ARCHETYPE AI

0

How Soarchain Is Making Roads Safer With Physical AI

Archetype AI Team
  • August 13, 2024

Imagine a world where your car doesn’t just respond to what you can see but to what every vehicle, traffic light, and pedestrian smartphone in the vicinity can detect. 

That is what Soarchain is building toward using Archetype AI. Soarchain is pairing their decentralized connectivity platform with Newton using Archetype AI’s developer API to revolutionize road safety. Together, we will give drivers and autonomous vehicles a rich real time understanding of what’s happening on the roads around them.

In 2023 alone, 1.19 million lives were lost in road traffic incidents globally. Road traffic injuries are the leading cause of death of children and young adults, and more than half of fatalities are pedestrians, cyclists, and motorcyclists.

Despite global efforts and significant investments – such as the World Bank’s $3.34 billion commitment over the past decade – road deaths have barely reduced. With 1.5 billion (and climbing) vehicles on the road, initiatives and traditional measures alone won’t suffice. It needs new technology that can reduce road deaths while optimizing traffic to make roads more efficient.

The combination of Archetype AI's physical AI and Soarchain's decentralized platform has the potential to create a dynamic, interconnected road ecosystem that orchestrates and adapts itself to real time conditions. The potential impact is profound: fewer accidents, reduced traffic fatalities, and more efficient transportation networks.

Navigation mobile app built on Soarchain

Soarchain—a decentralized connectivity layer for vehicles

Modern vehicles are sensor platforms. Equipped with cameras, radars, GPS, and accelerometers, vehicles now produce vast amounts of data about their status, performance, and interactions with the road.

This data remains largely untapped. While a vehicle's software powers basic functions like cruise control and diagnostics, its potential to improve overall road safety and traffic efficiency at a large scale remains unrealized.

Soarchain’s platform unlocks this potential through vehicle-to-everything (V2X) communication. With V2X, vehicles can securely share data across a network, transforming isolated data points into a comprehensive web of data that provides real-time insights into road conditions, traffic patterns, and potential hazards.

V2X enables networked intelligence and connected mobility by allowing each vehicle on the network to enhance the awareness and safety of all the others, making every vehicle smarter, more aware, and better equipped to contribute to improving road safety.

Having the data on Soarchain’s network isn’t enough. It needs to be combined with intelligence, in the form of an AI model that can understand the physical world through sensor data, responding to road conditions, traffic patterns, and potential hazards in real time. The network needs Newton.

Navigation mobile app with live alert notifications, built on Soarchain

Archetype AI–adding Newton to the roads

Soarchain chose Archetype AI not just for Newton’s capabilities, but for its straightforward developer API, which simplifies the creation of physical AI applications. As Amir Khoshbakht, lead full stack engineer at Soarchain says, “The Newton API is] very straightforward and simple...and very fast."

Using Newton, Soarchain has rapidly prototyped, iterated, and deployed advanced road safety featuress. To start, a mobile road incidents detection app is built on Soarchain — akin to an automated version of Waze — that uses Newton to build a real time map of road hazards to route drivers more safely and efficiently.

The app captures visual data through smartphones mounted on dashboards. Soarchain’s app then provides the visual road data to Newton’s API via Soarchain’s mobility network where itanalyzes these images in real time to detect road conditions, traffic, and potential hazards. 

What sets Newton apart is its ability to understand behaviors, not just objects. It goes beyond visual language models that translate images into text to truly understand the underlying behavior the images represent. This is why Archetype AI calls Newton a Large Behavior Model (or LBM). It is able to follow pedestrians, cyclists, and motorcyclists, as well as cars, recognizing dangerous driving patterns and areas like construction zones.

This takes it beyond simple “AI driving”. Newton understands how vehicles, pedestrians, and crowds behave and directs drivers accordingly. In the short-term, Soarchain’s Newton-based app can help improve road safety. In the long-term, Soarchain’s Newton-based solutions can dramatically change how people and autonomous vehicles drive.

Newton: Enhancing highway safety with real time unsafe driving detection. (Example dashboard camera video from YouTube.)

How Soarchain and Archetype AI are improving road safety

Working together, Soarchain and Archetype AI want to significantly reduce road fatalities. Progress can be made using physical AI to understand and act on Soarchain’s wealth of V2X data:

  • Early road hazard detection. This system could quickly identify and alert users to potential dangers ahead such as stopped cars, potholes, road works, accidents, or adverse weather conditions. This early warning system allows drivers to adjust their speed and driving behavior well in advance, reducing the risk of sudden maneuvers or collisions.
  • Real-time traffic optimization. Traffic patterns can be analyzed to suggest optimal routes and reduce congestion. The network can distribute traffic more evenly across routes and decrease the density of vehicles in a given area, lowering the probability of multi-vehicle accidents and creating safer conditions for pedestrians and cyclists.
  • Enhanced autonomous vehicle communication. Better coordination can be facilitated between self-driving cars and human drivers. The network’s intelligence can allow self-driving vehicles to make more informed decisions, enhancing their ability to navigate complex traffic situations safely. Human drivers can have their awareness extended to any road hazards perceived by the self-driving vehicles around them.
  • Predictive maintenance for vehicles. Beyond visual data from smartphones, Soarchain’s mobillty network can be used with vehicles’ own telemetry data. Newton’s time series sensor understanding could be used to analyze telemetry data and predict potential mechanical issues before they become serious problems. Ensuring vehicles are in optimal condition reduces the risk of accidents caused by vehicle malfunctions, such as brake failures or tire blowouts, thereby contributing to overall road safety for all drivers and passengers.
Behind the scenes of the API: real time location and road description from dashboard camera feed

Beyond road safety

While improving road safety is the primary goal, the benefits of integrating physical AI extend further. Optimized traffic flows can lead to reduced carbon emissions, shorter commute, lower vehicle costs and smarter urban planning. All these can come from the integration of physical AI into vehicle sensor networks.

Soarchain and Archetype AI are pioneering what is now becoming possible. With Archetype AI's Newton foundation model and developer API, Soarchain can bring intelligence to its V2X sensor data network to revolutionize road safety and efficiency.

If you want to learn more about Newton and Archetype AI’s work on physical AI, you can reach out to the team here. If you want to learn more about V2X and AI, check out Soarchain’s solution here

Drive safe.

Recommended posts

Implementing AI in industrial settings comes with significant challenges like ensuring employee safety, estimating productivity, and monitoring hazards—all requiring real-time processing. However, sending sensor data to the cloud for analysis introduces latency and security concerns, driving up costs. The solution? Eliminate the cloud. With Archetype AI’s Newton foundation model, AI can run on local machines using a single off-the-shelf GPU, delivering low latency, high security, and reduced costs in environments like manufacturing, logistics, transportation, and construction.

September 5, 2024

At Archetype, we want to use AI to solve real world problems by empowering organizations to build for their own use cases. We aren’t building verticalized solutions –instead, we want to give engineers, developers, and companies the AI tools and platform they need to create their own solutions in the physical world.

In a world where devices constantly collect and transmit data, many organizations struggle to harness its potential. At Archetype AI, we believe AI is the key to transforming this raw data into actionable insights. Join us as we explore how the convergence of sensors and AI can help us better understand the world around us.

August 26, 2024