The Goal of the Project
While traditional cars relied solely on the senses of their drivers – mostly their eyes and ears –, the cars of today are equipped with more and more sensors, supplying information to their drivers or using the information to take decision autonomously. Self-driving cars come within reach by equipping cars with their own set of eyes, in the form of LIDARs and cameras. Yet, to become truly aware of their environment, such smart cars are still missing an invaluable input on which we, as humans, rely strongly: the acoustic information. I-SPOT targets the addition of acoustic sensing technology to cars, to bring enhanced environmental awareness.
This acoustic information complements the information from other sensory technologies. In active (drive) mode, this will
give information about nearby emergency vehicles, accidents, passing cars, etc., which are currently causing major disruptions of autonomous and computer-assisted driving. Moreover, information on weather conditions and mechanical car wear or failure is present in the acoustic signal. More than just detection of the nature of the sound, also the direction, even for visually occluded sources, can be derived. In passive (park) mode, information can be obtained on car damage (e.g. car body scratch, breaking car glass or side mirrors, etc.), theft or nearby critical events (e.g. cry for help). The acoustic sensor can as such form the low-cost wake-up trigger to direct the more power-hungry camera system to activate and point in a specific direction.
- The goal of I-SPOT is to drive acoustic awareness of smart cars from two different angles. As its technical contribution, I-SPOT aims to enable sensing, localizing and analysing environmental audio signals during the active (drive) and passive (park) car mode by performing R&D on the following aspects:
- the efficient placement of audio sensors on the car body to improve the received signal quality
- the development of low-footprint signal processing technologies for automotive acoustic signal characterization and localization
- the design of smart, adaptive, ultra-low-power hardware that can be always-active, also when the car is switched off
- The industrial/economical ambition of I-SPOT is to train young scientists in the field of low-power signal processing technologies and hardware for automotive applications, to:
- strengthen the position of Europe in the smart car electronics business
- transfer the relevant know-how to industry by educating scientists who apply the academic knowledge in a real industrial environment.
To achieve this dual goal, innovation is needed in three distinct domains, requiring complementary, multi-disciplinary expertise:
- Innovation is needed on smart sensor array design, placement and integration. This involves the evaluation of system trade-offs between cost and task accuracy, taking into account the specific constraints of the car manufacturing business.
- Innovation is needed on adaptive signal processing algorithms for acoustic detection, localization and signal enhancement, exploiting state-of-the-art signal processing and machine learning techniques.
- Innovation is needed on low-power chip implementations for the acoustic sensor front-end and embedded signal processing, exploiting custom processor architectures and mixed-signal processing.
The realization of the envisaged concept requires a very tight interaction between the different pillars, and between state-of-the-art actors in academia and business-oriented actors in industry. The framework of a European Industrial Doctorate perfectly fits this need. In this context, I-SPOT targets to start a dedicated doctoral programme between Bosch and KUL, with very frequent exchanges between the two institutes. The two pioneering Early Stage Researchers (ESR1 and ESR2) will be trained in the above-mentioned complementary domains, closely guided by the different PIs, and will be embedded in research groups already very knowledgeable in the field to be the first of a generation innovators in this field.
Upon realization of the I-SPOT technology, Europe can strengthen its position in the smart car electronics business. The two highly skilled PhDs can easily be accepted in the employment market to transfer the required know-how to the European industry. The target application for I-SPOT technologies (information capture in the presence of emergency cars such as fire trucks, ambulance and police, in case of accidents, specific weather conditions, etc.) is part of the major disruption of autonomous and computer assisted driving in the car manufacturing sector. Very few teams have the required broad multi-disciplinary expertise to bring all these aspects together. We look forward to play a leading role in this field!