
The researchers’ self-driving neural network gets into very few accidents in their virtual town.
Self-driving cars are powered by machine learning algorithms that require vast amounts of driving data in order to function safely. But if self-driving cars could learn to drive in the same way that babies learn to walk – by watching others around them and trying to mimic certain movements – they would require far less data. Hariri Institute Junior Faculty Fellow Eshed Ohn-Bar, an assistant professor of electrical and computer engineering, developed an efficient, safe, and collaborative paradigm for watching and predicting other cars’ actions to train autonomous vehicles.
Ohn-Bar and Jimuyang Zhang, a PhD student in electrical and computer engineering, presented their findings recently at the 2021 Conference on Computer Vision and Pattern Recognition (CVPR 2021).
The idea for the team’s training paradigm came from a desire to increase data-sharing and cooperation among researchers. Autonomous vehicles require many hours of driving data to learn how to drive safely, and some of the world’s largest car companies keep their vast data private to prevent competition. “There are a lot of autonomous driving companies and each company goes through the same process of taking cars, putting sensors on them, paying drivers to drive the vehicles, collecting data, and teaching the cars to drive,” said Ohn-Bar. Sharing driving data could help companies create safe autonomous vehicles faster, allowing everyone in society to benefit from the cooperation. Ohn-Bar highlights that no one company can solve this problem today on their own because current AI systems require so much data to work well. “Billions of miles are just a drop in an ocean of real-world events and diversity. Yet, a missing data sample could lead to unsafe behavior and a potential crash, and billions of miles are just a drop in an ocean of real-world events and diversity,” Ohn-Bar said.
The researchers’ proposed machine learning algorithm leverages data from other cars. The algorithm estimates the viewpoints and blind spots of other cars in the area to create a map that has a bird’s eye view of the surrounding environment. These maps help self-driving cars detect obstacles, like other cars or pedestrians, and can be used to understand how the other cars turn, negotiate, and yield without crashing into anything. A self-driving neural network is then trained by translating the actions of surrounding vehicles into the autonomous vehicle’s own frame of reference. These other cars may be human-driven vehicles without any sensors, or another company’s auto-piloted vehicles. Since observations from all of the surrounding cars in a scene are central to the algorithm’s training, this “learning by watching” paradigm encourages data sharing, and consequently safer autonomous vehicles.
Ohn-Bar and Zhang tested their self-driving cars in two virtual towns — one with straightforward turns and obstacles similar to their training environment, and another with unexpected twists like five-way intersections. In both scenarios, the researchers found that their self-driving neural network gets into very few accidents. With just one hour of driving data to train the machine learning algorithm, the autonomous vehicles arrived safely at their destinations 92 percent of the time. “While previous best methods required hours, we were surprised that our method could learn to drive safely with just ten minutes of driving data,” said Ohn-Bar.
While these results are promising, Ohn-Bar said that there are still several open challenges in dealing with intricate urban settings. “Accounting for drastically varying perspectives across the watched vehicles, noise and occlusion in sensor measurements, and various drivers is very difficult,” said Ohn-Bar.
The team’s paradigm for teaching autonomous vehicles how to self-drive could be used in other technologies as well. “This machine learning paradigm can be applied to many other systems,” said Ohn-Bar, “Delivery robots or even drones could all learn by watching other AI systems in their environment.”
Original Article: Cars that learn how to drive themselves by watching other cars
More from: Boston University
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Training autonomous vehicles
- Do autonomous vehicle drivers need to keep hands on wheel?
Question: I was wondering, with the ads on television showing people driving with their hands off the steering wheel, is that legal in Minnesota if your vehicle has that capability? Answer: I believe ...
- From Self-Driving Cars To Military Surveillance: Quantum Computing Can Help Secure The Future Of AI Systems
Artificial intelligence algorithms are quickly becoming a part of everyday life. Many systems that require strong security are either already underp ...
- Waymo's autonomous vehicles to be available on Uber app under new partnership in Phoenix
Autonomous vehicle partnerships have become increasingly common in recent years in Houston as well as places like Phoenix, where Uber is teaming up with Waymo.
- Israeli startups show autonomous driving, sensors technology at EcoMotion
Automotive and mobility technology startups are flourishing in Israel, gaining investment from automakers and major suppliers.
- Remote human operators: Enhancing the safety of autonomous vehicles
Autonomous vehicles can handle simpler tasks by adopting a hybrid system with remote human operators, improving passenger safety and boosting efficiency.
Go deeper with Google Headlines on:
Training autonomous vehicles
[google_news title=”” keyword=”training autonomous vehicles” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Self-driving cars
- Ferrari on self-driving cars: ‘We don't care'
The ultraluxury brand doesn't plan to make software that will take over for the driver but is working toward releasing an EV by 2025.
- Tesla Whistleblower Leaks 100GB Data Of Customer Complaints Against Self-Driving Cars
Despite several concerns, Elon Musk-run Tesla made its Full Self-Driving (FSD) beta self-driving features available to all its car owner.
- We’re still waiting for self-driving cars, but autonomous boats are already here
In 2016, Lyft predicted that most of its rides would be self-driving by 2021, while in 2017, General Motors said it would be mass producing fully autonomous vehicles even sooner. But creating a car ...
- From self-driving cars to military surveillance: quantum computing can help secure the future of AI systems
People can even carry out such attacks from the physical world. Someone could put a sticker on a stop sign to fool a self-driving car’s AI into identifying it as a speed-limit sign. Or, on the front ...
- Uber teams up with Google’s Waymo on self-driving cars
Google sister company Waymo signed a deal with Uber to bring its self-driving cars to the app, a major development in the slow march towards robotaxis.
Go deeper with Google Headlines on:
Self-driving cars
[google_news title=”” keyword=”self-driving cars” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]