via University of Oxford
Researchers at Oxford University’s Department of Computer Science, in collaboration with colleagues from Bogazici University, Turkey, have developed a novel artificial intelligence (AI) system to enable autonomous vehicles (AVs) to achieve safer and more reliable navigation capability, especially under adverse weather conditions.
Yasin Almalioglu, who completed the research as part of his DPhil in the Department of Computer Science, said: ‘The difficulty for AVs to achieve precise positioning during challenging adverse weather is a major reason why these have been limited to relatively small-scale trials up to now. For instance, weather such as rain, fog, or snow may cause an AV to detect itself in the wrong lane before a turn, or to stop too late at an intersection because of imprecise positioning.’
To overcome this problem, Almalioglu and his colleagues developed a novel, self-supervised deep learning model for ego-motion estimation, a crucial component of an AV’s driving system that estimates the car’s moving position relative to objects observed from the car itself. The model brought together richly-detailed information from visual sensors (which can be disrupted by adverse conditions) with data from weather-immune sources (such as radar), so that the benefits of each can be used under different weather conditions.
The model was trained using several publicly available AV datasets which included data from multiple sensors such as cameras, lidar, and radar under diverse settings, including variable light/darkness and precipitation. These were used to generate algorithms to reconstruct scene geometry and calculate the car’s position from novel data. Under various test situations, the researchers demonstrated that the model showed robust all-weather performance, including conditions of rain, fog, and snow, as well as day and night.
Estimating the precise location of AVs is a critical milestone to achieving reliable autonomous driving under challenging conditions. This study effectively exploits the complementary aspects of different sensors to help AVs navigate in difficult daily scenarios
Professor Andrew Markham, Department of Computer Science, Oxford University
The team anticipate that this work will bring AVs one step closer to safe and smooth all-weather autonomous driving, and ultimately a broader use within societies.
Professor Niki Trigoni, from the Department of Computer Science at Oxford, who co-supervised the study with Professor Andrew Markham, said: ‘The precise positioning capability provides a basis for numerous core functionalities of AVs such as motion planning, prediction, situational awareness, and collision avoidance. This study provides an exciting complementary solution for the AV software stack to achieve this capability.’
Original Article: Oxford researchers develop new AI to enable autonomous vehicles to adapt to challenging weather conditions
More from: University of Oxford | Bogazici University
The Latest Updates from Bing News
Go deeper with Bing News on:
Autonomous vehicles
- Shhh! 3 Secret Autonomous Driving Stocks Flying Below Wall Street’s Radar
InvestorPlace - Stock Market News, Stock Advice & Trading Tips While a high-risk, high-reward sector, autonomous driving stocks represent a ...
- Buckle Up for Change: How Tech is Transforming Car Accident Claims
Fender bender? Buckle up, because the way car accident claims are handled is about to undergo a major overhaul. Technology is rapidly changing the landscape of personal injury law, and its impact on ...
- The main reason why self-driving cars are not ready for prime time
"It's like trying to send a rocket to the moon in 1910 when the Wright Brothers were still working on their planes," one expert said.
- This highly reflective black paint makes objects more visible to autonomous cars
Self-driving cars could soon become better night drivers thanks to a new, highly reflective black paint that’s easily detectable by lidar sensors, as described in ACS Applied Materials & Interfaces.
- AI-driven race cars test limits of autonomous driverless technology
AI-driven race cars compete at the Yas Marina circuit in Abu Dhabi, a showcase of driverless autonomous technology and an advanced test bed for AI research ...
Go deeper with Bing News on:
All-weather autonomous driving
- US opens investigation into Ford crashes involving Blue Cruise partially automated driving system
Two fatal crashes involving Ford's Blue Cruise partially automated driving system have drawn the attention of U.S. auto safety regulators.
- Driverless semis will start hauling freight along Texas highways later this year
Within three or four years, Aurora and its competitors expect to put thousands self-driving trucks on America's public freeways.
- From Self-Driving Cars to Electric Vehicles: The Latest in Automotive Innovation
Buckle up, because the automotive industry is revving up with groundbreaking innovation! From self-driving cars to electric vehicles, the future of transportation is here. Join us as we take a closer ...
- The Future of Driving: Exploring the Latest Advancements in Automotive Technology
Buckle up and get ready to take a thrilling ride into the future of driving! In this blog post, we will dive deep into the latest advancements in automotive technology that are revolutionizing the way ...
- Crewless cargo? Autonomous shipping aims to overcome safety, trust concerns to reach mainstream
Major shipping firms have completed successful tests of autonomous vessels. Building trust among freight owners and regulators remains the biggest hurdle for the tech reaching primetime. A cargo ...