The challenges of developing advanced driver assistance systems

07 November 2013

http://www.newelectronics.co.uk/electronics-blogs/the-challenges-of-developing-advanced-driver-assistance-systems/57515/

The challenges of developing advanced driver assistance systems

Just months after the release of the ISO 26262 automotive functional safety standard in 2011, the auto industry began to grasp its importance and adopt it in a big way. Safety certification is gaining traction in the industry as automakers introduce advanced driver assistance systems (ADAS), digital instrument clusters, heads up displays and other new technologies.

Governments around the world, and the US and the EU in particular, are calling for the standardisation of ADAS features. Meanwhile, consumers are demonstrating a readiness to adopt these systems and ABI Research claims the global ADAS market will grow to be worth more than $260billion by the end of 2020.
So what are the challenges that ADAS suppliers face when bringing systems to market?
Here, in my opinion, are the top 10:

1. Safety must be embedded in the culture of every organisation in the supply chain.
ADAS suppliers can't treat safety as an afterthought; they must embed it into their development practices, processes and corporate culture.
To comply with ISO 26262, an ADAS supplier must establish procedures associated with safety standards, such as design guidelines, coding standards and reviews, and impact analysis procedures. It must also implement processes to assure accountability and traceability for decisions. These processes provide appropriate checks and balances and allow for safety and quality issues to be addressed as early as possible in the development cycle.

2. ADASs are a collaborative effort.
Most ADASs must integrate IP from a number of partners; they are too complex to be developed in isolation by one supplier. Also, in a safety certified ADAS, every component must be certified — from the underlying hardware (be it a multicore processor, gpu, fpga or dsp) to the OS, middleware, algorithms and application code. Application code must be certified to the appropriate automotive safety integrity level; for ADAS applications, this is typically ASIL D, the highest level of ISO 26262 certification.

3. Systems may need to comply with multiple industry guidelines or specifications.
Besides ISO 26262, ADASs may need to comply with additional criteria, as dictated by the tier one supplier or automaker. On the software side, these criteria may include Autosar or MISRA. On the hardware side, they will include AEC-Q100 qualification, which involves reliability testing of auto grade ics at various temperature grades. ICs must function reliably over temperature ranges that span from -40 to 150 °C, depending on the system.

4. ADAS development costs are high.
To achieve economies of scale, they must be targeted at mid and low end vehicles. Prices will then decline as volume grows and development costs are amortised, enabling more widespread adoption.

5. The industry lacks interoperability specifications for radar, laser, and video data in the car network.
For audio/video data alone, automakers use multiple data communication standards, including MOST, Ethernet AVB, and LVDS. As such, systems must support a multitude of interfaces to ensure adoption across a broad spectrum of possible interfaces. Systems may also need additional interfaces to support radar or lidar data.

6. The industry lacks standards for embedded vision processing algorithms.
Ask five people to develop a lane departure warning system and you'll get five different solutions. Each will likely start with a Matlab implementation that is ported to run on the selected hardware. If the developer is fortunate, the silicon will support image processing primitives to accelerate development.

7. Data acquisition and data processing for vision based systems is high bandwidth and computationally intensive.
Vision based ADASs present their own technical challenges. Different systems require different image sensors operating at different resolutions, frame rates and under different lighting conditions. A system that performs high speed forward facing driver assistance functions, such as road sign detection, lane departure warning and autonomous emergency braking, must support a higher frame rate and resolution than a rear view camera that performs obstacle detection.
Forward facing systems must acquire and process more data at a faster frame rate, before telling the driver of an unintentional lane drift or warning the driver that the vehicle is exceeding the posted speed limit.

8. ADAS cannot add to driver distraction.
There is an increase in the complexity of in vehicle tasks and displays that can result in driver information overload. Systems are becoming more integrated and are presenting more data to the driver.
Systems must therefore be easy to use and should make use of the most appropriate modalities and be designed to encourage driver adoption. Development teams must establish a clear specification of the driver vehicle interface early in development to ensure user and system requirements are aligned.

9. Environmental factors affect ADAS.
ADASs must function under a variety of weather and lighting conditions. Ideally, vision based systems should be smart enough to understand when they are operating in poor visibility, such as heavy fog or snow, or when direct sunlight shines into the lens. If the system detects that the lens is occluded or the lighting conditions are unfavourable, it can disable itself and warn the driver that it is non operational. Another example is an ultrasonic parking sensor that becomes prone to false positives when encrusted with mud. Combining the results of different sensors or different sensor technologies – sensor fusion – can often provide a more effective solution than using one technology in isolation.

10. Testing and validating is an enormous undertaking.
Arguably, this is the most challenging aspect of ADAS development, especially when it comes to vision systems. Prior to deploying a commercial vision system, an ADAS development team must amass hundreds, if not thousands, of hours of video clips in a regression test database, in an effort to test all scenarios. The goal is to achieve 100% accuracy and zero false positives under all possible conditions. But how can the team be sure the test database comprises all test cases? The reality is they cannot — which is why suppliers spend years testing and validating systems and performing extensive real world field trials.

There are many hurdles to bringing ADAS to mainstream vehicles, but they are surmountable. ADAS systems are available today, consumer demand is high and the path towards widespread adoption is paved. If consumer acceptance of ADAS provides any indication of societal acceptance of autonomous drive, we're well on our way.

Author
Tina Jeffrey

Comment on this article