Knowledge Center
Navigation
Knowledge Center

Automotive Sensors

popularity

Description

Sensors are becoming more intelligent, more complex, and much more useful. They are being integrated with other sensors in sensor fusion, particularly in autonomous driving applications. Today’s sensors involve complex power management, radar, and increasing amounts of intelligence. Other developments include acoustic sensing, which is being applied in parallel to radar, so different sensors are combined to get more specific results and make sure that people are only taking action when they need to, while also saving power by not turning on certain sensors when not required.

The number of sensors in automobiles is growing rapidly alongside new safety features and increasing levels of autonomy. The challenge is integrating them in a way that makes sense, because these sensors are optimized for different types of data, sometimes with different resolution requirements even for the same type of data, and frequently with very different latency, power consumption, and reliability requirements. This is the challenge of sensor fusion.

Adding another layer of complexity to sensor fusion is the evolution of radar from 2D to 4D sensing, giving the vehicle a 360 degree view. Together, these sensors are producing an enormous amount of data that needs to be processed very quickly. In addition, the software has to be tightly integrated with the hardware, even more so than was typical in the past.

Autonomous driving is dependent on this kind of successful sensor fusion. The ability to fuse together inputs from multiple sensors is essential for making safe and secure decisions – but there are multiple problems that need to be solved, including how to partition, prioritize, and ultimately combine different types of data, and how to architect the processing within a vehicle so that it can make decisions based on those various data types quickly enough to avoid accidents. There is no single best practice for how to achieve that, which is why many automotive OEMs are taking very different approaches. It also helps explain why there are no fully autonomous vehicles on the road today.

Figuring out where to process data is a challenge, in part because not all data is in the same format. Fusing different data types also depends on what type of sensors are present. Another consideration that comes into play, especially with the tremendous focus on AI/ML techniques, is when to use them, or if classical DSP is more appropriate. A lot of time with AI engines, the data that goes into the AI engine must be pre-processed, which means it must be in a specific format.

This discussion in the automotive ecosystem is just beginning, and there are plenty of challenges to overcome. Sensor fusion is an area of rapid innovation, enabled by continuous improvements in algorithms and the chip industry’s deep knowledge of SoC architectures.

Experimentation will be a requirement as automotive OEMs and systems companies evolve their computing architectures toward sensor fusion. Where each OEM stands today depends on the OEM, how long they’ve been doing architecture development, and how they want to do this going forward.

Multimedia

Improving Image Resolution At The Edge

Multimedia

New Approaches To Sensors And Sensing

Multimedia

Sensor Fusion Everywhere

Multimedia

Sensor Fusion Challenges In Automotive