TP4.4: Collaborative and Social Mobility Services

Subproject manager
Prof. Dr. Johann Schlichter
Subproject manager
Dr. Wolfgang Wörndl

Innovative mobility services are essential when facing the challenges of future mobility. They are supposed to make transportation within and between cities more sustainable and help cities turn into smart cities. Such mobility services are not limited to private transport only. They can promote public transport and facilitate the planning of inter-modal transportation which combines different kinds of means of transportation within one trip. Furthermore, pedestrians represent another target group of mobility services. One example are tourists who receive recommendations for points of interest like restaurants, museums or monuments while exploring a city.

Figure 1: Waze Android Application [2]
Use cases for innovative mobility services are a big topic in research but also various real working applications are already available on the market. Waze (Figure 1) is an application that improves navigation by adapting to current warnings shared by the community. User can notify others about accidents, threats or cheap gas stations and are incentivized by a gamification method awarding them with points. New taxi services like Uber, which already became “the world’s largest taxi company” [1] without owning a single vehicle, change traditional mobility behaviors and shape the future of shared mobility. Other examples of such innovations are various car- and bikesharing services like DriveNow or Call-a-bike in Munich which allow urban dwellers to share vehicles with others. Carpooling applications like Blablacar increase the number of passengers per car which remains to be low and is one of the main reasons for congestion and pollution. Tourists and local pedestrians use applications like Yelp (Figure 2), TripAdvisor and Foursquare to be supported by other users while navigating through a city.

Some of these innovative services enhance their functionalities by providing personalized recommendations to the users. Such recommender systems filter large amounts of data to present services or products to users which best satisfy their needs. Due to the widespread usage of mobile devices likes smartphones, recommender systems are more and more accessed in mobile environments. Recommendations can be improved when taking context into account like the user’s current location to recommend, for example, interesting spots nearby. Furthermore, recommender systems can incorporate social or collaborative aspects like the opinions of friends or people with similar preferences to generate personalized recommendations. Recommender systems enrich innovative mobility services. They support road users, passengers and pedestrians in various scenarios, for example, when recommending points of interest, inter-modal routes or interesting events.

Figure 2: Yelp iOS App [3]

The main goal of this subproject is to develop and evaluate new ideas for intelligent and innovative mobility services providing personalized information adapted to the user’s current needs. For this, we start with a research phase where we search for related work and relevant, existing applications. Based on our findings we will suggest ideas for mobility services which we will evaluate based on several criteria. We will implement the most promising ideas as prototypes and eventually integrate a real working version of one prototype into the TUM LLCM platform.

Our chair already puts some effort in the development of innovative mobility service. One example of a recommender system in the field of connected mobility is the City Trip Planner in Figure 3. Based on the user’s preferences, this service recommends points of interest and combines them in a reasonable itinerary. It does not only support tourists exploring a city, furthermore traffic flow can be optimized.

This service could be improved by considering the current context (e.g., recommending outdoor events only when the sun is shining), taking friends’ opinions into account and offering optimized user interfaces for mobile devices. Other current work focuses on the recommendation of local events, the facilitation of parking spot search or personalized news recommendations in a mobile context. Furthermore, we are interested in intelligent user interfaces ensuring a high usability of our systems and reducing distraction when accessed while driving.

Figure 3:City Trip Planner [4]

In addition, the project team released a first mobility application TourRec:
TourRec is a personalized city route recommendation system that helps you explore new cities more easily!
To better tailor recommendations to your needs, you can tell TourRec which types of attractions you particularly like. As soon as you need a new route, indicate your starting point (for example, your current position), your destination (for example, your hotel), the start time, and the maximum duration of the route. TourRec will suggest a trip to explore the city. The recommendations also take into account external factors, e.g. the weather. So you can easily plan your next vacation or city trip and miss no highlights on your trip!
More information about the application are available here. To download the application please visit the Google Playstore.
Feedback is very welcome!

If you would like to get more information about this subproject, our work in general or if you are interested in a cooperation to develop innovative mobility services, please contact Dr. Wolfgang Wörndl or Daniel Herzog. Motivated students who are looking for a thesis or a guided research in one of the presented topics are always invited to contact use as well.

[1] Goodwin, T. (2015): The Battle Is For The Customer Interface. (zuletzt aufgerufen am 20. Januar 2016)
[4] Laß, C., Wörndl, W., Herzog, D. (2016): A Multi-Tier Web Service and Mobile Client for City Trip Recommendations. Proc. of the 8th EAI International Conference on Mobile Computing, Applications and Services (MobiCASE), Cambridge, Great Britain, Nov. 2016

Own Publications
[1] Dietz, Linus W.; Herzog, Daniel; Wörndl, Wolfgang: Deriving Tourist Mobility Patterns from Check-in Data. Proceedings of the WSDM 2018 Workshop on Learning from User Interactions, 2018
[2] Laß, Christopher; Herzog, Daniel; Wörndl, Wolfgang: Context-Aware Tourist Trip Recommendations. Proceedings of the 2nd Workshop on Recommenders in Tourism co-located with 11th ACM Conference on Recommender Systems (RecSys 2017), Como, Italy, August 27, 2017., 2017
[3] Herzog, Daniel; Wörndl, Wolfgang: Mobile and Context-Aware Event Recommender Systems. In: Lecture Notes in Business Information Processing. Springer International Publishing, 2017
[4] Laß, Christopher; Wörndl, Wolfgang; Herzog, Daniel: A Multi-Tier Web Service and Mobile Client for City Trip Recommendations. International Conference on Mobile Computing, Applications and Services (MobiCASE), 2016
[5] Herzog, Daniel; Wörndl, Wolfgang: Exploiting Item Dependencies to Improve Tourist Trip Recommendations. Proceedings of the Workshop on Recommenders in Tourism co-located with 10th ACM Conference on Recommender Systems (RecSys 2016), Boston, MA, USA, September 15, 2016., 2016
[6] Herzog, Daniel; Massoud, Hesham; Wörndl, Wolfgang: RouteMe. Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization – UMAP ’17, ACM Press, 2017
[7] Siddiqui, Sajjad Ali; Herzog, Daniel; Wörndl, Wolfgang: Real-Time Public Transport Navigation on Smartwatches. Adjunct Publication of the 25th [8] Conference on User Modeling, Adaptation and Personalization – UMAP ’17, ACM Press, 2017
[9] Wörndl, Wolfgang; Hefele, Alexander; Herzog, Daniel: Recommending a sequence of interesting places for tourist trips. Information Technology & Tourism 17 (1), 2017, 31-54
[10] Herzog, Daniel; Wörndl, Wolfgang: Collaborative and Social Mobility Services. Digital Mobility Platforms and Ecosystems, 2016
[11] Herzog, Daniel; Wörndl, Wolfgang: Extending Content-Boosted Collaborative Filtering for Context-aware, Mobile Event Recommendations. Proceedings of the 12th International Conference on Web Information Systems and Technologies, SCITEPRESS, 2016
Supervised student projects
[1] Florian Noack: Comparative Analysis of Real-Time Traffic Data for Integration in Urban Traffic Control Systems. Master Thesis, Technical University of Munich, 2018
[2] Simon Fakir: Computer Vision Approach to Derive User’s Preferences from Photos. Master Thesis, Technical University of Munich, 2017
[3] Hania Syed: An Evaluation of Technologies for Connecting Multiple Smartphones to Receive Tourist Trip Recommendations. Master Thesis, Technical University of Munich, 2017
[4] Robert Weindl: Meta Tour Generation for Trip Planning Applications based on a Recommender System utilizing Conversational, Deep Learning and Ontology Methodologies. Master Thesis, Technical University of Munich, 2017
[5] Julian Zurmühl: Next Location Prediction Based on Semantics of Personal Mobility Patterns. Master Thesis, Technical University of Munich, 2017 (in cooperation with BMW)