Technology

HD maps for automated driving – literature review

maps for automated driving

In January 2020 iMOVE, in partnership with the Queensland Department of Transport and Main Roads (TMR) and the Queensland University of Technology, published a report P1-007: How Automated Vehicles Will Interact with Road Infrastructure Now and in the Future.

The report highlighted the single most critical contributor to improved performance of automated vehicles is the availability and use of prior maps of the environment. Further the report highlighted the infrastructure manager may have a role in developing, monitoring, and maintaining the prior maps of the environment.

This new project will carry out a literature review on the subject of map creation, monitoring and maintenance to facilitate automated driving. The outcome of this project is expected to inform the scope of further study on the matter.

Participants

See the full list of iMOVE projects here

Project background

The capability of self-driving cars has increased substantially in recent years and are expected to be an important part of the fleet within the next decade. These vehicles can be thought of in two different ways:

  • connected vehicles, and
  • autonomous vehicles

Connected vehicles (CV) allow vehicles to communicate with each other and the world around them. This concept is often about supplying useful information that can inform decision making – it does not necessarily imply that the vehicle is making choices for the driver. Aspects of connected vehicle technologies are already well embedded in the vehicle fleet, for example with GNSS-based navigation systems often including dynamic route guidance.

Autonomous vehicles (AV) remove some or all tasks from human control. The level of automation in a vehicle may vary, ranging from minor assistance to the driver, to a fully automated vehicle that does not require a driver to function. Some of these technologies are market-ready and available to users, including self-parking, lane-keep assist, and emergency braking systems. These technologies are often described using the SAE International Standard, describing vehicles from Level 0 (No automation) to Level 5 (Full automation).

To operate safely, autonomous vehicles will likely require purpose-built prior maps (also known as High Definition (HD) maps), which contain significantly more detailed information and true-ground-absolute accuracy than those found in current conventional maps. For high-level autonomy (Levels 4 and 5) it is likely that significant use of prior maps will be critical, but these maps will also enhance the capability of lower levels of autonomy which already exist in current and future vehicle releases.

Prior map data is a key enabler of highly automated driving. With the advent of highly automated vehicles, car makers and map suppliers investigate new approaches to create, monitor and maintain prior maps by using onboard sensor data of series vehicles.

TMR and the Queensland Government supplies citizens and business with reliable data, giving information about infrastructure and network operations. An important part of the TMR/Government role is understanding the requirements placed on its data and undertaking a programme of continuous improvement to ensure benefits from data provision are maximised.

It is therefore essential for TMR and the Queensland Government to understand the potential requirements for geospatial data to support the operation of autonomous vehicles now and in the future.

Project objectives

The objective of this project is to carry out literature review on map creation, monitoring and maintenance to facilitate automated driving. The outcome of this project is expected to inform the scope of further study on the matter.

More from iMOVE Australia

Most Popular

To Top