Reducing traffic accidents is an automotive driving force of the European Commission (EC), which points out the development of advanced driver assistance systems (ADAS) as key to reduce them. Vehicles are in the market incorporating ADAS such as so-called ACC for keeping a safe gap with preceding vehicles. ACC and other ADAS monitor the road around the vehicle, which is essential to react under external unexpected events. However, driver distraction itself also causes more than 20% accidents. Thus, we can find ADAS in the market for monitoring driver drowsiness as well.
Another EC driving force is environment. In this case, electric cars are a major contribution of the automotive industry. Note that using electric cars will be an economic and ecologic option. We are interested in those for urban environments and we will term them as E³-cars. An arising question now is the following; can we have ADAS for E³-cars at the same time? For instance, can we buy E³-cars with ACC? or with Driver monitoring?. To the best of our knowledge, the answer is no.
Deploying current market ADAS into E³-cars presents several difficulties. For instance, ACC is based on radar/lidar which are technologies not well suited for E³-cars (price, interferences). Moreover, ACC works over 80Km/h while urban speeds are lower. In addition, other potential ADAS as pedestrian detection systems have a huge interest in urban environments, but they are not yet ready to the market and prototypes also rely on radar/lidar. Regarding driver monitoring ADAS, we see that they are mostly based on indirect measures (e.g., steering wheel movements, use of pedals and turn indicators, etc.) which require mid-long travels to adapt well to driver behaviour, while urban travelling relates to short distances. Besides, most systems focus on drowsiness, while in urban environments distractions are a more common problem.
Accordingly, the overall aim of this proposal is to research technologies for bringing ADAS to urban oriented electric vehicles. Two are the major distinctive features of our proposal are: (1) the use of vision as “eco”-sensor; and (2) to follow a driver-centric approach, i.e., rather than thinking in road and driver monitoring as working-alone ADAS, we will make them to cooperate in order to assist the driver only when he/she really need it, or in other words, working as actual co-drivers. Both things together build our concept of eco-driver.
We organize the overall coordinated project “eCo-DRIVERS: Ecologic Cooperative Driver and Road Intelligent Visual Exploration for Route Safety” as three complementary and collaborative subprojects: (1) “Vision-based Driver Assistance Systems for Urban Environments (ViDAS-UrbE)”; (2) “Driver Distraction Detection System (D3System)”; and (3) “Intelligent Agent-based Driver Decision Support (i-Support)”. The core research of subprojects (1) and (2) will focus on computer vision while (3) will address research on machine learning and reasoning under uncertain and incomplete data. Based on this research the project aims to develop two urban-oriented and vision-based co-drivers for (a) driver-centric obstacle detection; and (b) driver-centric pedestrian detection.