Autonomous Driving (AD) is a complex research area. Through the aid of Machine Learning (ML) techniques, AD systems have rapidly developed, yet there are several challenges involved in deploying these ML algorithms to systems in production. Solving these challenges is beyond the capability of any single company or institution, necessitating large-scale communication and collaboration. Our goal is to provide a platform for this at ICLR, and promote the real-world impact of ML research toward self-driving technology. To this end, we propose a workshop titled “Scene Representations for Autonomous Driving” (SR4AD). We have invited a diverse span of keynote speakers (different regions, academic/industry, junior/senior) to contribute to the workshop. In addition, our program includes a call for contributed papers and a call for competition participation around two new and exciting benchmark tasks for mapping and planning. Finally, to encourage broad discussions, we conclude with a panel debate regarding promising future directions.