Articles tagged with Autonomous Vehicles
A recent study by Washington State University researchers found that trust in autonomous vehicles' reliability and performance plays a crucial role in improving perceptions of the technology's risk. Knowledge alone is insufficient to sway people's attitudes toward complex technology like autonomous vehicles.
A new partnership has developed a functional safety sensing platform based on 3D ultrasound, providing an additional layer of safety and reliability for autonomous vehicles. The technology complements existing systems and enables vehicles to detect their surroundings in real-time, even in extreme conditions.
Researchers developed a technique called Multi-View Attentive Contextualization (MvACon) to improve AI's ability to map 3D spaces using 2D images from multiple cameras. MvACon significantly improved the performance of vision transformers in locating objects and detecting speed and orientation.
Researchers have developed a system combining bio-inspired cameras with AI to quickly detect obstacles around cars, using less computational power. The hybrid system detects objects up to one hundred times faster than current systems while reducing data transmission and processing needs.
Researchers studied how pre-teen children determined when it was safe to cross a residential street with self-driving cars. Children made safer choices when the light turned green later and the vehicle stopped at the crossing point, treating it like a walk light and waiting for clearance.
Researchers at Bar-Ilan University developed a new AI confidence measure that distinguishes between high- and low-confidence decision making in deep learning architectures. This breakthrough enables the creation of safer and more reliable autonomous vehicles by prioritizing human intervention when confidence levels are lower.
A study proposes a safe motion planning and control (SMPAC) framework to address safety of the intended functionality (SOTIF) challenges in automated driving. The framework leverages set theory, robust control theory, and reachability analysis to enhance SOTIF under multi-dimensional uncertainties.
Researchers at University of Missouri are developing software that allows drones to fly independently, perceiving and interacting with their environment while achieving specific goals. This technology has the potential to assist in mapping and monitoring applications, such as 3D or 4D advanced imagery for disaster response.
A new traffic signal concept, known as the 'white phase,' uses autonomous vehicles to expedite traffic flow at intersections. The concept has been shown to improve travel time for both pedestrians and vehicles, especially when autonomous vehicles make up a higher percentage of traffic.
Scientists from Tokyo Tech propose two design techniques to minimize unwanted signals known as fractional spurs, which degrade phase noise in output of the PLL. The first technique uses a cascaded-fractional divider and achieves a -62.1dBc fractional spur, while the second technique employs a pseudo-differential DTC, resulting in an in...
Researchers at Duke University create a system called MadRadar that can trick automotive radar sensors into believing anything is possible without prior knowledge. The technology can hide existing cars, create phantom vehicles, or make it seem like an actual car has changed course.
Researchers at George Mason University, led by Assistant Professor Pudukotai Dinakarrao, are working on a project to protect autonomous vehicle supply chains from backdoor attacks. The team aims to deploy an approach that can mitigate and avoid such attacks, with funding provided by the Virginia Innovation Partnership Authority.
Researchers studied user perceptions and requirements for remote driving in L4 AVs, highlighting the importance of clear communication and reliable teleoperation systems. The study found that users support remote driving as a failsafe mechanism but raise concerns about cybersecurity, privacy, and performance.
A new study reveals AI tools are more vulnerable than thought to targeted attacks that force AI systems to make bad decisions. Researchers developed a software called QuadAttac K to test for vulnerabilities in deep neural networks.
A team of researchers at North Carolina State University has developed a new experiment to better understand human moral judgments in traffic scenarios. The study aims to collect data for training autonomous vehicles to make
A new deep learning-based detection system has been developed by INU researchers to improve the detection capabilities of autonomous vehicles. The system, aided by IoT technology, generates bounding boxes and confidence scores for visible obstacles using point cloud data and RGB images as input.
A team led by Lehigh University's Yahong Rosa Zheng is developing an Autonomous Observatory Node that can collect and transmit data from underwater sensors wirelessly, without the need for expensive subsea cables. The prototype aims to operate at depths of up to 1000 meters, enabling researchers to study extreme environments and detect...
Researchers aim to balance technology and human needs in long-haul trucking, focusing on driver-centered design and workforce development. The project seeks to optimize the human-truck relationship through participatory design, ride-alongs, and analysis of trucker needs.
Scientists have developed a system to detect icing conditions in drones flying over the polar regions, allowing for safer and more efficient data collection. The onboard aerosol counters enable real-time detection of supercooled cloud droplets, which can damage drone components.
Researchers are working on EdgeRIC: Real-time radio access network intelligent control, aiming to enhance wireless communication and machine learning. The project involves developing intelligent systems that can adapt to changing conditions, prioritizing users and acquiring lower latency for applications.
Researchers developed MonoXiver, a new method to help AI extract 3D information from 2D images, making cameras more useful tools for emerging technologies. The method significantly improves accuracy when used in conjunction with existing techniques, such as MonoCon.
The University of Texas at Dallas will develop and commercialize new battery technologies, enhance domestic raw material availability, and train workers for the expanding battery industry. The Energy Storage Systems Campus will leverage $200 million in private capital.
A novel AI system developed by City University of Hong Kong improves predictive accuracy in dense traffic, reducing latency and increasing efficiency. QCNet achieves speed and accuracy in predicting road users' movements, even with long-term predictions, making autonomous driving safer and more human-like.
A new study published in the Journal of Safety Research found that drivers' takeover performance worsened with increasing levels of mental workload from activities such as working, watching videos, or taking a break. The study highlights the need for regulation to ensure driverless cars are safe, particularly for inexperienced drivers.
Researchers at North Carolina State University found that connected vehicles improve travel time through intersections, but automated vehicles without connectivity actually increase wait times. The study suggests that incorporating vehicle-to-vehicle and vehicle-to-infrastructure communication is crucial for optimizing traffic flow.
Researchers have proposed an innovative solution to address limitations of lidar technology, enabling imaging in low SNR environments. The novel technique uses a high-scanning speed AOD and metasurface-enhanced scanning lidar, extending ambiguity range by up to 35 times.
The VVE method allows for testing of driverless cars in a perfectly safe environment, enabling the car to learn to avoid collisions and increase pedestrian safety. By replacing high-resolution sensor output with simulated data, researchers were able to show that the autonomous driving system behaves as if it's driving on real roads.
The University of Houston's CYBER-CARE research center aims to prevent cyberattacks that could compromise the safe movement of people and goods in the US. The center will focus on four goals, including exploring advanced theories to mitigate the impact of large-scale cyberattacks.
Researchers at the University of Tokyo have developed a new navigation system using cosmic-ray muons, which can accurately determine position in underground environments. The MuWNS system uses time synchronization to achieve accuracy comparable to single-point GPS positioning aboveground.
A new approach to enhance artificial intelligence-powered computer vision technologies has been developed by UCLA researchers, adding physics-based awareness to data-driven techniques. This hybrid methodology aims to improve how AI-based machinery sense, interact, and respond to their environment in real time.
Researchers at the University of Washington have developed a multifunctional interface between photonic integrated circuits and free space, allowing for simultaneous manipulation of multiple light beams. The device operates with high accuracy and reliability, enabling applications in quantum computing, sensing, imaging, energy, and more.
A recent NC State University study examines the relationship between artificial intelligence (AI) and law enforcement. The study reveals that law enforcement agencies must be involved in developing public policies regarding AI technologies, such as autonomous vehicles. Key findings also suggest that many officers lack understanding of ...
University of Arizona engineers create a communication network allowing robots to explore subsurface environments independently, deploying miniaturized sensors as they traverse caves. The 'breadcrumb-style' system enables swarms of individual robots to navigate convoluted environments without losing contact.
Researchers have proved that a long-standing game theory dilemma does not exist in the wall pursuit game, introducing a new method of analysis that proves there is always a deterministic solution. This discovery opens doors to resolving other similar challenges and enables better reasoning about autonomous systems.
A new collaborative project led by the University of Liverpool aims to investigate the Gulf Stream's role in transporting nutrients and carbon, and its effect on the ocean's carbon uptake. The four-year programme will use cutting-edge sensors and models to better understand how the Gulf Stream influences climate change.
University of Arizona engineers create autonomous vehicle system that allows robots to scout out underground habitats on other planets. The 'Breadcrumb-Style Dynamically Deployed Communication Network' paradigm enables robots to work together without human input, addressing NASA's space technology grand challenges.
Researchers at MIT developed a technique to improve machine-learning models' reliability without requiring additional data or extensive computing resources. The method uses a simpler companion model to estimate uncertainty, enabling more effective uncertainty quantification.
A new approach, called the white phase concept, uses autonomous vehicles to control traffic flow at intersections, reducing fuel consumption and travel time. The system informs human drivers through a clearly identifiable signal, improving safety and efficiency.
Researchers developed an ethical algorithm to distribute risk fairly in autonomous vehicles, considering multiple factors such as responsibility and traffic regulations. The new approach enables more nuanced decision-making in critical situations, weighing risks and avoiding aggressive maneuvers.
Researchers developed a haptics-based automated driving system that encourages continuous engagement between drivers and automation. The system achieves this through three functionalities: interaction, arbitration, and inclusion, resulting in increased safety and comfort for human drivers.
The MEDA instrument aboard the Perseverance rover has provided high-precision meteorological measurements of Mars' atmosphere, revealing seasonal and daily cycles as well as dynamic phenomena like dust devils. The analysis sheds light on the Martian climate and its potential for supporting life.
A new study finds that autonomous vehicles could consume enough energy to generate significant greenhouse gas emissions, highlighting the need for rapid advancements in hardware efficiency. To mitigate this, researchers recommend more efficient autonomous vehicles with smaller carbon footprints.
The three-year effort aims to establish a widely accepted protocol for comparing lidar performance. The first year's tests evaluated range, accuracy, and precision of eight automotive-grade lidars using a survey-grade reference. Results showed the distribution of measured values was not Gaussian, with significant errors in some cases.
Researchers at Incheon National University have developed an IoT-enabled, real-time object detection system for autonomous vehicles. The YOLOv3-based model achieved high accuracy (>96%) in detecting 2D and 3D objects, outperforming other state-of-the-art detection models.
Researchers at Purdue University are designing autonomous vehicles that can accommodate people with disabilities. Their goal is to create a standard for technology accessibility that will enable the entire population to use these vehicles, regardless of their mobility or sensory challenges.
Researchers have demonstrated a power-efficient component for demultiplexing operation using silicon photonic MEMS, enabling efficient wavelength demultiplexing for fiber-optic communications. The compact footprint of the add-drop filter allows fast operation compared to established MEMS products.
Researchers at Purdue University and the University of Tennessee, Knoxville, have developed a metamaterial that can learn to adapt to its surroundings on its own. The material uses shape to store information in microseconds, allowing drones to quickly recall patterns associated with dangerous conditions.
A new study at the University of Tokyo suggests that robotic eyes on autonomous vehicles can help pedestrians anticipate a vehicle's intentions, leading to safer crossings. The experiment found that participants made more cautious decisions when faced with moving eyes, with some males even reporting feeling safer.
Researchers developed a silicon photodiode array for in-sensor processing, allowing for real-time image filtering and extraction of relevant visual information. The technology has potential applications in machine vision, bio-inspired systems, and intelligent imaging devices.
Researchers at NC State University have developed a cooperative distributed algorithm that allows autonomous vehicle software to make calculations more quickly, enabling real-time navigation of complex merging scenarios. The approach improves both traffic flow and safety, with zero incidents in simulations.
A recent study published in Nature Scientific Reports has found that women are better at taking over control of automated cars compared to men. The research involved 76 drivers who participated in a driving simulator study and showed that women exhibited faster reaction times and more stable operation of the steering wheel.
The Impact Acceleration Account supports critical early-stage translation of UK research to transform public services, create new businesses, and jobs. The programme provides funding to unlock the value of UK research, including commercialisation of new technologies.
A new AI system uses artificial neural networks to recognize objects more accurately and stably, despite changing visual inputs. The system mimics human eye movements to improve machine vision capabilities, reducing errors in self-driving cars and other applications.
A new optimization tool can quickly improve performance of various autonomous systems, including walking robots and self-driving vehicles. The tool uses automatic differentiation to identify tweaks that achieve desired outcomes, reducing trial-and-error simulations.
Researchers from Carnegie Mellon University gathered data on an all-terrain vehicle's interactions with challenging off-road environments, collecting over 200,000 real-world interactions. The resulting TartanDrive dataset is multimodal and includes information about speed, suspension shock travel, and video.
Researchers at MIT developed a technique that enables an autonomous vehicle to plot a provably safe trajectory in highly uncertain situations. The algorithm considers probability of observing different environmental conditions and obstacles, and formulates trajectory planning as a probabilistic optimization problem.
A new study demonstrates a machine-learning approach that can learn to control a fleet of autonomous vehicles as they approach and travel through a signalized intersection. The technique reduces fuel consumption and emissions while improving average vehicle speed, with benefits seen even when only 25% of cars use the control algorithm.
Researchers at Stevens Institute of Technology developed an underwater robot capable of mapping its environment, tracking its location, and planning safe routes in complex marine environments. The breakthrough enabled the robot to accurately map a busy harbor in real-time using active SLAM algorithms.
Researchers at Tokyo University of Science propose two new search strategies to reduce the computational cost of rebalancing in bicycle-sharing systems. The approaches focus on finding feasible solutions more efficiently and redefine the problem to minimize solving time.
Researchers at Duke University have demonstrated a new attack strategy that can deceive industry-standard autonomous vehicle sensors into believing nearby objects are closer or further than they appear. This vulnerability highlights the need for additional redundancy and data sharing between vehicles to protect against such attacks.