Helping robots assess risk
A new project aims to help robots assess risks and make autonomous decisions. The research focuses on quantifying ambiguity in robot perception to improve safety and efficiency.
Autonomous Robots
Articles tagged with Autonomous Robots
The new robot is taking its first intuitive steps
A team of engineers at the University of Pittsburgh has created a new robot that can navigate complex environments using bio-inspired neural networks. The robots will be able to avoid obstacles and learn from their experiences, enabling autonomous navigation for various applications such as commercial transport and disaster response.
New cyber algorithm shuts down malicious robotic attack
Australian researchers developed an algorithm that can intercept and shut down man-in-the-middle cyberattacks on unmanned military robots. The algorithm, tested on a replica of a US army combat ground vehicle, was 99% successful in preventing malicious attacks.
SourceUniversity of South Australia·JournalIEEE Transactions on Dependable and Secure Computing·TypeExperimental study·DateOct 11, 2023
Engineering researchers to study wireless communication and machine learning with NSF grant
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.
WVU researcher to help send swarm of marine robots on climate change quest beneath ocean ice
Researchers aim to access ocean waters hidden beneath ice shelves, where critical information about climate change is stored. An intelligent mothership and coordinated marine robots will communicate data from under-ice cavities, optimizing sampling and configuration.
Scientists successfully maneuver robot through living lung tissue
Researchers have successfully developed a robot that can autonomously navigate through living lung tissue, avoiding vital structures such as airways and blood vessels. This innovation enables surgeons to reach previously inaccessible small tumors, improving treatment outcomes for patients with lung cancer.
Groundbreaking soft valve technology enabling sensing and control integration in soft robots
Researchers developed a groundbreaking soft valve technology that integrates sensors and control valves into soft robots, eliminating the need for electric components. This innovation enables safe operation underwater or in environments with sparks risks, reducing weight burdens and costs.
SourceUlsan National Institute of Science and Technology(UNIST)·JournalNature Communications·DateSep 15, 2023
How do robots collaborate to achieve consensus?
Researchers proposed a novel self-organizing approach for robot swarms to achieve consensus, combining aspects of centralized and decentralized control. This method reduces uncertainty sources and enhances collective perception accuracy, enabling robots to fuse sensor information without global or static communication networks.
‘Brainless’ robot can navigate complex obstacles
Researchers at North Carolina State University have created a soft robot that can navigate simple mazes without human or computer guidance. The new robot has an asymmetrical design, allowing it to turn and move in arcs, enabling it to navigate complex and dynamic environments.
SourceNorth Carolina State University·JournalScience Advances·TypeExperimental study·DateSep 8, 2023
Autonomous robot for subsea oil and gas pipeline inspection being developed at University of Houston
Researchers are developing an autonomous robot to identify potential pipeline leaks and structural failures during subsea inspections, reducing costs and risk. The SmartTouch technology uses stress wave-based smart touch sensors, video cameras, and scanning sonars to inspect flange bolts and detect corrosion.
New framework for oceanographic research provides potential for broader access to deep sea scientific exploration
A new framework, SHARC, provides a way for shore-based scientists, citizen scientists, and the public to collaborate with robotic sampling processes. The framework enables remote participants to conduct shipboard operations and control robotic manipulators using basic internet connection and consumer-grade hardware.
SourceWoods Hole Oceanographic Institution·JournalScience Robotics·TypeExperimental study·DateAug 24, 2023
Development of NIMS-OS: general-purpose software enabling autonomous, automated experiments
The NIMS-OS middleware coordinates materials-search AI and robotic experiment systems for efficient automation. The system successfully executed a model experiment to identify effective electrolytes for lithium metal electrodes.
SourceNational Institute for Materials Science, Japan·JournalScience and Technology of Advanced Materials Methods·TypeExperimental study·DateAug 24, 2023
$1 million grant helping empower students to succeed in the ‘fourth industrial revolution’
The University of Missouri is using a $1 million grant to develop an Industry 4.0 lab, providing engineering students with hands-on learning experiences in the latest industrial revolution's technology-centered job market. The lab will integrate skills at a higher level and keep students at the state-of-the-art level for industry.
Purdue thermal imaging innovation allows AI to see through pitch darkness like broad daylight
Researchers at Purdue University have developed an innovative thermal imaging method called HADAR, which enables artificial intelligence to perceive physical attributes and recover textures in pitch-dark environments. The technology has the potential to revolutionize fields such as autonomous vehicles and robotics.
Wide field-of-view metasurface-enhanced scanning lidar technology
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.
SourceSPIE--International Society for Optics and Photonics·JournalAdvanced Photonics·DateJul 20, 2023
Enabling autonomous exploration
Researchers at Carnegie Mellon University's Robotics Institute have developed a suite of robotic systems and planners enabling robots to explore more quickly, probe the darkest corners of unknown environments, and create more accurate maps. The systems allow robots to do all this autonomously, finding their way and creating a map witho...
AI nursing ethics: viability of robots and artificial intelligence in nursing practice
Researchers examine whether robots and AI can replicate the ethical concepts attributed to human nurses, including advocacy, accountability, cooperation, and caring. While AI can inform patients about medical errors and present treatment options, it questions its ability to truly understand and empathize with patients' values.
Bees make decisions better and faster than we do, for the things that matter to them
Researchers discovered that honey bees make rapid and accurate decisions by balancing effort, risk, and reward. By studying the bees' brain structure, they created a computer model that replicated their decision-making process, showcasing how simple brains can be efficient.
A robot that performs genetic manipulations of the roundworm C. elegans
A robotic system, WormPicker, autonomously detects and manipulates Caenorhabditis elegans for genetic research, increasing productivity for human researchers. The system accelerates studies in diverse areas of C. elegans biology.
Soft robo-glove can help stroke patients relearn to play music
A soft robotics glove with integrated sensors and AI can aid patients in relearning daily tasks after neurotrauma, including playing music. The glove provides hand guidance, amplifying dexterity and motor skills.
This self-driving boat maps underwater terrain
Researchers at the University of Texas at El Paso have developed an autonomous boat that can carry out bathymetric surveys with unprecedented ease. The robotic vessel uses a multibeam echosounder to measure water depth and detect material types on the seafloor, enabling scientists to create accurate maps of underwater terrain.
Hybrid AI-powered computer vision combines physics and big data
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.
SourceUniversity of California - Los Angeles·JournalNature Machine Intelligence·TypeCommentary/editorial·DateJun 14, 2023
Four-legged robot traverses tricky terrains thanks to improved 3D vision
Researchers at University of California - San Diego developed a new model that trains four-legged robots to see more clearly in 3D, allowing them to autonomously cross complex environments. The robot uses a forward-facing depth camera to synthesize visual information from past frames and estimate its surroundings.
ChatGPT designs its first robot with TU Delft researchers
Researchers at TU Delft and EPFL collaborated with ChatGPT to design a tomato-harvesting robot, showcasing the potential of AI in robotics. The study highlights the need for verification and validation of LLM output to prevent misinformation and bias.
SourceDelft University of Technology·JournalNature Machine Intelligence·TypeExperimental study·DateJun 7, 2023
Autonomous products like robot vacuums make our lives easier. But do they deprive us of meaningful experiences?
Researchers found that manual labor's perceived meaning can predict the adoption of autonomous products. Consumers tend to reject these products due to a loss of meaning in life. Companies can highlight alternative sources of meaning to reduce negative effects on adoption.
Toys demonstrate how biological machines move
Scientists develop elastoactive chains with self-oscillatory, self-synchronizing, and self-snapping behavior, mimicking biological machines. The study explores material properties and potential applications in autonomous robot development.
Researchers have mimicked the human hippocampus to improve autonomous navigation
HBP researchers develop a robotic platform capable of learning as humans do while navigating around a space. The simulated hippocampus alters its own synaptic connections to remember paths, a marked improvement over current methods relying on deep learning.
Carnegie Mellon researchers develop head-worn device to control mobile manipulators
A new head-worn device allows users to control a mobile robot via head motion and speech recognition, requiring fewer fine motor skills than existing technologies. In a human study, participants performed household and self-care tasks with low error rates, minimal effort, and high perceived ease of use.
CONVINCE project kicked off to improve autonomy of robots
The CONVINCE project, funded by €4 million, focuses on developing cognitive deliberation capabilities in autonomous robots to enhance safe and robust operation in unstructured environments. The goal is to enable robots to adapt to their surroundings and tasks autonomously without human intervention.
Robot helps students with learning disabilities stay focused
Researchers at the University of Waterloo used a robot to help students with learning disabilities stay focused, leading to higher completion rates. The study found that students who worked with the robot were generally more engaged with their tasks.
AI-powered massage robot to start product evaluation in the United States and clinical trial in Singapore
A new clinical trial will assess the efficacy of an AI-powered massage robot, EMMA, in managing chronic low back pain. The study aims to explore the effectiveness of robotic Tuina therapy in alleviating pain and improving health outcomes.
Compact, non-mechanical 3D lidar system could make autonomous driving safer
Researchers developed a new non-mechanical 3D lidar system that combines scanning and flash illumination using a chip-based light source, enabling safe navigation in dynamic environments. The system can measure the distance of poorly reflective objects and track their motion, making autonomous driving safer.
The ants go marching … methodically
Researchers at the University of Arizona found that rock ants follow a methodical search strategy, combining systematized meandering with random movement to efficiently explore new areas. This unique behavior may provide insights into the evolution of exploration strategies in other species.
Words prove their worth as teaching tools for robots
Researchers found that providing language descriptions of tools can accelerate a simulated robotic arm's learning of tool manipulation. The team used GPT-3 to obtain tool descriptions and showed improved performance in tasks such as pushing, lifting, sweeping, and hammering with new tools.
SourcePrinceton University, Engineering School·TypeComputational simulation/modeling·DateDec 21, 2022
Researchers develop winged robot that can land like a bird
Scientists at EPFL have developed a method for a flapping-wing robot to land autonomously on a horizontal perch using a claw-like mechanism. The innovation could significantly expand the scope of robot-assisted tasks and enable robots to recharge using solar energy.
SourceEcole Polytechnique Fédérale de Lausanne·JournalNature Communications·TypeExperimental study·DateDec 19, 2022
Making “transport” robots smarter
University of Missouri engineers are working on a collaborative human-robot order picking system to speed up the online delivery process. The proposed model aims to optimize key decisions in warehouse operations, allowing robots to navigate efficiently and collaborate with humans to increase efficiency.
SourceUniversity of Missouri-Columbia·JournalInternational Journal of Production Economics·DateNov 29, 2022
Experts from across the disciplines come together at new center to push the boundaries of smart robotics and AI
The University of Manchester's Centre for Robotics and AI will focus on interdisciplinary research, exploring applications of robotics in extreme environments and the intersection of AI and humanity. The centre aims to develop robots that can work safely in hostile zones, such as nuclear decommissioning sites.
Flocks of assembler robots show potential for making larger structures
Researchers have made significant progress toward creating robots that can build nearly anything, including vehicles, buildings, and even bigger robots. The new system uses complex voxels that can carry power, data, and force, enabling the building of structures with intelligence.
Robots are taking over jobs, but not at the rate you might think
A recent study found that only 14% of workers have seen their job replaced by a robot, while those who experienced displacement overestimated the rate. The study suggests that workplaces are integrating robots and humans in ways that generate more value for human labor.
SourceBrigham Young University·JournalSocius Sociological Research for a Dynamic World·TypeSurvey·DateNov 9, 2022
Tracking trust in human-robot work interactions
Researchers at Texas A&M University used functional near-infrared spectroscopy to monitor participant responses during human-robot collaborations. They found that faulty robot actions decreased operator trust and associated it with increased brain activity in the frontal, motor, and visual cortices.
Neuroscience of electric fish gives jolt to advances in machine learning at WVU
Researchers at WVU are developing software for robots to learn and adapt in real-time, inspired by the neural networks of electric fish. The goal is to enable robots to navigate different terrains autonomously without human supervision.
Balancing risk and reward in planetary exploration
Researchers at Carnegie Mellon University have developed a new approach for conducting automated science in space by balancing risk and scientific value. The approach uses a model that estimates science value and risk, allowing rovers to chart their own course while protecting against high-risk missions.
How can flying insects and drones tell up from down?
Researchers developed a new principle for estimating gravity direction in flying insects and drones by combining optical flow with movement modeling. This allows them to determine the direction of gravity in most situations except when completely stationary, which destabilizes their flight.
Can robots and humans co-exist in public? UT campus study will offer answers
The University of Texas at Austin will launch a five-year study on human-robot interactions in public spaces, with the goal of improving safety and communication between robots and pedestrians. The research project will deploy robotic delivery networks on campus, allowing for extensive data collection on human-robot encounters.
How scientist summarized the development of space robotic technologies for on-orbit assembly?
The article discusses the development status of space robot technology and relevant on-orbit assembly technology. Key findings include the shift from manual to autonomous assembly and the need for advanced motion planning and control methods to achieve high-precision operations.
SourceBeijing Institute of Technology Press Co., Ltd·JournalSpace Science & Technology·DateOct 14, 2022
New walking robot design could revolutionize how we build things in space
Researchers designed a state-of-the-art walking robot that can assemble large constructions in space, such as telescopes. The E-Walker robot proved to be versatile and ideal for future in-orbit missions.
Tiny particles work together to do big things
Researchers at MIT designed simple microparticles that can collectively generate complex behavior, generating a beating clock that can power tiny robotic devices. The particles use a simple chemical reaction to interact with each other and create an oscillatory electrical signal.
New algorithms help four-legged robots run in the wild
A team from the University of California San Diego has developed a new system of algorithms that enables four-legged robots to walk and run on challenging terrain while avoiding obstacles. The system combines vision with proprioception, allowing the robot to move efficiently and smoothly in various environments.
With DARPA award, researcher will allow robots to autonomously collaborate in teams without human intervention
Researcher Giuseppe Loianno receives $1 million grant from DARPA to develop USARC robots that can autonomously collaborate in teams. The project aims to create robots capable of executing maneuvers with superior performances compared to human-controlled or current autonomous ground and aerial robots.
Can robots have morals? Robots’ decisions on forced medication evoke doubts
A study at the University of Helsinki found that people accept human nurses overruling patient autonomy but reject similar decisions made by robots. The researchers suggest that human empathy is required to consider robot-made solutions equally acceptable as those made by humans. The findings imply that machines cannot comprehensively ...
A swarm of 3D printing drones for construction and repair
A team of Swiss researchers has developed Aerial Additive Manufacturing (AAM), a system that uses flying drones to print materials for construction projects. The technology enables on-site manufacturing and building in difficult-to-access or dangerous locations, such as post-disaster relief construction and tall buildings.
SourceSwiss Federal Laboratories for Materials Science and Technology (EMPA)·JournalNature·TypeExperimental study·DateSep 22, 2022
3D printing drones work like bees to build and repair structures while flying
Researchers have developed a technology using flying robots that mimic the collective building methods of bees and wasps to construct and repair large structures. The Aerial Additive Manufacturing system consists of drones that work autonomously but are monitored by human controllers, adapting their techniques as needed.
Smart microrobots walk autonomously with electronic ‘brains’
Researchers at Cornell University have created smart microrobots that can walk autonomously using electronic brains. The robots, powered by photovoltaics, feature a complementary metal-oxide-semiconductor (CMOS) clock circuit and platinum-based actuators. With this innovation, scientists can track bacteria, sniff out chemicals, destroy...
WVU engineers aim to improve safety with autonomous robotic inspection system for coal waste storage facilities
Researchers aim to create intelligent drones that can autonomously inspect coal waste storage facilities, detecting cracks and deformities with thermal and visual images. The drones will be equipped with AI-based software to identify potential hazards, providing a faster and long-term solution to prevent environmental damage.
Extra “eye” movements are the key to better self-driving cars
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.
Robotic lightning bugs take flight
Researchers at MIT created insect-scale robots that can emit light during flight, allowing for precise motion tracking and potential communication between robots. The ability to emit light also enables the robots to call for help in search-and-rescue missions.
SourceMassachusetts Institute of Technology·JournalIEEE Robotics and Automation Letters·DateJun 21, 2022
MIT engineers devise a recipe for improving any autonomous robotic system
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.
Insect-inspired AI for autonomous robots
Researchers draw inspiration from insect intelligence to create more efficient and robust AI for small autonomous robots. Advances in biology and technology enable fine-grained investigations of insect brains, leading to faster energy efficiency and speed in sensing and neural processing.
Twisted soft robots navigate mazes without human or computer guidance
Researchers developed soft robots that can navigate complex environments like mazes and climb slopes of loose sand. The twist in the robot's design allows it to rotate around obstacles and 'snap' into place, enabling autonomous navigation without human or computer input.
SourceNorth Carolina State University·JournalProceedings of the National Academy of Sciences·TypeExperimental study·DateMay 23, 2022
New study highlights major step forward in monitoring ocean health
Researchers at MBARI use eDNA and autonomous underwater robots to survey marine biodiversity, providing clues about changes in sensitive areas and the presence of rare species. The technology enables persistent monitoring of ocean ecosystems, supporting food webs and regulating climate.