The automotive revolution begins with Imagination

Innovating the future of automotive technology and autonomous vehicles with PowerVR Automotive.

Making the future of automotive a reality

The automotive industry is going through rapid change and several technological disruptions that will change the face of driving and the industry itself. The auto industry is a huge global undertaking with a market per annum in the trillions of dollars range. With rising congestion, pollution and accident rates, the car industry and governments are pushing for new technologies to help. A move to Electric cars is mooted by 2040, new fuel cell technology with low no emissions, increasing automation of the driving functions to help reduce the 1.2m road deaths world-wide per year, fully integrated traffic systems in smart cities and changes in the model of car ownership are all contributing to a radically changes automotive market environment.

Automotive infotainment and cluster​

There is a shift in the dashboard from an analogue/digital hybrid system to a fully digital dash with larger screens of higher resolution (to 4K), no analogue dials, more screens driven off single GPU. Cluster, HUD, infotainment (including Navi) are coming as complete systems with ADAS included. In vehicles of the future, the human machine interface (HMI) will be more than just dials and digital readouts due to the nature of the information that must be imparted to the driver. This can include audio, visual, sense cues as to what that can is about to do or what issue may lie ahead that the driver must be aware of. Increasing use of the Head Up display (HUD) to make sure that eyes are on the road at all times will become more prevelant as will advanced 3D graphics and new types of dash screen to make sure that the most relevant information is highlighted as a priority to the driver.

In-car entertainment

The infotainment system is taking over from the older Audio Video systems. This is a graphics heavy User Interface delivering FM and DAB radio, internet, navigation, music, multi source data and camera information to the vehicle occupants. Imagination has long been a leader in DAB radio IP (Pure radios were based on the IMG IP). Also with key Automotive applications processors partners imagination IP has been delivered to 10s of millions of cars in the Infotainment space. With its leading embedded GPU performance, support for leading edge APIs and low power, low footprint, its IP is ideally suited to delivering high performance graphics across multiple screens as well as delivering GFlops of processing for GPU compute applications such as ADAS.

Navigation

As part of the infotainment system, the navigation system leverages both the GPU and its pixel handling as well as the HW Virtualisation to allow optimal use of a single GPU for multiple functions within the dashboard systems.

Functional Safety and Virtualization

Functional safety is an essential requirement for many automotive applications that demand a high level of reliability. All PowerVR processors will have proven systematic capability for functional safety. Imagination is investing in the broadest functional safety solutions in the industry, including processors with systematic capability for ASIL D, Software Test Libraries (STLs), and a comprehensive software safety package for the Arm compiler C/C++ toolchain.

Advanced driver-assistance systems (ADAS)

Most new cars will have some form of driver assist applications. Multiple ADAS functions delivered in a vehicle would be considered to be a Level 2 implementation. There are different types of ADAS function – passive/informational where the driver is informed of issues or situations visually on the cluster or centre console or audibly. These tend to be functions like lane departure warning, blind spot detect and similar. The other is active ADAS where the car will automatically take control of some of the car functions such as braking, steering, headlights and so on. For example, Automatic Emergency Braking, as the name suggests, will put the brakes on for the driver the case that they ignore previous warning. ADAS functions can be implemented using the Compute pipeline of the GPU.

Lane departure warning

These are two different use cases. One is a warning to the driver that they are drifting out of lane which can be an audio visual indicator. Lane Keep Assist on the other hand will actually take control of the steering momentarily to bring the car safely back into the right lane. 

Blind spot detect

Blind spot detect is a use case to cover for that gap in the rear view mirror and the door mirrors warning the driver either visually (light on the door mirror) or with an audible signal that the path into that lane is not clear. This either uses dedicated cameras for the function or leverages the multiple surround view cameras that may be in place.

Reversing camera

This has been now mandated on all new cars by NHTSA (The US Transport Authority) so as of today all new cars will be required to support this. This can be a standalone camera or part of the surround view camera system in place.

Surround view

Surround view is becoming the no.1 ADAS feature to be added to a car package. It uses a minimum of 4 cameras of nominally 2K resolution that are stitched together using a GPU to give a 360 view from above the car. This is ideal for parking and checking for pedestrians.

Automotive AI and Neural Networks

With a move along the driving curve to full autonomy from Level 1 to 5, there is a broad rule of thumb that says that you will need at least 10 times the processing power as you go from one level to the next. From a processing perspective we are looking at perhaps 10000 times the base level of processing for all the elements of sensing, computing and actuating all the functions. An ADAS function that is run on the CPU can be run generally 10-20 times faster and a lower power on an embedded GPU due to its inherent capability to perform masses of MAC functions at a lower clock frequency than the CPU. 

Contact Us

Contact Us