Overview
About 40 000 people are killed and 1.7 million injured each year in accidents in the European Union. 150 000 victims become permanently disabled. A significant part of these accidents involves particular driver cohorts, such as motorcycle riders, truck drivers and emergency vehicle drivers. For example, accidents with the involvement of novice drivers account for roughly 15% of all traffic accidents, whereas this group accounts only for 2% of the total traffic volume.
Several scientific studies have shown that a good percentage of these accidents may be attributed to insufficient or even inappropriate training, of higher order skills and risk awareness. Computer Based Training (CBT) tools, such as training videos and CDs, multimedia training, static and dynamic driving simulators, Ambient Intelligence and cooperative driving- based simulation systems, mobile units (i.e. eye tracking) and in-vehicle tools (black box, ADAS, IVICS, cameras) have been proposed and used to train relevant skills in small scale projects so far.
There is a pan-European consensus on the fact that driver training needs to expand away from its current focus on controlling the vehicle in traffic, so as to cover 'higher level' strategic factors. TRAIN-ALL can improve initial and continuous driving training in order to stimulate road users towards a more responsible behaviour. In this way the project can contribute to the European Road Safety Action Programme's goal of halving the number of road fatalities in 2010.
TRAIN-ALL aimed to develop a computer-based integrated training system for different land-based drivers of passenger vehicles, trucks, motorcycles and emergency vehicles, that integrates multimedia, driving simulator, virtual driving simulator and on-board vehicle sensors, into a single modular platform. The new system is cost-effective (able to create a viable business) and adequate both for training and assessment during all modes of vehicle operation (pre-trip, on-trip and emergency handling).
Specific project objectives were:
- To prioritise a concise set of training scenarios for each driver type, for which the use of computer-based training is recommended, with emphasis on risk awareness and emergency handling, covering all levels of driver behaviour (control, manoeuvring, strategic, behavioural).
- To agree on a minimum set of technical specifications for the development of computer-based systems for driver training and assessment.
- To benchmark existing and emerging technologies, such as multimedia s/w, driving simulators, virtual and augmented reality based simulation, etc., against the actual needs and priorities of different categories of drivers.
- To develop a common and concise ontological framework for CBT tools functionalities and scenarios that will guarantee interoperability and transferability of scenarios and data between different CBT tools, and will also support collaborative simulation applications.
- To develop a cost-efficient and valid methodology to assess simulator reliability and fidelity and correlate it to actual driving behaviour.
- To employ Intelligent Agents Technology in order to develop CBT's with AmI-based traffic participants, representing with high reliability a natural traffic environment.
- To develop cooperative training scheme (trainee-trainee and trainer-trainee) and co-driver training (for emergency vehicle co-pilots) scenarios and tools, allowing multiple trial-time interactions and even remote presence.
- To develop the appropriate P2P tools to allow CBT's networking and even real-time collaboration, as well as central data storage and processing for statistical and research reasons.
- To develop a virtual instructor module, that will allow autonomous and cost-effective multi-user training by CBT's.
- To develop guidelines and specifications on simulator sickness aversion in CBT's design and operation.
- To develop and test the method of adaptive training, where t
The core developments focused on driving simulators, with several prototypes developed. New simulation tools have been developed for motorcycle riding, passenger car (novices and emergency drivers) and truck driving. The new tools include also VR-based immersive simulation tools, as well as a common architecture (ontologies-based) and a modular simulator design process for multi-user groups.
The new simulation tools encompass many innovative features, such as AmI-based traffic participants, virtual instructor guidance, ADAS/IVICS training modules and support co-driving, co-operative and group training, remote networking, dynamic scenario management, enhanced reality representation and adaptive training. The developed tools have been tested and optimised with over 250 drivers in 8 pilots Europe-wide, aiming at products, guidelines, standards, certification and accreditation at pan-European level.
Funding
Results
The analysis of several relevant standards has taken place as well as their comparison to TRAIN-ALL work. In total, 14 existing standards are included in the analysis, which are relevant to TRAIN-ALL, to most of which the TRAIN-ALL project abides. Important actions were performed in the project, for the proposal of a new standard on open road network, namely Road Network Format Standard. It describes the logical road network, the road and its vicinity, the structure of the datamodel and belonging objects and attributes. This standard allows interoperability (exchange) of Road Network databases between driving simulators and simulation tools of different manufacturers. To explore the feasibility of having one certified standard, a meeting was organised with representatives of both OpenDRIVE and ROADXML standards.
Guidelines for manufacturers and driving schools on required design characteristics, scenarios, modules and operation of each type of application and driver cohort are extracted. Based on the input from project modules developers, simulators developers, Pilot site leaders of the tests, 24 guidelines are provided that are appropriate for manufacturers, training, pilot testing, public/training bodies, as well as for general simulation training. For each guideline, the reasoning, reference, and the body-user type that it is addressed to, are indicated.
Finally, the legislation in 17 countries has been examined for the inclusion or not of the driving simulator in the training procedure, followed by suggestions on the factors that should be standardised at a European level, to obtain proper use of driving simulators. Only the Directive 2003/59/EC has a reference to the use of simulators for training purposes and again only for trucks. Also, there are not uniform, common simulator-based training curricula among countries, suggesting that there is a need for development of guidance and recommendations to standardise the use of simulators for training purposes.
The strategic impact of TRAIN-ALL can be viewed as:
- Setting the frame for the development of modular, cost-effective and training adequate computer-based tools that can be standardised and officially acknowledged as elements of driver/pilot training curricula.
- Inaugurating a new pan-European market for computer-based training tools, according to a minimum set of common specifications and communication/ interoperability attributes, that are user-group and task-dependent.
Innovation aspects
Ten innovative simulator modules have been developed that aim to improve the training process and efficiency.
- Ambient intelligence in driving simulation
This innovative module monitors actual drivers profile in a driver simulator (in particular scenarios) in order to build a driver behaviour model and offer natural simulation environments and the enabling of training personalisation according to each driver's own driving style. - Co-driving, cooperative and group training
This module enables solutions, training and evaluation methods for the co-driving training between the pilot and the co-pilot from a set of Police mission scenarios, which cover different themes as knowing where you drive, accidents and causes of damage, responsibility and tactics in emergency driving. New methods of team training are proposed and then validated. - Immersive simulation for multi-vehicle
This module allows, by means of Virtual Reality technologies, to switch quickly from a given vehicle type to another, and even from a given vehicle category to another, this in order to train the novice driver with a gradual approach, starting from easy-to-drive vehicles till to 'difficult' ones. The 3D visualization allows a good perception of sizes and distances, and the head tracking allows a right visual interaction among driver, interiors and external scenario. - P2P Internet technologies for CBT
This module sets up an Internet remote control and its instructor functionalities to the TRAIN-ALL demonstrators. The Remote control tool is a software tool, which can be run on an arbitrary computer in the internet to control remote a simulator. - Virtual instructor and debriefing
This module objectively measure the driver's performance based on a representative set of normative values and gives assistance to assessment or self-assessment by a simple automatic protocol during the exercise or the debriefing. - Dynamic scenario management
This module manages the scenarios as a set of short sequence with certain traffic, terrain and rendered difficulties. It builds an adapted trainee exercise sequence from the curricula objective or for example from the feedback of the automatic assessment from the VI. It reduces the work cost of the scenarios script realisation and enhance the capacity to profile the exercise to the trainee benefit. - ADAS/ IVICS simulation
This module consisTechnical Implications
A systematic review of a wide range of existing tools and technologies for computer-based training (CBT) of drivers in all TRAIN-ALL application fields, was conducted at the early stages of the project life. The review covered all CBT tools, with emphasis on driving simulations of all functional levels. The purpose was to provide an indication of the state of the market and take the first steps towards clarifying the types of CBT available and showing how they might be considered during future accreditation and certification of driver training schemes. The focus here was on technology provision. More precisely, a questionnaire survey was conducted to gather information on multimedia tools, neurological test batteries and driving simulators used in project member countries and overseas. In total 46 completed questionnaires on multimedia tools, neurological test battery and simulators were analysed.
The review showed that the set-up of simulator training often seems to be a mere translation of on-road driving lessons into the virtual worlds. The lack of coverage of the highest levels of the GADGET matrix (strategic and motivational driving goals) may not only be explained by technical inabilities of a simulator, but rather by the absence of an in-vehicle training format that successfully addresses these variables. Finally, more and robust evaluation studies of simulator-based driving are urgently needed.
Policy implications
The main objective of the project was the development of the TRAIN-ALL platform, for an advanced, holistic, and uniform training of various drivers cohorts throughout Europe. The introduction and deployment of this platform is expected to have thus the following impact:
- Improved road safety by delivering better drivers' training and assessment.
- Improved road safety simply by less need for on-the-road training.
- Reduction of traffic volume and pollution in cities by less on-the-road training as well as through ecological/economical training promotion by the new training tools.
- Creation of invaluable statistical record of drivers' behaviour through the log files of the computer-based tools.
- Reduction of the stress levels of trainers and trainees, induced by actual on-road training of complex situations.
- Reduction in training time and cost.
- New employment opportunities and competitive advantage for the European training tools industry.
Readiness
TRAIN-ALL developments have contributed significantly to the standardisation procedure described in 'A sustainable future for transport: Towards an integrated, technology-led and user friendly system - Communication from the Commission of European Communities – Brussels COM(2009) 279/4; 5.3 § 77-78: Technology - how to accelerate the transition to a low-carbon society and lead global innovation'.
The following TRAIN-ALL product configurations are foreseen:
- Product Configuration A: a motorcycle simulator owned by INRETS;
- Product Configuration B: a truck simulator owned by THALES;
- Product Configuration C: an emergency vehicle simulator owned by WIVW;
- Product Configuration D: a passenger simulator owned by WIVW;
- Product Configuration E: an immersive simulator owned by CRF;
- Product Configuration F: a multi-purpose driving simulator owned by GREEN DINO;
- Product Configuration G: an emergency vehicle simulator owned by BPP;
- Product Configuration H: a passenger simulator owned by FOERST.