'An autonomous vehicle is able to navigate city streets and other less-busy environments by recognizing pedestrians, other vehicles, obstacle
PublishedResearchers at Cornell University have developed a way to help autonomous vehicles create “memories” of previous experiences and use them in future navigation, especially during adverse weather conditions when the car cannot safely rely on its sensors.
Cars using artificial neural networks have no memory of the past and are in a constant state of seeing the world for the first time — no matter how many times they’ve driven down a particular road before. The researchers have produced three concurrent papers with the goal of overcoming this limitation. Two are being presented at the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , being held June 19–24 in New Orleans.Kilian Weinberger , professor of computer science. “For example, a car may mistake a weirdly shaped tree for a pedestrian the first time its laser scanner perceives it from a distance, but once it is close enough, the object category will become clear. So, the second time you drive past the very same tree, even in fog or snow, you would hope that the car has now learned to recognize it correctly.” Spearheaded by doctoral student Carlos Diaz-Ruiz, the group compiled a dataset by driving a car equipped with LiDAR sensors repeatedly along a 15-kilometer loop in and around Ithaca, 40 times over an 18-month period. The traversals capture varying environments , weather conditions and times of day. This resulting dataset has more than 600,000 scenes. “It deliberately exposes one of the key challenges in self-driving cars: poor weather conditions,” said Diaz-Ruiz. “If the street is covered by snow, humans can rely on memories, but without memories a neural network is heavily disadvantaged.” HINDSIGHT is an approach that uses neural networks to compute descriptors of objects as the car passes them. It then compresses these descriptions, which the group has dubbed SQuaSH features, and stores them on a virtual map, like a “memory” stored in a human brain. The next time the self-driving car traverses the same location, it can query the local SQuaSH database of every LiDAR point along the route and “remember” what it learned last time. The database is continuously updated and shared across vehicles, thus enriching the information available to perform recognition. “This information can be added as features to any LiDAR-based 3D object detector;” said doctoral student Yurong You. “Both the detector and the SQuaSH representation can be trained jointly without any additional supervision, or human annotation, which is time- and labor-intensive.” HINDSIGHT is a precursor to additional research the team is conducting, MODEST , that would go even further, allowing the car to learn the entire perception pipeline from scratch. While HINDSIGHT still assumes that the artificial neural network is already trained to detect objects and augments it with the capability to create memories, MODEST assumes the artificial neural network in the vehicle has never been exposed to any objects or streets at all. Through multiple traversals of the same route, it can learn what parts of the environment are stationary and which are moving objects. Slowly it teaches itself what constitutes other traffic participants and what is safe to ignore. The algorithm can then detect these objects reliably — even on roads that were not part of the initial repeated traversals. The researchers hope the approaches could drastically reduce the development cost of autonomous vehicles and make such vehicles more efficient by learning to navigate the locations in which they are used the most.
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Toyota Recalls Electric SUVs over 'Embarrassing' Self-Detaching WheelsToyota has recalled more than 2,000 all-electric SUVs over problems that could cause the wheels or axles to detach from the vehicle, warning drivers if that happened it could “result in a loss of vehicle control, increasing the risk of a crash.”
Read more »
What sea cucumbers can teach us about self-defenseGenome mining techniques have helped to explain how sea cucumbers produce defensive chemicals that enable them to fend off foes in the murky depths.
Read more »
Self-Determination Has Been Wrenched Away From Half the US PopulationFor the first time in U.S. history, the Supreme Court has retracted a fundamental constitutional right.
Read more »
CoinDesk Podcast Network: BREAKDOWN: The Battle for Self-Hosted Wallets on Apple Podcasts“Without the option to self custody, people would have to roll the dice and choose the custodian,” NLW says. “The Breakdown” addresses the ongoing regulatory debate surrounding self-hosted wallets.
Read more »
Area Man Considers Self Ally To Women Unless They Threaten His Status In Literally Any WayPHILADELPHIA—Calling himself a “staunch supporter” of issues ranging from equal pay to reproductive rights, area man Brian MacKinnon told reporters Monday he considers himself an ally to women unless they threaten his personal status in any way whatsoever. “I would definitely describe myself as a feminist [insofar as…
Read more »
Jayda Cheaves: A True Self-Made MogulThe influencer leveraged her cult-like following to create a million-dollar empire.
Read more »