Community Research and Development Information Service - CORDIS

H2020

SOUTHPARK Report Summary

Project ID: 674119

Periodic Reporting for period 1 - SOUTHPARK (SOUTHPARK - SOcial and Universal Technology HelPing to detect ARrivals via sdK)

Reporting period: 2015-08-01 to 2016-07-31

Summary of the context and overall objectives of the project

ParkTAG has been set up as a company to address individual, as well as societal problems related to parking space search and road congestion by building a smart, integrated, technology-based, easy to use and cost-free system that renders the traffic more efficient thereby decreasing negative effects on humans and the environment while at the same time fulfilling today's need for fast and individualised urban mobility. The technology prototype is based upon an elaborated set of algorithms that match car drivers' predicted and actual behaviour in order to allocate nascent parking space.

The SOUTHPARK project is set up to fulfill two overall objectives:

First, it will localise the ParkTAG system to the contexts of three European cities of more than one million inhabitants. The aim of the project is to demonstrate that the technology functions in the operational environment. This will be achieved when ParkTAG reduces the time of the participating test users spent on parking in three cities by 50 %.

Second, the SOUTHPARK project will enhance the existing ParkTAG algorithms with a component that enables the technology to self-adopt to new local settings, thereby significantly reducing the implementation time and costs. This will enable the company to swiftly role out and commercialise the product on the world market. The ambition is to reduce both time and cost of localisation to new cities by 75% after the project.

The outcome of the project will be an ensemble of algorithms that had been tested on large scale in the operational environment of three European cities. These algorithms will have the capacity to self-adopt to the parking situation in new cities thereby significantly decreasing the time millions of car drivers cruise to park. The technology will thus become a crucial part of the value chain in many products of the motorised vehicle industry.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

Work package 1 - Project Management
All administrative tasks have been progressing well and all deliverables and milestones due during this reporting period were timely delivered. The project internal communication is excellent, with biweekly team meetings to monitor progress of tasks and to manage any issues that occur. WP1 organised a kick-off meeting in the beginning of the SOUTHPARK project to ensure that all involved persons were well informed about the projects objectives and its upcoming tasks. Besides, the coaching sessions provided by the EASME were prepared. A suitable coach has been found who is in contracting phase by the end of the first reporting period.

Work package 2 - Localisation and scale-up studies
To localise the ParkTAG system to the three selected testing cities Barcelona, Milan and Stockholm, WP2 researched the parking situation and legal particularities of these sites, adapted all aspects of the technology to the respective languages and worked on the recruitment of test users. This task proved to be a major challenge for the project. The ParkTAG sales team undertook great efforts to reach out to public and private partnerships in the respective cities to provide a data base that would be satisfying for consumers, but these efforts were little successful due to unforeseen commercial hurdles and the lack of support from local governments. Still, the testing of the current prototype is about to start.

Work package 3 - Machine learning
All data gathered by the ParkTAG technology provide the basis for the building, training and testing of the algorithms. In WP 3, data scientist and machine learning experts work on the collection and evaluation of the various data sets, the extraction of possible features for the technology and the training and implementation of the algorithms. A Data Management Plan was created and a demonstrator app of the Start/Stop detection has been developed. As in WP 2, a lot of obstacles had to be faces like changes in the operating systems iOS and Android or the difficulty to gather ground truth data in the needed amount. Nevertheless, it has proven that the start/stop detection is functioning in principal and of great value for many different use cases. The transport mode detection is currently in a prototype phase and is also demanded by several of ParkTAG’s customers and partners.

Work package 4 - Dissemination
SOUTHPARK focused in the first project year on participating on events and applying (successfully) for awards. Following a timeline that considers the best experience for B2C users, ParkTAG decided to postpone most social media activities and public relations campaigns towards consumers until autumn 2016. The corresponding ground work has been accomplished, like the translations of the websites and the creation of all necessary social media accounts. A commercialisation plan has been developed which is suitable for the SOUTHPARK testing sites as well as for a global roll out.

With regard to the project's overall objectives significant new commercial and technological hurdles have arisen. Meanwhile strong indicators for a more promising commercialisation route have emerged for ParkTAG’s core technology stack. While the testing phase for the reduction of the search time was planned to start at the end of this reporting period, it can be already seen that no product with high commercialisation potential can be build with given (new) limitations. However, the developed SDK, now promoted under the brand name predict.io, can be highly valuable for many smart mobility verticals like public transport, but also in fraud prevention within banking apps and hospitality apps. It continues to have great value in on-street parking scenarios which is illustrated by the existing paying licensees of the technology.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

While reaching 50% reduction in search time seems not achievable within the timeframe of this project, the underlying logic of saving time with a more efficient allocation of parking spots is still valid. ParkTAG’s detection SDK, once it has reached a higher level of accuracy for start and stop detection and clear distinction between car and non-car, could make this efficient allocation possible, even without being the frontend app for consumers.
With the widened scope of use cases through predict.io, even more benefits for users can be realised, e.g. making public transport more convenient and accessible.

Virtually all mobility apps desire background detection of arrival and departure without user interaction and low-battery consumption as hygienic factor. Known use cases in the mobility vertical are:

a. Real-time parking occupancy
b. Parking payment automation
c. Automated public transport ticketing
d. Intermodal navigation offerings
e. Mobility as a service
f. Real-time traffic alarms (car and public)
g. Capacity planning for…
i. Public transport
ii. Car sharing
iii. Rental bikes
h. Find my car feature
i. Dynamic pricing for...
i. Congestion charges
ii. Parking
j. Trip Logging for tax purposes
k. Commuter travel analysis
l. Handicapped guiding systems

If ParkTAG could pursue this line of work within the SOUTHPARK project, a lot of benefit could come out of the cooperation with the mobility sector. The related call “Small business innovation research for Transport”, part of the H2020 Specific Programme Part III – 4. “Smart, green and integrated transport” aims to tackle the specific challenges of the Transport Specific Programme in a sustainable way. By integrating the SDK into mobility applications, innovative solutions for user movement detections are possible.

Related information

Record Number: 192812 / Last updated on: 2016-12-14
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top