Researchers at Chalmers University of Technology created an AI scientist capable of generating scientific hypotheses, designing experiments and interpreting results. The AI system, Eve, identified promising biological questions, recommended experiments and evaluated outcomes, and iteratively refined its understanding based on new evide...
DirectHop, a 1-gram robot, can perform multiple hops in sequence and jump high enough to clear a standard stair step with single centimeter accuracy. The robot uses a tiny electric motor and three folding legs to launch itself to a specified jump height, and can twitch to right itself after landing for another jump.
The robotic lab can autonomously assemble and fine-tune optics experiments, reducing manual setup time from days or months to minutes. This could enable scientists to focus on theoretical work and accelerate innovation in fields like quantum technologies and renewable energy.
A new AI framework, AdvWT, uses realistic fading, cracks, and corrosion to test vulnerabilities in AI vision systems. It achieves near-perfect attack success rates on lightweight CNNs and transformer-based models, and can also be used to restore naturally damaged traffic signs.
The robots use torsion to store elastic energy and release it all at once, causing them to jump and repeat the process as long as they are exposed to infrared light. Design changes can control the movement, such as jumping forward or leaping vertically.
Researchers developed a disturbance observer to compensate for external disturbances, allowing the robot to reject disturbances while maintaining stable flight. The approach reduced the X-axis position error by 53.1% and improved overall stability.
Researchers at the University of Minnesota have developed an AI system that tracks a diver's health in real-time using robotic vision and exhaled bubble analysis. The system can detect signs of stress, hyperventilation, or exhaustion, providing a non-contact approach to monitor divers' physiological stress underwater.
Researchers create tiny swimmers to deliver drugs through the human body, finding they reverse direction in non-Newtonian fluids like mucus and blood. This discovery enhances understanding of fluid behavior and could lead to targeted drug delivery.
Researchers at Texas A&M University are designing how humans will build and survive on the moon, focusing on sustainable construction using lunar regolith. The institution's efforts aim to reduce costs associated with shipping materials to the moon, making it possible to produce rocket propellant locally.
A new open-source trajectory-planning system, MIGHTY, has been developed by researchers at MIT and the University of Pennsylvania. The system enables robots to generate smooth flight paths while reacting to obstacles in real-time, making it suitable for applications such as search-and-rescue, last-mile delivery, and industrial inspection.
Researchers at FAU's CA-AI are developing machine learning technologies to enable autonomous systems to sense, learn, and act in coordination. The project aims to overcome the challenge of individual smart systems failing to collaborate effectively as part of a network.
Researchers at Aston University have created an AI-based training method that enables robots to adapt to real-world conditions without extensive data collection. This breakthrough could significantly accelerate innovation in sustainable manufacturing, recycling, and autonomous industrial systems.
A new rulebooks framework developed by Iowa State University researchers provides a principled way for autonomous systems to rank and reconcile competing goals. The framework avoids the issues of blending weighted trade-offs, allowing systems to clearly define which rules come first and choose the least harmful option.
The eDNA-bot revolutionizes biological monitoring by providing comprehensive results at lower cost than conventional surveying methods. It can detect elusive species and monitor wastewater for pathogens, streamlining environmental assessments in hydropower licensing.
The study, led by Lucy Liu and L. Mahadevan, shows that adding the right amount of noise to individual robot movements can ease gridlock and improve efficiency in crowded environments. The researchers used computer simulations and experiments with small robots to test their ideas.
Researchers propose a foundational framework to help multi-agent, connected systems decide what information they can trust before acting. The 'cy-trust' concept assigns a numerical trust value between 0 and 1 to data from other agents based on sensing, context, network behavior, and past experience.
Researchers at Worcester Polytechnic Institute developed a palm-sized aerial robot that uses ultrasound sensors and AI to navigate through fog, smoke, and other difficult conditions. The drone achieved a success rate of 72% to 100% in navigating challenging courses during 180 tests.
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 at Penn and UMich created microscopic swimming machines that can independently sense and respond to their surroundings, operate for months, and cost just a penny each. The robots are powered by light and can be programmed to move in complex patterns, sense local temperatures, and adjust their paths accordingly.
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.
Scientists at TU Delft developed an algorithm allowing multiple autonomous drones to work together to control and transport heavy payloads even in harsh weather. The system enables drones to lift and orient a payload with precision, ideal for reaching infrastructure like offshore wind turbines.
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.
A new Physical AI technology cuts driving time for robots in logistics centers and smart factories by up to 30%, improving navigation efficiency through social behavior modeling. The tech allows robots to forget unnecessary information, share important details, and achieve more efficient cooperative navigation.
Researchers at CARS create detailed maps of chemical reactivity, discovering regions of unexpected outcomes and reconstructing intricate reaction networks. This new understanding enables control over the formation of different major products from a set of starting materials.
Researchers at Stanford University created an algorithm that efficiently manufactures products with a team of robots, directing them to work alone or in teams and laying out the assembly floor to prevent collisions. The ability to generate assembly plans quickly could provide flexibility in manufacturing, allowing factories to pivot mo...
Researchers at the University of Minnesota developed AI-guided aerial robots to detect, track and analyze wildfire smoke plumes. The technology provides high-resolution data collection across large areas at a lower cost than satellite-based tools, enabling more accurate computer models for air quality predictions.
Vasile's research aims to map and model an agent's capabilities, particularly in motion, manipulation, and perception, to reliably predict their behavior. The goal is to use this understanding to plan effectively for large teams of agents.
Researchers at North Carolina State University unveiled Rainbow, a self-driving laboratory that autonomously discovers high-performance quantum dots. The system combines advanced robotics and AI to conduct up to 1,000 experiments per day, accelerating materials discovery.
Researchers created dynamic metashells that leap into the air on a predetermined schedule without intervention, jumping up to nine times their height. The structures were engineered to store energy and release it at a controlled timing, with scheduled jumps possible from three seconds to 58 hours in advance.
Researchers developed an intelligent autonomous robot capable of automating hospital disinfection processes through dual disinfection system, increasing efficiency and precision. The robot's performance was validated through real-world testing, reducing the risk of infection in hospitals.
Scientists used virtual reality to mimic schooling behavior in zebrafish, discovering a simple and robust control law that enables coordinated motion. This natural algorithm was then applied to swarms of robotic cars, drones, and boats, achieving performance comparable to state-of-the-art autonomous systems.
A soft robot can carry loads through the air along established tracks, navigating angles of up to 80 degrees and carrying loads up to 12 times its weight. The robot uses infrared light to move along the track, repeating a rolling motion that pulls it forward.
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.
A research paper proposes an earthworm-inspired soft robot with a novel wire-winding transmission mechanism, achieving multimodal motion and superior motion efficiency. The robot surpasses other robots of the same type in planar crawling speed by an order of magnitude.
Scientists successfully developed a method to precisely control the flight altitude of robo-pigeons using targeted electrical stimulation of the LoC nucleus. The study found that stimulation frequency and cycle can effectively control altitude, while increasing neural fatigue is minimized with proper inter-stimulus interval.
Researchers created a hopping robot that can traverse challenging terrains, carry heavy payloads, and uses less energy than aerial robots. The robot's springy leg and flapping-wing modules enable it to jump over obstacles and adjust its orientation mid-air.
A tiny, soft robot developed by Penn State researchers can navigate through debris and deliver medicine inside the body. The flexible electronics system enables smart sensors to interact with its surroundings, allowing the robot to operate with minimal human intervention.
Researchers at Kumamoto University have developed a new mathematical modeling technique for linear periodically time-varying systems, enhancing the accuracy of control system models. This breakthrough has profound implications for industries relying on complex control systems, such as autonomous vehicles and aerospace applications, imp...
Researchers are developing soft-bodied actuators, shape-adaptive propulsors, and AI-driven control strategies to improve energy efficiency and adaptability in MURs. Future innovations may enable robots to mimic marine organisms with unprecedented fluidity and facilitate swarm robotics for collective exploration.
This groundbreaking research systematically reviewed construction robots' scientific technologies and progress in extreme environments, including hazardous work environments, polluted environments, and harsh natural environments. The study elucidated four key technical performance aspects: mechanism, perception, planning, and control.
State-of-the-art AI models struggle to interpret clock-hand positions and answer questions about dates on calendars, requiring spatial awareness, context, and basic maths. Researchers tested various clock designs with different fonts and styles and found that AI systems got clock-hand positions right less than a quarter of the time.
Researchers develop active metamaterials that can autonomously roll, crawl, and wiggle over unpredictable terrain, including uphill and obstacles. These 'odd' objects achieve motion through unusual interactions between motorized building blocks, demonstrating decentralized and robust locomotion.
Researchers at Yokohama National University have developed a tiny, low-weight robot that can act independently and with ultra-high precision in extreme environments. The Holonomic Beetle 3 (HB-3) integrates piezoelectric actuators with autonomous technology for precise manipulation tasks, addressing industries such as laboratory automa...
Researchers from the University of Washington have developed an assistive feeding arm that can help people with motor impairments feed themselves. The system, dubbed ADA, uses a robotic arm and web app to deliver meals autonomously, with users able to customize its functionality.
A bioinspired robot called GOAT can change shape to alter its physical properties in response to the environment, resulting in a robust and efficient autonomous vehicle. The robot's compliance allows it to navigate diverse environments with minimal sensing equipment, enabling it to find the path of least resistance.
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.
Researchers at Columbia University developed a way for robots to autonomously model their own 3D shapes using a single camera, enabling them to understand and adapt to their movements. This breakthrough allows robots to overcome damage to their bodies, making them more reliable and resilient for various applications.
Ebru Demir aims to study how groups of AI-driven microswimmers move in biological fluids for potential applications in drug delivery, fertility treatments, and other medical fields. Her research combines artificial microswimmers with machine learning to uncover the underlying physics governing their movement.
Researchers created robotic materials that can change shape, support heavy loads, and self-heal by enabling dynamic inter-unit forces and biochemical signaling. The system can be scaled to thousands of units, enabling the development of robust and adaptable robotic materials.
Researchers develop a novel adaptive nonlinear PID controller integrated with radial basis function neural network for enhanced ballbot functionality. The proposed NPID-RBFNN controller demonstrates superior stability and robustness, outperforming traditional PID and NPID controllers.
Researchers at Japan Advanced Institute of Science and Technology developed Leafbot, a soft robot that uses vibration-driven locomotion to traverse uneven surfaces. The robot's compliant structure and simple motion strategy enable it to overcome complex obstacles, making it valuable for applications such as inspection and exploration.
Two EU-funded projects presented digital, robotic, and other technologies for improved road monitoring and maintenance, emphasizing the need for automation, data-driven solutions, and sustainability. High-level participants highlighted the importance of collaboration and regulation in paving the way for smarter infrastructure management.
A team of MIT engineers has developed a training method for multiagent systems that can guarantee their safe operation in crowded environments. The method enables agents to continually map their safety margins, allowing them to scale up to any number of agents while maintaining system safety.
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
Researchers advise reprogramming and repurposing robots for sustainable use, as current recycling methods are often ineffective. The study aims to challenge the robotics industry to design for a circular economy, addressing challenges such as economic viability and technical capability.
A new 6D pose dataset has been introduced, providing high-quality RGB and depth images with annotated 6D pose data. This dataset achieves state-of-the-art accuracy rates of 97.05% and 98.09% for robotic grasping and automation applications.
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.
Researchers from Singapore, Japan and US developed an advanced swarm navigation algorithm for cyborg insects that prevents them from getting stuck in challenging terrain. The new algorithm represents a significant advance in swarm robotics and could pave the way for applications in disaster relief and search-and-rescue missions.
Scientists have developed swarms of tiny magnetic robots that can lift and transport heavy objects, thanks to their unique assembly configuration and rotating magnetic field. The microrobots can even guide small organisms through complex motions.
Researchers discover that modifying BallBot's body mass and ball size can significantly improve its balancing abilities, enabling more stable and reliable robots. The study introduces a Linear Quadratic Regulator (LQR) controller to fine-tune the robot's movements, allowing for improved balance and stability in dynamic environments.