Discover the new Simcenter SCAPTOR and learn why ADAS sensor data collection is critical to the development of next-generation vehicles. Simcenter SCAPTOR is a high-speed in-vehicle data collection solution to capture, store, and replay essential ADAS data.
Also watch the YouTube Premiere of Simcenter SCAPTOR – available in replay.
Live webinar coming up! Join our experts on December 9, 2020, and learn how to tackle the challenges of ADAS sensor data collection!
What is ADAS?
Firstly, what does this strange acronym stand for? ADAS means advanced driver assistance systems. It is a generic denomination to designate all past, current, and future electronically-controlled, advanced safety systems in a car. It includes, but is not limited to, automated emergency braking systems (AEBS), lane-keeping assistance systems (LKA), adaptive cruise control (ACC), blind-spot monitoring (BSM)… Yes, the world of ADAS is full of acronyms!
But behind the capital letters hides essential technology that saves lives. Over the past decades, these systems have been gradually introduced to enhance safety in vehicles. Based on the information captured by the sensors around the car, the system will warn the driver of a critical driving condition. The lane-keeping assistance system, for example, uses front cameras to detect the presence and trajectory of the driving lanes. If the driver veers unexpectedly off the lane, the system issues sensory warnings to the driver, with a short beep, a warning light, and a sensation of resistance in the steering wheel. In some situations, depending on the level of automation of the car, the assistance system might even initiate – or execute – the braking or escaping maneuver.
But why do you need to collect ADAS sensor data?
At first, the technology may seem relatively straightforward. Various sensors, short and long-range radars, low or high-resolution cameras, or even lidars (3-D laser scanning sensors), gather the information. The car’s electronic control unit (ECU) uses this information to meet an appropriate driving decision, such as issuing a warning, slowing down, or applying the brakes. But real-life driving conditions are rarely simple ones.
Take the example of the pedestrian detection systems. These systems are designed to avoid a potentially fatal collision between cars and pedestrians on the roads. Yet most systems aren’t nearly as efficient as they should be. The American Automotive Association performed a study in October 2019. The association warns vehicle owners that they should not blindly rely on their collision avoidance systems and remain engaged drivers. While most systems detected the presence of an adult crossing the streets, a vast majority failed to avoid a collision with a child darting out. Worse, all systems failed to properly detect pedestrians at night.
ADAS sensor data helps validate the pedestrian detection systems.
Testing and validating the systems using real-life data is a must. Thinking about it, how does a pedestrian look like? How tall is he, what garment does he wear, how fast does he move? An anti-collision system must be able to identify any pedestrian crossing the road, adults and children alike, even a person in a wheelchair. Equally, the system should not apply the brakes when spotting the image of a running child featured on a digital billboard. It must be smart enough to identify real driving hazards and set them apart from non-threatening situations.
What vehicle manufacturers need to train the algorithm of the ECU is data. Information about the myriad of possible driving situations that the ADAS system has to consider. Only then it is possible to train the algorithm to make the right driving decision in any situation.
Why is it complex to collect this ADAS sensor data?
But yet again, data acquisition and processing have already been part of a vehicle development process for many years. Why is it different with ADAS sensor data?
Firstly, this data needs to be raw. Only authentic, uncompressed data will render a genuine vision of a complex driving situation. This raw data is essential to the training of the algorithms.
Secondly, the driver assistance systems evolve towards a higher degree of automation. The society of automotive engineers (SAE) defines 6 levels of driving automation, ranging from 0 (fully manual) to 5 (fully autonomous). Many vehicles driving on the road today feature level 2 partial driving automation. However, car manufacturers expect to introduce higher levels of driving automation in near future. These advanced systems require more sensors, and more data to operate. The number of radars, cameras, and other sensors fitted in the car explodes, and so does the outcoming raw data.
Thirdly, all this raw data streaming from various sensors need to be perfectly synchronized. The slightest delay could result in delivering the wrong information about the driving situation. And lead to a fatal collision. To avoid this, you need the quickly and accurately time-stamped the data, as close as possible to the sensors itself.
So, how do you do all of that?
Simcenter SCAPTOR captures raw ADAS data at ultra high-speed
Collecting information from the various ADAS sensors in a vehicle is essential to the development of the next-generation, partially autonomous or fully autonomous, vehicles.
But how many terabytes of ADAS sensor data can you collect per test vehicles per day? How fast can data stream from the sensors to the central unit? And how can you synchronize data streaming from multiple sensors?
Also, how can you ensure the interrupted collection of data? How can you avoid that the recorder fails or breaks down in harsh driving conditions?
Discover Simcenter SCAPTOR, the new Simcenter solution for high-speed, in-vehicle data collection.
Do you have a question for our experts? Ask it in the comments below, tune in to our Simcenter YouTube channel, or voice it in person during the live webinar on December 9!
Are you now looking for more technical information about Simcenter SCAPTOR? Read also the knowledge-base article Validate tomorrow’s vehicle with Simcenter SCAPTOR