Radar for Autonomous Driving – Paradigm Shift from Mere Detection to Semantic Environment Understanding

Dickmann, Jürgen; Lombacher, Jakob; Schumann, Ole; Scheiner, Nicolas; Dehkordi, Saeid K.; Duraisamy, Bharanidhar

doi:10.1007/978-3-658-23751-6_1

Cited by 7 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other perception sensors are also employed for identifying obstacles without relying on visual information from cameras such as the very recent publication [4] where the LIDAR information on its own is exploited through a deep learning structure for the identification of obstacles through a generativeadversarial approach. Similar publications employing deep learning approaches for extraction of information of interest from raw data from other RADARs for the purpose of autonomous driving is presented in recent publications such as [5], [6] and [7], where in the latter we see on top a fusion approach for both the RADAR and LIDAR data. Ultrasonic sensors, as well, are used for environment perception using deep learning based methodologies, such as in [8] where deep learning approaches are used to classify noise and echoes of automotive-grade ultrasonic sensors and [9] where a deep learning structure is proposed to suppress spurious noise artifacts superimposed on ultrasonic echo raw signals showing that it surpasses conventional methods in terms of maintaining the integrity of the signal of interest and causing minimal distortion.…”

Section: State Of the Artsupporting

confidence: 53%

A deep learning approach for direction of arrival estimation using automotive-grade ultrasonic sensors

Elamir

Gotzig

Zöllner

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In this paper, a deep learning approach is presented for direction of arrival estimation using automotive-grade ultrasonic sensors which are used for driving assistance systems such as automatic parking. A study and implementation of the state of the art deterministic direction of arrival estimation algorithms is used as a benchmark for the performance of the proposed approach. Analysis of the performance of the proposed algorithms against the existing algorithms is carried out over simulation data as well as data from a measurement campaign done using automotive-grade ultrasonic sensors. Both sets of results clearly show the superiority of the proposed approach under realistic conditions such as noise from the environment as well as eventual errors in measurements. It is demonstrated as well how the proposed approach can overcome some of the known limitations of the existing algorithms such as precision dilution of triangulation and aliasing.

show abstract