Circular Convolutional Learned ISTA for Automotive Radar DOA Estimation

Jihwan Youn, Satish Ravindran, Ryan Wu, Jun Li, Ruud van Sloun

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

2 Downloads (Pure)


Radar is imperative for many automotive applications in detecting targets. Accurate direction of arrival (DOA) estimation is essential for maximizing the reliability of radar by improving the angular resolution. And a lightweight algorithm with a small memory footprint is desired considering that limited computational resources are accessible for automotive radar. Conventionally, iterative algorithms such as iterative shrinkage thresholding algorithm (ISTA) were used for DOA estimation. However, algorithms like ISTA can require many iterations to converge, and a lot of manual parameter tuning is required to obtain optimal performance. Learned ISTA (LISTA) has been used to approximate ISTA with fewer iterations without the necessity of manual tuning by unfolding the iterative algorithm as a neural network. But directly using LISTA is not suitable for DOA estimation due to the large size of the matrices that need to be learned. The large number of learning parameters require a lot of training data, a long training time, and heavy computation. This work proposes to use circular convolutions to reduce the number of learning parameters in the model as well as computation. We show that the circular convolution-based ISTA has better performance metrics than the traditional ISTA.
Originele taal-2Engels
Titel2022 19th European Radar Conference (EuRAD)
UitgeverijInstitute of Electrical and Electronics Engineers
Aantal pagina's4
ISBN van elektronische versie978-2-8748-7071-2
ISBN van geprinte versie978-1-6654-5879-5
StatusGepubliceerd - 25 okt. 2022
Evenement19th European Radar Conference, EuRAD 2022 - Milan, Italië
Duur: 28 sep. 202230 sep. 2022
Congresnummer: 19


Congres19th European Radar Conference, EuRAD 2022
Verkorte titelEuRAD 2022


Duik in de onderzoeksthema's van 'Circular Convolutional Learned ISTA for Automotive Radar DOA Estimation'. Samen vormen ze een unieke vingerafdruk.

Citeer dit