Even the best of drivers cannot always avoid crashes, particularly if caused by sudden and dangerous behaviours of pedestrians, cyclists, or poorly visible objects on the road. Existing technological solutions designed to improve safety and assistance, like optical camera solutions, Light Detection and Ranging (LIDAR) systems and high frequency radars, are based only on systems of undisturbed sightline to objects, which omits many dangerous events. The EU-funded DeepSight project will address this problem by developing an innovative detection system that will employ a low-frequency radar with a resolution designed to detect cyclists, pedestrians and objects outside a line of sight. It will guarantee road safety and effective assisting drivers in their proper decisions.
The number of road accidents continue to increase dramatically each year. Cyclists and pedestrians, being a part of the daily traffic, keep challenging drivers thus making safety issues increasingly important. Furthermore, miniature electrical vehicles, paving their way through traffic and being in many cases unseen by drivers, put themselves in danger. Improving driving safety, being always a subject to technological efforts, is one of the most important challenges of the modern society.
Continuously developing technologies offer a broad range of tools, capable to assist a driver in a decision making. Moreover, autonomous vehicles, nevertheless facing a broad range of challenges nowadays, will certainly sooner or later contribute to the endeavor. Optical camera solutions, LIDARs and high-frequency radars are already demonstrating exceptional assistance in driving safety by providing overlapping and complementary data. However, all existent safety systems require having an unperturbed line of sight to obstacles. This is a severe limitation, which cause those systems to overlook numerous dangerous events, including pedestrians, stepping on a road from behind a parked vehicle and many others.
MHz and lower GHz frequencies are known to penetrate material bodies and diffract around obstacles - e.g. we have a Wi-Fi signal in office, nevertheless the router is placed behind a wall in a corridor. However, low frequency waves are never used in automotive applications owing to low range and angular resolutions they can grant, as it is commonly believed. While this statement is almost a ground truth in the field, it can be bypassed if a preliminary information on an object does exist. This includes and not limited to rotating bicycle wheels, human breath, and several others. Here we will develop a low-frequency radar for detecting cyclist and pedestrians with a resolution, sufficient to ensure a road safety and assisting drivers to make right decisions.