Articles tagged with Autonomous Vehicles
A Norwegian University of Science and Technology study highlights seafarers' concerns about autonomous ships' technical safety, trust in technology, and crew competence. The researchers aim to ensure safer use of advanced technology and increase seafarers' trust in autonomy by addressing the challenges highlighted by the seafarers.
Researchers developed photonic computing chips that enable fast, all-optical learning and decision making, overcoming key limitations for photonic spiking neural systems. The new chips could improve autonomous driving technologies and enable robotic systems that learn through real-world interactions.
A groundbreaking system repurposes a vehicle's taillight as an LED matrix transmitter to enable data transmission between vehicles in platoons. The approach eliminates the need for roadside units or photodetectors, offering a secure and low-cost solution for V2V communication.
Roadside radar sensors like EyeDAR enhance automotive radar systems by capturing reflections from obstacles, reducing blind spots and improving sensing accuracy. This technology has potential applications in robots, drones, and wearable platforms, complementing artificial intelligence with analog design.
Researchers from UC Irvine have discovered a critical security vulnerability in autonomous target-tracking drones that can be exploited using an ordinary umbrella. The team demonstrated how attackers could use the 'FlyTrap' attack framework to manipulate drones, drawing them close enough for capture or causing them to crash.
The article highlights the psychological demands of self-driving cars on human brains, citing Professor McLeod's research and personal experience. He emphasizes the need for clearer interfaces, simulation-based training, and updated driving tests to address these challenges and ensure safe automation uptake across society.
The Advanced Driving Simulation Center enables researchers to realistically test and optimize vehicles, chassis, and advanced driver assistance systems. The simulator's high bandwidth generates fine vibrations, crucial for optimizing electric vehicle comfort.
The COMET project AutoForst aims to increase safety, alleviate labor shortages, and improve forest logistics with digital and automated systems. Researchers will develop sensor and camera systems to recognize critical situations during loading and automate transport systems.
Researchers developed a multi-dimensional analysis model to understand self-driving vehicles' behavior, incorporating perceptual and behavioral intelligence. The model enables rigorous evaluation of interactive cognition abilities, supporting human-vehicle-friendly interaction and fostering public trust.
A breakthrough AI system called OmniPredict can predict human pedestrian behaviors with unprecedented accuracy, revolutionizing self-driving cars and urban mobility. The model combines visual cues with contextual information to anticipate pedestrians' next moves, reducing the risk of accidents and improving traffic safety.
Researchers developed a socially aware prediction-to-control pipeline to enable autonomous vehicles to safely weave through dense crowds. The integrated framework achieved zero safety violations and maintained comfortable motion while meeting real-time computing limits.
Researchers developed a drone-aided mobile blood collection system to transport donated blood in cities. The model uses drones to shuttle between bloodmobiles and a central blood centre, eliminating traffic delays and ensuring fresh blood reaches the lab quickly.
A team of researchers at the University of Waterloo developed a framework that uses mathematical tools and machine learning to rigorously check and verify the safety of AI-driven systems. The framework has been tested on challenging control problems and matched or exceeded traditional approaches.
The £250 million investment will create an Advanced Marine Technology Hub at the University of Plymouth, leveraging its expertise in autonomous marine systems, maritime cyber security, and renewable energy. This initiative aims to boost the city's economy and enhance UK's national resilience.
A large-scale modeling study led by MIT researchers reveals that dynamically adjusting vehicle speeds can cut annual city-wide intersection carbon emissions by 11-22%. Implementing eco-driving measures could also result in a 25-50% reduction in CO2 emissions if only 10% of vehicles adopt the technology.
Researchers at the University of Cincinnati are developing drones that can optimize wind in real time using a principle called dynamic soaring, inspired by albatrosses. The project aims to turn wind into an advantage for drones, reducing energy loss and increasing efficiency.
Researchers at the University of Rochester are developing biologically inspired predictive coding networks for digital image recognition using analog circuits, which could lead to more efficient drones. The team aims to approach the performance of existing digital approaches and translate it to complex perception tasks needed by self-d...
SwRI's award-winning NEXTCAR project successfully completed its 8-year-long connected and automated vehicle technology project. The completed SwRI NEXTCAR vehicle demonstrated up to 30% energy savings compared to traditional hybrid vehicles.
The Michigan Air Mobility Research Corridor will test advanced air mobility technologies, including battery-powered aircraft and autonomous systems. The corridor, spanning 40 miles from Ann Arbor to Detroit, aims to enable safe and efficient flight testing.
New research suggests that driving assistance systems can backfire by making drivers less attentive and increasing hazardous behaviors. The study analyzed data from over 195,000 vehicles and found that different types of warning signals trigger opposite effects on driving behavior.
Researchers developed a technique to study moral decision-making while driving, testing it on 274 philosopher participants. The results showed consistency across different philosophical schools of thought regarding what constitutes moral behavior in the context of driving.
Researchers at UMass Amherst created integrated arrays of gate-tunable silicon photodetectors that can capture dynamic visual information and classify static images with high accuracy. The technology has the potential to reduce latency in computer vision tasks, enabling applications like self-driving vehicles and bioimaging.
Researchers at MIT developed a machine learning-based adaptive control algorithm that enables autonomous drones to adapt to unknown disturbances like gusting winds. The system achieves 50% less trajectory tracking error than baseline methods in simulations.
A new study found that augmented reality can significantly increase trust in autonomous vehicles by adding, modifying or removing driving-related information. The technology uses sensors to deliver real-time data, ensuring drivers stay focused on the road while accessing critical info.
A new cognitive encoding framework enables self-driving cars to 'think' like human drivers, reducing overall traffic risk by 26.3%. This system integrates social sensitivity, allowing AVs to prioritize pedestrian protection while minimizing harm to nearby vehicles.
Researchers used a new verification framework to test the safety of Autoware, revealing potential limitations in critical traffic situations. The study found that Autoware failed to consistently follow safety rules during scenarios like cut-in, cut-out, and deceleration, highlighting the need for improvement before real-world deployments.
Researchers at Osaka Metropolitan University developed an autonomous driving algorithm for robots to navigate raised cultivation beds, utilizing lidar point cloud data. The system enables precise movement and accuracy in both virtual and actual environments, promising to expand tasks beyond harvesting to monitoring and pruning.
Researchers found people in Japan are less likely to exploit cooperative AI agents compared to humans, while Westerners take advantage of robots more often due to guilt over human exploitation. Cultural differences may shape the future of automation.
Researchers have developed a new sensor to detect hazardous gas leaks in lithium-ion batteries, which could prevent catastrophic failures and enhance the reliability of battery-powered technologies. The sensor detects trace amounts of ethylene carbonate vapour, targeting potential battery failures before they escalate into disasters.
A Wayne State University researcher is working on an integrated architecture to enhance the safety and reliability of autonomous vehicles. The project aims to address complex issues with timing accuracy and schedulability analysis, enabling safe operation of autonomous systems.
The project aims to create perception and communication technologies enhancing healthcare, industrial automation, and real-time environmental interaction. IMDEA Networks is focusing on an energy-efficient network perception system and developing machine-learning algorithms for multi-static sensing.
A recent study by UC Irvine researchers found that multicolored stickers can be used to confuse self-driving vehicle AI algorithms, leading to hazardous operations. The attack vectors were demonstrated to be easily deployable and inexpensive, with the potential to exploit spatial memorization designs in commercial TSR systems.
The University of Michigan is merging its transportation safety research with automated vehicle testing to improve roadway safety. The move marks the institution's 60th anniversary and includes Mcity, a public/private partnership test facility, to develop connected and automated vehicle technologies.
Researchers develop system for self-driving vehicles to share AI models, allowing them to learn from each other's experiences even when they don't meet directly. The Cached Decentralized Federated Learning approach enables vehicles to train locally and share models with others, improving learning efficiency and adaptability.
Researchers developed a submersible robot that leverages vortices to boost efficiency in autonomous underwater vehicles. By 'surfing' vortex rings, CARL reduces energy consumption by one-fifth compared to traditional methods.
A new study found that driving-related conversational prompts improve driver performance in taking control of the vehicle, but only when drivers are engaged. Conversely, non-driving related tasks like solving anagrams can significantly decrease performance and render prompts ineffective.
Researchers are developing a software framework for crowd-sourced 3D map generation and visual localization from camera data to improve real-time updates and low-cost visual localization. This technology aims to advance self-driving vehicles and enable fully automated transportation
The University of Virginia's AI-powered vision system, mimicking praying mantis eyes, has been selected as the best paper of 2024 by Science Robotics. The innovative system enables machines to track objects in 3D space, addressing limitations in current visual data processing.
A team of researchers from UniTrento examined how ants manage traffic congestion using pheromone trails and observed individual ant movements. Their findings could provide a model for optimizing autonomous vehicle traffic flow, reducing congestion and emissions.
Researchers optimized the design of sensors in autonomous vehicles to reduce aerodynamic drag, resulting in a 3.44% decrease in total drag and 5.99% reduction in aerodynamic drag coefficient. This improvement enables longer driving ranges for self-driving cars.
A new study reveals that people tend to assign more blame to artificial intelligences perceived as having human-like minds. The researchers found that participants blamed the AI more than other parties involved in real-world moral transgressions, such as companies or governments.
Researchers at UC3M are conducting a pioneering study on how morphological differences between men and women affect road safety systems, specifically seat belts. The study aims to improve protection for vehicle occupants regardless of gender, as anatomical and behavioural differences may lead to increased risk of injury.
The Mcity Test Facility's first open-source digital twin enables researchers to test autonomous algorithms in a virtual environment. The digital twin introduces real-world data and simulated safety-critical events, accelerating the development of connected and automated vehicle software.
Research shows that remote drivers' reaction time is significantly slowed by distractions and disengagement, increasing response latency and impairing decision-making. This poses serious safety concerns for Level 4 automated vehicles, which rely on remote drivers to make critical decisions.
Researchers developed a comprehensive methodology to quantify intelligence attributes in autonomous vehicles, harmonizing physical, cognitive, and functionality domains. The MIQ framework provides a transformative approach that benchmarks intelligence and fosters human-like cognition.
The authors propose an ML-based authentication mechanism to solve privacy and security issues in the emerging Internet of Vehicle (IoV) ecosystem. The proposed scheme is lightweight, effective, and minimizes bandwidth consumption and delay.
Hoda Eldardiry receives $349,360 grant from NSF to develop practical competencies for students to apply ethical principles in AI system design. Her team aims to engage industry professionals to translate AI ethics into concrete decision-making.
A recent study reviews advancements in reinforcement learning for autonomous vehicle control, highlighting similarities and differences in DRL formulations and training algorithms. The research aims to enhance RL applications, making autonomous vehicles more capable of handling complex traffic situations under uncertain conditions.
Dr. Lishan Yang is developing an automated tool called MELIOREM to enhance the safety of autonomous vehicles through rigorous testing and simulation. The project aims to identify potential safety issues before they affect public roads, ensuring dependability and safety for all road users.
Researchers propose a new approach to reduce the tradeoff between overhead and protecting machines against vulnerabilities. The 'Vulnerability-Adaptive Protection Paradigm' applies different protection strategies to different parts of the system, allocating resources more wisely.
A new method called Clio allows robots to make task-relevant decisions by identifying the parts of a scene that matter. In real experiments, Clio successfully mapped scenes at different levels of granularity based on natural-language prompts and enabled robots to grasp objects of interest.
A team of researchers aims to improve autonomous vehicle safety by identifying and mitigating vulnerabilities in software and hardware. They plan to use knowledge gained from a $926,737 NSF award to design protection mechanisms that can be applied selectively to ensure safety while maximizing efficiency.
Researchers at Purdue University found that autonomous vehicles can interpret and respond to commands from passengers using large language models like ChatGPT. This technology allows the vehicle to personalize its driving to a passenger's satisfaction and take into consideration traffic rules, road conditions, and weather.
Duminda Wijesekera has received $40,000 in funding to evaluate and test the Nvidia Drive Sim for full integration with CDA/CARMA. He will also assess the advantages and disadvantages of using Drive Sim and Omniverse for autonomous vehicle simulations.
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.