EcoGem claimed that the success and user acceptability of Fully Electric Vehicles (FEVs) was predominantly depend on their electrical energy consumption rate and the corresponding degree of autonomy that they could offer. EcoGem aimed at providing efficient ICT-based solutions to this great issue, by designing and developing a FEV-oriented highly-innovative Advanced Driver Assistance System (ADAS), equipped with suitable monitoring, learning, reasoning and management capabilities that would help increase the FEV's autonomy and energy efficiency.

EcoGem based its approach on rendering the FEV:

• capable of reaching the desired destinations through the most energy efficient routes possible;
• fully aware of surrounding recharging points/stations while on move.

To achieve its goals, EcoGem developed and employed novel techniques:

1. on-going learning-based traffic prediction;
2. optimised route planning;
3. interactive and inter-operative traffic, fleet and recharging management via V2V and V2I interfaces and communication.

EcoGem's key-objective was to infuse intelligence and learning functionalities to on-board systems, enabling autonomous as well as interactive learning through V2X interfacing. EcoGem vehicles should learn over time to predict (and thus avoid) congested routes, based on experience that they gather. This learning process eventually renders each EcoGem FEV capable of autonomously classifying routes according to their degree of congestion, enabling energy-driven route planning optimisation.

The EcoGem ADAS additionally worked to cater for the complete planning of the vehicle's recharging strategy. This optimisation process would typically include automated battery monitoring and various levels of pro-activeness, optimised scheduling according to several parameters (battery levels, energy consumption rate, desired destination, present location, daytime, traffic, user agenda, etc.), and real-time booking of recharging points.