System trains driverless cars in simulation before they hit the road

Control systems, or "controllers," for autonomous vehicles largely rely on real-world datasets of driving trajectories from human drivers. From these data, they learn how to emulate safe steering controls in a variety of situations. But real-world data from hazardous "edge cases," such as nearly crashing or being forced off the road or into other lanes, are -- fortunately -- rare.

Some computer programs, called "simulation engines," aim to imitate these situations by rendering detailed virtual roads to help train the controllers to recover. But the learned control from simulation has never been shown to transfer to reality on a full-scale vehicle.

The MIT researchers tackle the problem with their photorealistic simulator, called Virtual Image Synthesis and Transformation for Autonomy (VISTA). It uses only a small dataset, captured by humans driving on a road, to synthesize a practically infinite number of new viewpoints from trajectories that the vehicle could take in the real world. The controller is rewarded for the distance it travels without crashing, so it must learn by itself how to reach a destination safely. In doing so, the vehicle learns to safely navigate any situation it encounters, including regaining control after swerving between lanes or recovering from near-crashes.



Nowadays one of the biggest problems in cities is the transportation system and its infrastructure. There have been lots of studies and research in recent decades trying to find solutions. In general, there is an economic impact when countries make an investment in this sector. Most of the studies on transport infrastructure, in particular, focus on its impact on growth.

To simulate and optimize the urban transport infrastructure, Idalia F. L. M. and Esther S. P. used a systematic approach to divide it according to the city of Calgary. The survey result was published at the journal Urban Transportation & Construction.

The objective of this paper is to summarize how this issue has been studied in recent years, with an emphasis on the use of simulation and optimization at the whole planning process. They also consider the important key topics as sustainability, costs and risks, mobility and environment impact. Some study cases are shown to clarify the concepts presented. 

Read the full paper at: