ON-GOING PROJECTS

NOSTROMO - Next-Generation Open-Source Tools for ATM Performance Modelling and Optimisation – Active Learning for Scenario Discovery in Air Traffic Management simulators.

SHOW - migration path towards affective and persuasive sustainable urban transport, through technical solutions, business models and priority scenarios for impact assessment, by deploying shared, connected, cooperative, electrified fleets of autonomous vehicles in coordinated Public Transport (PT), Demand Responsive Transport (DRT), Mobility as a Service (MaaS) and Logistics as a Service (LaaS) operational chains in real-life urban demonstrations in 5 Mega, 6 Satellite and 3 Follower Pilots taking place in 20 cities across Europe.

LINC - Prediction of demand for autonomous shuttles in a small area. Multi-output models for spatio-temporally correlated movements. Interfacing with demand-responsive optimization of supply.

PRISM – Probabilistic prediction for smart mobility under stress scenarios.  (Marie Sklodowska-Curie Individual Fellowship H2020-MSCA-IF- 2016, ID number 745673)

PAST PROJECTS

TrIC (DTU) - Transportation in context: from explaining the past to predicting the future using information mined from the Web.

Demand Prediction for Autonomous Mobility (DTU, NTU) – Both DTU and NTU (Nanyang Technological University) have on-campus autonomous buses experiments. The goal in this research is to predict demand in real-time, in order to support a dynamic optimisation process.

Tripod (MIT) – on using an incentive system for sustainable energy travel behavior, considering multiple modes, intelligent sensing, and predictive optimisation.

Extraordinary Queueing Detection (DTU, Danish Road Directorate) - A methodology for automatically detecting non-recurrent queues in the Danish Motorway network.

Semantics and the City (DTU) - on using natural language processing and information retrieval technology to capture data about the city and use it for predicting behaviour.

Demand prediction for special events (DTU, SMART/MIT) – In this research we apply machine learning and web mining techniques to retrieve data from the web, combine with smart card data from Denmark and Singapore and create prediction models (regression and/or classification).

Event detective (DTU, CISUC) – Using data from the transport system (e.g. taxi data, smart card data, loop counters), identify anomalies and search for potential explanations from available feeds (mostly in the internet). This combines event detection data analysis with web mining.

Activity based grammars (DTU, Univ. Maryland) – We apply probabilistic context free grammar (PCFG) techniques for activity pattern modelling and generation (e.g. for choice set generation in activity based modelling). The assumption is that our daily (and weekly, monthly…) life has some sort of “syntax” (e.g. days normally start and end at home; if you drop-off your kid, you’re like to pick him up; etc). This is a collaboration with U.Maryland

DynaMIT2.0 (SMART/MIT) — on next generation real time traffic prediction, that considers new types of data, public transport and crisis management support;

Future Mobility Survey, FMS (SMART/MIT) — a smartphone-based data collection platform that is focused on capturing activity diary data for transportation modeling applications;

SimMobility (SMART/MIT)— a multi-level simulation model that considers decision making processes that range from short-term choices (e.g. lane changing, breaking) to very long term ones, such as house or relocation;

Language based technologies for supply operations (DTU, SMART/MIT)- Application of natural language processing tools to support more efficient transport network operators. For example, real-time analysis of incident response communications to assess severity and predict impact.

Crowds (CISUC)— about using crowdsensing tools to analyse urban land use, both statically (e.g. Points of Interest) as well as dynamically (e.g. special events).

COSMO — about distributed routing mechanisms and individualized spatial cognition;

iTEAM — an integrated transportation and energy simulation model;

Citymotion — about real-time traffic data analysis and prediction;

AIDA — an Affective Intelligent Driving Agent, a very fun project that involves user interaction, driver behavior prediction and personal robots;

YouTrace — focused on generating transport network maps from GPS traces.