Supervised vs. Unsupervised Learning in AI-based Autonomous Driving Solutions

Which approach is the most advantageous for implementation by OEMs and Tier-1s?

by Ilan Shaviv, Ph.D. – Imagry CTO

In the dynamic world of autonomous driving, the choice between supervised and unsupervised learning methods plays a pivotal role in shaping the capabilities and reliability of self-driving vehicles. At Imagry, our commitment to pushing the boundaries of innovation has led us to adopt a supervised learning approach, setting us apart from the unsupervised methods employed by some other players in the industry.

Let’s delve into the nuances of these two approaches and explore why Imagry’s emphasis on supervised learning is a game-changer.

Supervised vs. Unsupervised Learning: A Fundamental Distinction

The fundamental difference between supervised and unsupervised learning lies in the utilization of labeled training data. In an unsupervised learning approach, the vehicle relies on actual driving experiences by human drivers and perception of the world, deriving patterns and relationships automatically. A prominent example of this is Tesla’s “unsupervised learning” method, where data from participating vehicles is collected over the cloud to continuously train their self-driving option. However, this approach may lead to imperfect learning, as demonstrated by instances of less-than-ideal driving behaviors observed in the unfiltered data (such as rolling “stops” at stop signs, and driving 60 in a 55 mph zone.)

In stark contrast, Imagry employs a powerful supervised learning methodology, utilizing multiple neural networks to emulate the cognitive processes and decision-making of skilled and law-abiding human drivers. This is based on extensive visual data collected continuously from 2019 (today Imagry is collecting data from demo vehicles driving autonomously on public roads in the U.S., Germany, Japan, and Israel), and annotating them consistently with a predefined policy using proprietary in-house developed software and human oversight. The neural networks learn by imitating the driving path solutions generated by human drivers and filtered for non-desirable behaviors by Imagry personnel, ensuring that the Imagry autonomous driving system aligns seamlessly with the highest driving standards.

Other Differentiators in the AI Learning Approaches

Typically, autonomous driving solutions that employ unsupervised learning techniques are based on a monolithic neural network that handles all tasks in a single, large network. This approach simplifies training and reduces effort, but it creates a big “black box” with low explainability and high maintenance complexity. The Imagry solution, on the other hand, which is comprised of two steps (perception and motion planning), uses multiple small neural networks to understand and respond to the visual cues. This modular approach, where different tasks are handled by separate networks, offers better traceability, easier maintenance, and adaptability.

Ultimately, the perception and motion planning development processes used in the Imagry solution incorporate a semi-automated approach, whereby proprietary in-house tools are used to automate and therefore speed up the labeling process. However, all data undergoes thorough human review before being integrated into the neural networks’ learning process. This emphasis on supervised learning reinforces Imagry’s dedication to precision and reliability.

Supervised Learning Workflow for AI Based Autonomous Driving


Comparison Table: Different Data Training Methods for AI-based Autonomous Driving

Aspect Unsupervised Supervised
Data Type Unlabeled data, where the model finds patterns without labels
play Labeled data, where each input has a corresponding output label
Learning Approach Models learn to identify patterns and structures in data without predefined labels
play Trains models by using labeled data to map inputs to desired outputs
Training Process Data is collected and processed autonomously to find patterns
play Data is collected, labeled by humans, and used to train the model
Neural Network Structure Monolithic, single large network handling all tasks
play Multiple smaller, modular networks handling specific tasks
Traceability and Maintenance Lower traceability, as the model’s decisions are based on patterns it identified without explicit labeling
play Higher traceability and easier to debug, as the model's decisions can be traced back to specific labeled data
Computing Power Requires powerful systems (lots of TOPS) to process data, due to large data samples
play Less powerful systems (i.e., more economical) required, due to data sample size
Latency Due to large data processing requirement, more latency introduced
play Data in modular neural networks is processed simultaneously, resulting in less latency
Safety/Reliability Risk of imperfect learning from unfiltered, real-world data (i.e., bad drivers)
play Ensures adherence to traffic laws and high driving standards
Imagry's unwavering commitment to advancing autonomous driving technology through the integration of AI-driven solutions stands as a testament to our dedication to safety, reliability, and innovation.

By embracing a supervised learning methodology, we bridge the gap between human expertise and machine intelligence, ensuring our autonomous driving system mirrors the precision and adherence to standards demonstrated by skilled human drivers.

As we continue to push the boundaries of the autonomous vehicle industry, Imagry remains at the forefront, driving towards a future where AI-enhanced technologies redefine the landscape of transportation, making roads safer and transportation more efficient for everyone.
Watch how it works play

Next stop, full autonomy!

Are you coming? Got a question for us?

    Company Locations

    Imagry, Inc.
    1630 Old Oakland Rd.
    Suite #A112
    San Jose CA 95131
    USA
    Imagry (Israel) Ltd.
    53 Derekh HaAtsma'ut
    3rd Floor
    Haifa 3303327
    Israel

    Accessibility Toolbar