AI techniques and tools are beginning to impact every part of the system design, build, and testing process. Each stage is affected in unique ways but enabled by the same underlying advances in technology.
David Doria of Magna International explores how AI is transforming ADAS from system design and development to end-to-end driving models and simulation.
Written by:
David Doria- Director of Engineering, Automated Driving
On the design side, even traditionally non-flashy or behind the scenes tasks are being overhauled. As one of many examples, we are starting to see many tools on the market for automating requirement management – such as identifying overlaps between requirement documents from multiple customers -which has historically been tedious and error-prone for humans.
In the realm of online systems – the actual ADAS features running in real-time in vehicles – we are entering the third era. The first era (pre-~2012), involved hand- coded systems for both “halves” of the system- ‘Perception’, and ‘Drive Policy’.
Perception required teams of computer vision engineers to craft image descriptors that could be extracted and matched.
Drive Policy relied on fragile rules and heuristics to control steering and acceleration to achieve driving goals. Over the last decade, the second era emerged with the introduction of Convolutional Neural Networks, which nearly replaced manual feature extraction in perception, though Drive Policy remained largely rule-based.
Now, with the introduction of Transformer models and Foundational models, we are entering the third era. Drive Policy is beginning to be replaced similarly, with early signs of integrating the subsystems into a single “End to End Model”, where AI is trained to take in the sensor data and emit control signals directly- much like how human drivers operate.
Closing Remarks
Finally, it is well known that large quantities of data are needed to train and evaluate the models and systems. This type of data collection on real roads with real vehicles is tedious and expensive. AI is playing a significant role here through simulation. Tools now enable the creation of massive, powerful datasets without ever leaving the office, leading to significant cost savings and faster project timelines. These simulations can generate video game-like data, and with the latest models, even use natural language commands to modify real-world data. For example, commands like “add rain to the scene” can produce new datasets with water on the roads and even droplets on the camera lenses. While not yet fully mature, these capabilities are rapidly advancing, and soon we will have augmentation features where commands like “add more traffic” will generate the desired scenarios.
While these paradigm shifts present challenges, it’s clear that AI is having a revolutionary and lasting impact. The current challenge is to keep pace with rapid developments and harness this technology to make real-world driving safer and more comfortable, despite its enormous complexity.
Don’t miss David’s presentation ‘AI Inside and Out: Redefining the Driver and Driving Experience for the Future of Consumer ADAS‘ at AutoSens USA this year!
Interested in In-Cabin monitoring technology?
With a pass to AutoSens USA, you’ll also get full access to our co-located sister event, InCabin. Take a look at the full agenda for InCabin here >>
Explore more interviews on the AutoSens YouTube Channel⬇
