Blend machine learning and radar for improved navigation
What you will learn:
- What does the central processing architecture enable?
- The advantage of having a radar and a camera over either.
- What’s wrong with LiDAR?
Two hot technologies these days are artificial intelligence (AI) and self-driving cars. One of the sensors used with the latter is the radar. Oculii is a company merging machine learning and radar to deliver a more efficient solution to car navigation and obstacle avoidance.
I spoke with Steven Hong, CEO/co-founder of Oculii, about their software platform.
What does your business do?
Oculii creates a next-generation AI software platform for radars that delivers significantly higher resolution, longer range, more accuracy and lower cost than conventional solutions, increasing safety and reliability. The promise of autonomous vehicles depends on high-performance, all-weather, inexpensive and scalable perception technology, and Oculii is bringing it to the world.
What is the problem your business is trying to solve?
There are 6 million car accidents in the United States each year, many of which are fatal. Moreover, 96% of these accidents are caused in part by human error. The biggest problem we are working to solve is making safe transportation more accessible.
Current radar solutions do not meet the autonomy needs of the industry. Prior to Oculii, enabling higher levels of battery life required more cameras, which increased cost, size, and power consumption. Oculii’s software unlocks the potential of low-cost, mass-produced, market-proven commercial radars, making autonomy more accessible to everyone.
Tell us about the acquisition with Ambarella. What does this mean for your business?
Joining the Ambarella team has allowed us to expand the development of our radar technology and use Ambarella’s camera technology to create higher levels of autonomy for Tier 1s and automotive OEMs worldwide. . Oculli’s Radar Technology Extends Ambarella’s Existing Cutting-Edge AI CV [computer vision] SoC perception for automotive and other IoT terminal applications, including mobile robotics and security.
What is the advantage of having a radar and a camera compared to one or the other?
The camera provides RBG information and is excellent for object detection, classification and sign recognition, but it significantly reduced performance in bad weather. Radar is a natural complement to cameras as it provides accurate range and Doppler data while being unaffected by weather conditions. These detection modalities naturally complement each other and, unlike LiDAR, are cost effective enough to be deployed on L2+ vehicles.
With either, more resolution could mean more power, processing, and cost. However, the combination of radar, camera and Oculii software unlocks higher resolution without sacrificing efficiency.
What does a central processing architecture enable?
With the addition of centralized processing, Oculii software can increase resolution up to 1,000 times over traditional radar.
Most systems currently use decades-old technology. Oculii’s core fusion platform allows radar data to inform camera data and vice versa for the fastest, smartest autonomous systems possible.
Compute resources in the core processing architecture scale more cost-effectively because they are housed in a single SoC. In addition, there will be reduced insurance rates for consumers since the cost of replacing the radar sensor will be lower in the event of an accident. Finally, there will be a simpler software solution: a single device requires an over-the-air update rather than multiple radar modules.
What tech trends are you most excited about?
Radar’s potential as a stand-alone navigation technology is not as widely recognized as it should be. LiDAR is the most well-known navigation system and it gets a lot of media attention due to the high number of LiDAR-focused startups.
While there are many great LiDAR companies doing great work, radar is often seen as a problem already solved. Traditionally, improving radar resolution meant adding more antennas, which increased cost, size, and power. But that was before Oculii. With Oculii’s Virtual Aperture Imaging technology, we’ve found a software solution to a hardware problem that has unlocked tremendous potential for radar.
Radar is very cost-effective, which could be a key element in driving the adoption of self-driving technology more widely. It is also extremely robust and can operate in all weather conditions.
Oculii’s software enables all the benefits of radar, plus high resolution and long-range performance. Oculii’s Virtual Aperture Imaging software platform is also continuously evolving by leveraging unique and proprietary radar data models. Future generations of sensors built with Oculii AI software will scale exponentially, delivering significantly higher resolution and longer range in a cheaper, more compact package.
Steven Hong is CEO/co-founder of Oculii, a radar software company enabling the next generation of autonomous systems. Using aperture imaging software that dynamically learns and adapts to the environment, Oculii’s exclusive Virtual Aperture Imaging Software increases the resolution of any radar hardware up to 100X .