Autonomous systems such as "self-driving" vehicles and closedloop medical devices increasingly rely on learning-enabled components such as neural networks to perform safety critical perception and control tasks. As a result, the problem of verifying that these systems operate correctly is of the utmost importance. We will briefly examine the role of neural networks in the design and implementation of autonomous systems, and how various verification approaches can contribute towards engineering verified autonomous systems. In doing so, we examine promising initial solutions that have been proposed over the past three years and the big challenges that remain to be tackled.