HappyRouting: Learning Emotion-Aware Route Trajectories for Scalable In-The-Wild Navigation

2024-01-28

arXiv.org

AI Summary

Current navigation systems prioritize efficiency—e.g., shortest or fastest routes—while neglecting drivers’ emotional well-being. This work introduces the “affect-aware navigation” paradigm, constructing the first emotion map layer that integrates static road attributes with dynamic traffic data. A deep learning model, trained on multi-source spatiotemporal contextual features, predicts in-vehicle valence trajectories to inform emotionally optimized route planning. Through real-world driving experiments and validated subjective assessments (e.g., SAM), our HappyRouting strategy increases average travel time by 25% but significantly improves self-reported pleasure by 11% (*p* = .007); notably, participants perceived trip duration as shorter, demonstrating emotion’s capacity to modulate temporal cognition. This study establishes a technically feasible framework and empirical foundation for transitioning navigation systems from efficiency-centric to affect-enhanced design.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Routes represent an integral part of triggering emotions in drivers. Navigation systems allow users to choose a navigation strategy, such as the fastest or shortest route. However, they do not consider the driver's emotional well-being. We present HappyRouting, a novel navigation-based empathic car interface guiding drivers through real-world traffic while evoking positive emotions. We propose design considerations, derive a technical architecture, and implement a routing optimization framework. Our contribution is a machine learning-based generated emotion map layer, predicting emotions along routes based on static and dynamic contextual data. We evaluated HappyRouting in a real-world driving study (N=13), finding that happy routes increase subjectively perceived valence by 11% (p=.007). Although happy routes take 1.25 times longer on average, participants perceived the happy route as shorter, presenting an emotion-enhanced alternative to today's fastest routing mechanisms. We discuss how emotion-based routing can be integrated into navigation apps, promoting emotional well-being for mobility use.

Problem

• Navigation systems ignore driver emotional well-being during route selection
• Lack of emotion-aware routing frameworks for real-world traffic navigation
• Current routing mechanisms prioritize speed over emotional experience enhancement

Innovation

• Machine learning-based emotion map layer
• Routing optimization framework for emotions
• Real-world emotion-aware navigation system