Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

David Bethge, Daniel Bulanda, Adam Kozlowski, Thomas Kosch, Albrecht Schmidt, Tobias Grosse-Puppendahl

TL;DR

HappyRouting tackles emotion-aware navigation by predicting continuous happiness weights on road segments using static and dynamic contextual features, and optimizing routes to maximize positive emotions while balancing travel time. The approach combines an ML-based emotion map layer with a contraction-hierarchies routing backend implemented in GraphHopper and deployed on a smartphone app; evaluated in a real-world driving study (N=13) and a city-scale simulation. Key findings show that happy routes increase perceived valence by 11% (p=.007) though they are ~1.25x longer on average; participants accepted longer detours for emotional benefits. The work demonstrates feasibility of scalable emotion-driven routing and discusses ethical, societal, and environmental considerations, offering a path to broader adoption in mobility apps and other transport modalities.

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.

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

TL;DR

HappyRouting tackles emotion-aware navigation by predicting continuous happiness weights on road segments using static and dynamic contextual features, and optimizing routes to maximize positive emotions while balancing travel time. The approach combines an ML-based emotion map layer with a contraction-hierarchies routing backend implemented in GraphHopper and deployed on a smartphone app; evaluated in a real-world driving study (N=13) and a city-scale simulation. Key findings show that happy routes increase perceived valence by 11% (p=.007) though they are ~1.25x longer on average; participants accepted longer detours for emotional benefits. The work demonstrates feasibility of scalable emotion-driven routing and discusses ethical, societal, and environmental considerations, offering a path to broader adoption in mobility apps and other transport modalities.

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.
Paper Structure (42 sections, 3 equations, 11 figures, 4 tables)

This paper contains 42 sections, 3 equations, 11 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Inferring Driver Emotions
  4. Affective Routing
  5. Summary
  6. Design Considerations
  7. User Emotions, Mood & Wellbeing
  8. Routing Concepts
  9. Optimization Objectives
  10. Modeling and Simulation
  11. Architecture
  12. [id=R3]RequirementsProblem Statement
  13. General Framework
  14. Input Features
  15. Emotion Prediction
  16. ...and 27 more sections

Figures (11)

  • Figure 1: Architecture of happy navigation computation.
  • Figure 2: Graph Building for Happy Route Optimization. The navigation finds the optimal emotional path according to the emotion-road-weight regularization (\ref{['eq:routing_opt']}). The bottom layer is a satellite image. The layer above represents the routable roads. Above is an emotion heatmap based on interpolation of the computed happiness points. The red path is the fastest path offered by navigation, while the blue path is the happy path.
  • Figure 3: GraphHopper web-server for Happy Route Optimization in a 2D-layout.
  • Figure 4: Implemented navigation app that supports normal and happy routing. The app is placed on the windshield and has the same functionality as normal navigation apps (turn-by-turn navigation, voice output for hinting next directions).
  • Figure 5: Experimental design of the emotional navigation driving study. The endpoint of the second drive was set to be the start point of the first drive.
  • ...and 6 more figures