Articles tagged with Autonomous Vehicles
Researchers developed MonoCon, a new AI technique that enables accurate identification of 3D objects in 2D images. By incorporating auxiliary context, the method improves object detection and estimation accuracy, paving the way for safer and more robust autonomous vehicles.
The MIT team developed a levitating rover design using ion thrusters, capable of producing enough repulsive force to hover on the moon and larger asteroids. The concept uses tiny ion beams to charge up the vehicle and boost its natural surface charge.
A team of UBC Okanagan researchers has developed a system to enhance interactions between humans and robots in industrial settings. The system uses artificial intelligence and machine learning to capture and analyze the environment, allowing robots to respond in a timely manner to ensure human safety.
The grant aims to build a robot that navigates complex environments and collects data over long periods, combining image collection and acoustic analysis to mimic a trained diver's curiosity. This will enable scientists to slowly build a detailed picture of ecosystem function and health, reducing the impact on animals' behavior.
Experts call for a national compensatory body and guarantee fund to compensate victims of mass-hacking, citing potential catastrophic consequences and financial losses. The UK has an opportunity to establish itself as a leading role in connected and autonomous vehicle development by creating an insurance fund.
The Quantum Sensors project aims to create ultrasensitive gyroscopes and accelerometers using quantum states, enabling precise measurements for self-driving cars and spacecraft. This technology could capture information not provided by GPS, improving navigation and stability in various environments.
A blockchain-based system allows leader robots to signal movements and add transactions to a chain, while malicious leaders forfeit tokens when caught in a lie. This limits the spread of incorrect information and enables follower robots to eventually reach their destination.
Researchers used neuroscientific theories to develop a decision-making model that predicts pedestrian road-crossing decisions. The model shows that pedestrians add up sensory data before crossing, helping autonomous vehicles communicate more effectively with pedestrians.
A North Carolina State University panel of experts assesses AV deployment risks and benefits, predicting substantial benefits if well-regulated. The study's findings suggest regulations could limit urban use of AVs and commercial fleet ownership, reducing risk and increasing benefits.
Researchers found that robots and vehicle automation account for a small percentage of greenhouse gas emissions, with delivery vehicle size and fuel source having larger impacts. A human-driven, battery-powered cargo van has the lowest per-package footprint among analyzed methods.
The new infrared detector can make two technically important ranges of infrared radiation visible, previously not covered by conventional photodiodes. The sensor can distinguish between substances based on their different absorption properties in the NIR and SWIR range.
Researchers at MIT have created an algorithm that enables drones to navigate complex obstacle courses at high speeds without crashing. The new approach combines simulations with real-world experiments, allowing drones to adapt to challenging aerodynamics and find the fastest routes.
A research team developed a novel sensor that can detect and convert infrared light into electrical signals at temperatures up to 100°C. The device eliminates the need for cooling devices, reducing production costs and operating speeds, making it suitable for smartphone and autonomous vehicle applications.
Researchers at Carnegie Mellon University developed an algorithm that can assist autonomous vehicles in navigating tight spaces and unknown driver intentions. The algorithm was trained on simulation data and found to perform better than current models in handling complex scenarios like bi-directional lane usage.
Researchers developed a method to transform uncertainty-unaware controller models into robustified models that can safely behave under uncertainty. The method generates formulas representing the degree of uncertainty a controller can tolerate, enabling flexible analysis and consideration of real-world deployment situations.
Researchers at Florida Atlantic University have developed a technology that uses non-intrusive sensors to perceive drivers' and passengers' moods and adjust driving modes accordingly. This innovation addresses major issues with autonomous vehicles, such as accurately predicting human behavior.
Researchers at Michigan Technological University discuss solutions for snowy driving scenarios using sensor fusion, which combines data from various sensors like lidar, radar, and cameras. This approach enables autonomous vehicles to better detect obstacles and understand their environment.
A study found that consumers are concerned about autonomous vehicles due to performance risks, loss of driving skills and privacy security breaches. Despite these concerns, many see benefits such as freeing time, removing human error and improved performance.
Researchers have developed a new, pixel-sized light detector that can accurately amplify weak signals in real-time, giving autonomous vehicles a fuller picture of their surroundings. This breakthrough increases sensitivity and consistency, making it ideal for lidar receivers and applications in robotics, surveillance, and terrain mapping.
New research reveals autonomous vehicles will increase energy consumption and greenhouse gas emissions across all categories studied. However, electric autonomous vehicles can change this outcome, particularly if adoption rates exceed 40%.
A new study by computer scientists found that individuals are more willing to sacrifice their own safety when peers are more likely to do so in programming autonomous vehicles. The researchers also showed that the social component of decision-making is often overlooked and that transparency in machine programming is crucial for public ...
The Autonomous Vehicle Assistant (AVA) smartphone app provides navigational assistance for people with disabilities and seniors to use self-driving cars. The app offers a multisensory interface, GPS technology, real-time computer vision, and artificial intelligence to support navigation and vehicle access.
Researchers developed a novel control architecture that defends complex, interconnected systems against cyberattacks by implementing a Leader-Follower approach. This algorithm can detect and isolate infected sub-systems, reducing the impact of targeted DoS attacks and increasing system robustness.
The University of Texas at Arlington is launching a public transportation pilot program with free rides for students, featuring autonomous vehicles provided by May Mobility. The program aims to develop efficient, safe, and accessible transit networks in low-density settings.
Researchers at TUM have developed a software module that analyzes and predicts events while driving, ensuring the vehicle will not cause accidents. The system determines movement options and emergency maneuvers to prevent collisions, using simplified dynamic models for swift calculations.
Researchers at the University of Warwick have developed a training tool to reduce motion sickness susceptibility by over 50% using visuospatial exercises. This method has shown promise in both driving simulators and on-road experimentation, with potential applications in autonomous vehicles and other domains.
Cyber-physical systems face challenges due to large volumes of data flowing through communication networks, causing routing and queuing delays that degrade system quality. The new algorithms developed by researchers strike a balance between communication sparsity, delay, and performance, ensuring safe and stable operation.
A North Carolina State University expert suggests using a framework that considers three variables: agent intent, deed, and consequence. This approach can lead to more nuanced moral judgments, similar to human moral judgment.
Researchers have developed a new optimization method for tracking self-driving car trajectories that reduces errors while keeping computation demands low. The method prioritizes passenger comfort, aiming to replicate human drivers' ability to balance speed, safety, and route choice.
Researchers at Northwestern University developed a decentralized algorithm that enables swarms of robots to form shapes and avoid collisions. The algorithm views the ground as a grid, allowing each robot to sense its closest neighbors and make local decisions without global information.
The study found that autonomous vehicles can reduce road accidents and promote physical activity, but the impact depends on factors like technology implementation and fuel use. If implemented correctly, autonomous vehicles could have a significant positive impact on public health, especially if used in electric and shared formats.
Researchers have developed bioinspired shapes that serve as acoustically conspicuous guideposts for sonar-guided autonomous vehicles. These bioinspired sonar reflectors were tested in experiments and showed promising results, enabling robots to navigate through new environments with improved accuracy.
Researchers have developed a new model to help autonomous vehicles navigate intersections with obstructed views, reducing the risk of collisions. The model estimates risks based on factors like sensor noise, driver awareness, and occlusions.
The researchers have developed a platform that enables companies to quickly address safety concerns in autonomous vehicles through software and hardware advances. They analyzed 144 AVs driving over 1,116,605 miles and found that human-driven cars were up to 4000 times less likely than AVs to have an accident.
New research from the University of Adelaide predicts that driverless cars could increase traffic congestion in Australia's City of Adelaide. The study, which surveyed over 500 commuters, found that autonomous vehicles may lead to an adverse impact on public transport, causing peak period vehicle flows to rise.
A new decision-making and motion-planning technology has been developed to limit injuries and damage when self-driving vehicles are involved in unavoidable crashes. The system considers various factors such as relative speeds, angles of collision, and differences in mass and vehicle type to determine the best possible manoeuvre.
A four-year study will examine the impacts of autonomous vehicles on the future workforce, focusing on how driving jobs will change and what new skills are required. Researchers will also investigate the anticipated downstream impacts on drivers' employment trends and income inequality.
A new algorithm assesses cloudlet placement to achieve an optimal balance between cost and service performance. The proposed method uses cloudlets, tiny versions of the cloud, to improve network service performance for a limited number of users.
A new study aims to explore ways to share decision-making and information between humans and AI drivers, addressing concerns about perceived loss of control and fear of unknown actions. The goal is to increase user trust, consumer acceptance, and overall usability of autonomous vehicles.
A study by the University of Warwick found that neither fully machine-like nor human-like autonomous vehicle driving styles were optimal, but a blend of both may be best. Passengers showed increased confidence with each run in both styles.
In the INFORMS O.R. & Analytics Student Team Competition, student teams from around the world used operations research (OR) and analytics to optimize autonomous vehicle delivery processes for General Motors. The winning team from Korea Advanced Institute of Science and Technology minimized total costs while satisfying all constraints.
A new mathematical method developed by USC researchers can identify anomalies in self-driving cars' perception algorithms before they hit the road, improving safety. The method uses 'sanity conditions' to test machine learning tools and can be used to pinpoint specific problems and retrain the algorithms for faster error detection.
Well-managed autonomous vehicles could increase mobility, improve safety, and reduce emissions, but poorly managed ones could exacerbate environmental problems. Implementing fuel economy standards and regulations can ensure a positive outcome.
A recent special issue published in Risk Analysis examines how attitudes and perceptions of risk affect the acceptance of autonomous vehicles. Studies found that most people prefer defaults to staying in their lane when faced with a collision, and social trust plays a significant role in public acceptance.
MIT researchers develop a two-dimensional, sub-terahertz receiving array on a chip that's orders of magnitude more sensitive than existing sensors. This can help steer driverless cars through fog and dust by detecting signals at sub-terahertz wavelengths with ease.
Researchers found that programming autonomous vehicles in advance leads to more cooperative decisions, as people prioritize collective interests over short-term rewards. This effect generalizes beyond the domain of autonomous vehicles and has implications for shaping societal dilemmas.
Researchers at George Washington University found that decentralized systems perform better when individual parts are less capable, as overly smart components lead to overcorrections and mistakes. This discovery has potential applications in company structure, autonomous vehicles, AI algorithms, and even biological evolution.
Self-driving cars will slow traffic by cruising at low speeds to avoid high downtown parking fees. Cities face challenges regulating autonomous vehicles, which can create havoc if not properly managed. Congestion pricing is proposed as a solution to reduce congestion and pollution.
The study explores the potential impact of autonomous vehicles on urban tourism, highlighting both benefits such as reduced traffic congestion and improved foreign car hire processes, as well as concerns over job losses and increased urban sprawl. As AVs become mainstream, urban attractions may be transformed, and new industries like A...
A study by CNRS and researchers gathered 40 million moral dilemma responses from web users worldwide. The data revealed global moral preferences guiding decision makers, prioritizing human lives over animals, saving the largest number of lives, and protecting the youngest over older people.
A massive global survey on autonomous vehicle ethics found that people generally prefer sparing human lives over animal lives and young people's lives. However, regional variations were observed, particularly in the eastern cluster of countries where preference for younger people was less pronounced.
Researchers have developed a new material with high birefringence properties that can improve infrared detection in dense fog and dark conditions. This technology may enable faster deployment of autonomous vehicles and create more efficient heat sensing tools for firefighters.
A new lane-change algorithm developed by MIT allows autonomous vehicles to model an entire range of driving styles, from conservative to aggressive, with safety guarantees. The system computes buffer zones on the fly and ensures collision avoidance within a given time frame.
The AVENUE project, led by the University of Geneva, aims to develop and test autonomous vehicle services in European cities. The project will focus on optimizing itineraries, in- and out-of-vehicle services, and addressing security concerns. Geneva is one of the pilot sites for the large-scale tests.
Wiseman and Grinberg propose a system to evaluate collision potential and choose the least harmful course of action for autonomous vehicles. The system uses Spatial Data Structures and Bounding Volumes to analyze possible crashes and decide on the most destructive option.
Researchers at U of T Engineering found that optimizing for autonomous vehicles can increase parking lot capacity by 62%. A well-designed AV parking lot can accommodate more cars than a conventional one, with square-shaped lots capable of increasing capacity up to 87%.
Researchers are developing a miniature collision detection sensor system that could drastically improve the safety of autonomous vehicles. The ULTRACEPT project combines near-range collision detection, long-range hazard perception, and thermal-based collision detection tools to overcome current limitations.
A new study found that autonomous vehicles can minimize environmental impacts with energy-efficient design and operational benefits outweighing increased energy use from sensors and computers. The study showed a 40% reduction in greenhouse gas emissions for electric powertrains versus internal-combustion engines.
A UMass Lowell professor is leading a research study on the ethical dilemmas posed by autonomous vehicles. The team aims to develop decision-making algorithms that balance individual rights with societal welfare. They will also investigate cybersecurity and privacy concerns related to self-driving cars.
New research shows that a small percentage of self-driving cars can significantly impact road flow, eliminating phantom traffic jams and reducing fuel consumption by up to 40%. The study demonstrates the potential for autonomous vehicles to regulate traffic flow and improve efficiency.