI Summary
Designing visualization feedback for autonomous vehicles (AVs) remains challenging due to the difficulty of simultaneously optimizing user comprehension, trust, perceived safety, and cognitive load. Method: This paper proposes a human–machine collaborative optimization framework that dynamically generates personalized visualizations for detection, prediction, and planning—tailored to individual user needs. It introduces a Warm-Start multi-objective Bayesian optimization (MOBO)-driven “human-in-the-loop” (HITL) paradigm, overcoming limitations of static, one-size-fits-all interfaces. The approach employs dual-path design space modeling (integrating expert knowledge and user input), online experiments (N=117), and multidimensional evaluation. Contribution/Results: Results demonstrate statistically significant improvements in user trust, acceptance, perceived safety, and predictability (p<0.01), without increasing cognitive load. The framework enables efficient exploration of high-dimensional visualization design spaces, yielding personalized, interpretable, and scalable in-vehicle visualization solutions.
Technology Category
Application Category
📝 Abstract
Automated vehicle (AV) acceptance relies on their understanding via feedback. While visualizations aim to enhance user understanding of AV's detection, prediction, and planning functionalities, establishing an optimal design is challenging. Traditional"one-size-fits-all"designs might be unsuitable, stemming from resource-intensive empirical evaluations. This paper introduces OptiCarVis, a set of Human-in-the-Loop (HITL) approaches using Multi-Objective Bayesian Optimization (MOBO) to optimize AV feedback visualizations. We compare conditions using eight expert and user-customized designs for a Warm-Start HITL MOBO. An online study (N=117) demonstrates OptiCarVis's efficacy in significantly improving trust, acceptance, perceived safety, and predictability without increasing cognitive load. OptiCarVis facilitates a comprehensive design space exploration, enhancing in-vehicle interfaces for optimal passenger experiences and broader applicability.
Problem
Research questions and friction points this paper is trying to address.
Autonomous Vehicles
Visual Feedback Optimization
User Trust and Acceptance
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-objective Bayesian Optimization
Autonomous Vehicles Visualization
User Trust and Safety Perceptions
🔎 Similar Papers
No similar papers found.
