The technology uses sensors and cameras to capture surrounding conditions and records status data for the vehicle such as the steering wheel angle, road conditions, weather, visibility and speed. The AI system learns to recognize patterns with the data.
Image: Taras Makarenko / Pexels
New early warning system for self-driving cars
A team of researchers at the Technical University of Munich (TUM) has developed a new early warning system for vehicles that uses artificial intelligence to learn from thousands of real traffic situations. A study of the system was carried out in cooperation with the BMW Group. The results show that, if used in today’s self-driving vehicles, it can warn seven seconds in advance against potentially critical situations that the cars cannot handle alone – with over 85% accuracy.
To make self-driving cars safe in the future, development efforts often rely on sophisticated models aimed at giving cars the ability to analyze the behavior of all traffic participants. But what happens if the models are not yet capable of handling some complex or unforeseen situations?
A team working with Prof. Eckehard Steinbach, who holds the Chair of Media Technology and is a member of the Board of Directors of the Munich School of Robotics and Machine Intelligence (MSRM) at TUM, is taking a new approach. Thanks to artificial intelligence (AI), their system can learn from past situations where self-driving test vehicles were pushed to their limits in real-world road traffic. Those are situations where a human driver takes over – either because the car signals the need for intervention or because the driver decides to intervene for safety reasons.
Pattern recognition through RNN
The technology uses sensors and cameras to capture surrounding conditions and records status data for the vehicle such as the steering wheel angle, road conditions, weather, visibility and speed. The AI system, based on a recurrent neural network (RNN), learns to recognize patterns with the data. If the system spots a pattern in a new driving situation that the control system was unable to handle in the past, the driver will be warned in advance of a possible critical situation.
“To make vehicles more autonomous, many existing methods study what the cars now understand about traffic and then try to improve the models used by them. The big advantage of our technology: we completely ignore what the car thinks. Instead we limit ourselves to the data based on what actually happens and look for patterns,” says Steinbach. “In this way, the AI discovers potentially critical situations that models may not be capable of recognizing, or have yet to discover. Our system therefore offers a safety function that knows when and where the cars have weaknesses.”
Warnings up to seven seconds in advance
The team of researchers tested the technology with the BMW Group and its autonomous development vehicles on public roads and analyzed around 2500 situations where the driver had to intervene. The study showed that the AI is already capable of predicting potentially critical situations with better than 85 percent accuracy – up to seven seconds before they occur.
Collecting data with no extra effort
For the technology to function, large quantities of data are needed. After all, the AI can only recognize and predict experiences at the limits of the system if the situations were seen before. With the large number of development vehicles on the road, the data was practically generated by itself, says Christopher Kuhn, one of the authors of the study: “Every time a potentially critical situation comes up on a test drive, we end up with a new training example.” The central storage of the data makes it possible for every vehicle to learn from all of the data recorded across the entire fleet.
Original Article: New early warning system for self-driving cars
More from: Technical University of Munich
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Early warning system for self-driving cars
- 2024 Tesla Model Y vs. 2024 Hyundai Ioniq 5 Comparison
Despite their differences, the Hyundai Ioniq 5 and Tesla Model Y present compelling options in the hotly competitive compact crossover EV segment. Here is how they compare.
- Inside the Autonomous Racing League event that pitted a self-driving car against a Formula 1 driver
Some teams, like the Indianapolis-based Code19, only started work on the monumental project of creating a self-driving car a few months ago ... but had to learn C++ to write the team’s antilock ...
- U.S. regulator says self-driving vehicles not ready for prime time as Tesla inks China deal
Even as big-name automakers are pushing the accelerator on full self-driving, reports have highlighted serious risks in Tesla's and Ford's technology.
- Self-driving tractor-trailers heading for U.S. roads
The self-driving semi, outfitted with 25 laser ... But in less than nine months, trucks with Aurora’s systems will start carrying loads between terminals for FedEx, Uber Freight, Werner and others.
- NHTSA to investigate fatal crashes involving self-driving Ford Mustang Mach-E
The NHTSA announced an investigation into the self-driving Ford Mustang Mach-E after two accidents resulting in fatalities.
Go deeper with Google Headlines on:
Early warning system for self-driving cars
[google_news title=”” keyword=”early warning system for self-driving cars” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Predicting critical traffic situations
- Tuning into the Flourishing Sector of Performance Audio
Industry experts reveal Performance Audio to be a thriving category, with notable strides in immersive audio & audio-over-IP technologies.
- Tornadoes & AI: How AI Is Changing Weather Forecasting
The Intelligent Tornado Prediction Engine is a new development by the Air Traffic Control Systems Climate Change Technology for National Security. It uses deep learning models to detect and predict ...
- An AI dataset carves new paths to tornado detection
The return of spring in the Northern Hemisphere touches off tornado season. A tornado's twisting funnel of dust and debris seems an unmistakable sight. But that sight can be obscured to radar, the ...
- Conroe faces 'critical infrastructure' issues as the Houston suburb's growth continues to explode
We are in a pretty tough situation ... “We are triaging critical infrastructure projects as we speak.” McGuire said the water issues will likely increase this summer. “(Weather officials) are ...
- Here’s How Artificial Intelligence Is Going To Transform The Driver/Car Relationship
Artificial intelligence is redefining how we interact with our cars. Let us take a look at how AI is going to transform the driver/car relationship.
Go deeper with Google Headlines on:
Predicting critical traffic situations
[google_news title=”” keyword=”predicting critical traffic situations” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]