INFORMATION:
Co-authors are Miles Macklin, Yashraj S Narang, Dieter Fox, Animesh Garg, Fabio Ramos, all of NVIDIA.
The full paper (open access) and blog post are available here: https://diff-cutting-sim.github.io/
New simulator helps robots sharpen their cutting skills
A simulation engine developed by University of Southern California and NVIDIA researchers predicts the forces acting on a knife as it cuts through soft materials, a capability that could have applications for safer food processing and surgical robotics
2021-07-21
(Press-News.org) Researchers from the University of Southern California (USC) Department of Computer Science and NVIDIA have unveiled a new simulator for robotic cutting that can accurately reproduce the forces acting on a knife as it slices through common foodstuffs, such as fruit and vegetables. The system could also simulate cutting through human tissue, offering potential applications in surgical robotics. The paper was presented at the Robotics: Science and Systems (RSS) Conference 2021 on July 16, where it received the Best Student Paper Award.
In the past, researchers have had trouble creating intelligent robots that replicate cutting. One challenge: in the real world, no two objects are the same, and current robotic cutting systems struggle with variation. To overcome this, the team devised a unique approach to simulate cutting by introducing springs between the two halves of the object being cut, represented by a mesh. These springs are weakened over time in proportion to the force exerted by the knife on the mesh.
"What makes ours a special kind of simulator is that it is 'differentiable,' which means that it can help us automatically tune these simulation parameters from real-world measurements," said lead author Eric Heiden, a PhD in computer science student at USC. "That's important because closing this reality gap is a significant challenge for roboticists today. Without this, robots may never break out of simulation into the real world."
To transfer skills from simulation to reality, the simulator must be able to model a real system. In one of the experiments, the researchers used a dataset of force profiles from a physical robot to produce highly accurate predictions of how the knife would move in real life. In addition to applications in the food processing industry, where robots could take over dangerous tasks like repetitive cutting, the simulator could improve force haptic feedback accuracy in surgical robots, helping to guide surgeons and prevent injury.
"Here, it is important to have an accurate model of the cutting process and to be able to realistically reproduce the forces acting on the cutting tool as different kinds of tissue are being cut," said Heiden. "With our approach, we are able to automatically tune our simulator to match such different types of material and achieve highly accurate simulations of the force profile." In ongoing research, the team is applying the system to real-world robots.
ELSE PRESS RELEASES FROM THIS DATE:
New quantum research gives insights into how quantum light can be mastered
2021-07-21
Los Alamos, N.M., July 21, 2021--A team of scientists at Los Alamos National Laboratory propose that modulated quantum metasurfaces can control all properties of photonic qubits, a breakthrough that could impact the fields of quantum information, communications, sensing and imaging, as well as energy and momentum harvesting. The results of their study were released yesterday in the journal Physical Review Letters, published by the American Physical Society.
"People have studied classical metasurfaces for a long time," says Diego Dalvit, who works in the Condensed Matter and Complex Systems group at the Laboratory's Theoretical Division. "But we came up with this new idea, which was to modulate in time and space the optical properties of ...
New framework applies machine learning to atomistic modeling
2021-07-21
Northwestern University researchers have developed a new framework using machine learning that improves the accuracy of interatomic potentials -- the guiding rules describing how atoms interact -- in new materials design. The findings could lead to more accurate predictions of how new materials transfer heat, deform, and fail at the atomic scale.
Designing new nanomaterials is an important aspect of developing next-generation devices used in electronics, sensors, energy harvesting and storage, optical detectors, and structural materials. To design these materials, researchers create interatomic potentials through atomistic modeling, a computational approach that predicts how these materials behave by accounting for their ...
A history of African dust
2021-07-21
In a recently published paper, a research team, led by University of Miami (UM) Rosenstiel School of Marine and Atmospheric Science Professor Emeritus Joseph M. Prospero, chronicles the history of African dust transport, including three independent "first" discoveries of African dust in the Caribbean Basin in the 1950s and 1960s.
Every year, mineral-rich dust from North Africa's Sahara Desert is lifted into the atmosphere by winds and carried on a 5,000-mile journey across the North Atlantic to the Americas. African dust contains iron, phosphorus and other important nutrients that are essential for life in marine and terrestrial ...
How a unique sponge 'goes with the flow' could improve man-made structures
2021-07-21
BROOKLYN, New York, Weekday, Month xx, 2021 - The remarkable structural properties of the Venus' flower basket sponge (E. aspergillum) might seem fathoms removed from human-engineered structures. However, insights into how the organism's latticework of holes and ridges influences the hydrodynamics of seawater in its vicinity could lead to advanced designs for buildings, bridges, marine vehicles and aircraft, and anything that must respond safely to forces imposed by the flow of air or water.
While past research has investigated the structure of the sponge, there have been few studies of the hydrodynamic fields surrounding and penetrating the organism, and whether, besides improving its mechanical ...
Team streamlines neural networks to be more adept at computing on encrypted data
2021-07-21
BROOKLYN, New York, Wednesday, July 21, 2021 - This week, at the 38th International Conference on Machine Learning (ICML 21), researchers at the END ...
Dynamic heart model mimics hemodynamic loads, advances engineered heart tissue technology
2021-07-21
Efforts to understand cardiac disease progression and develop therapeutic tissues that can repair the human heart are just a few areas of focus for the Feinberg research group at Carnegie Mellon University. The group's latest dynamic model, created in partnership with collaborators in the Netherlands, mimics physiologic loads on engineering heart muscle tissues, yielding an unprecedented view of how genetics and mechanical forces contribute to heart muscle function.
"Our lab has been working for a long time on engineering and building human heart muscle tissue, so we can better ...
Researchers find immune component to rare neurodegenerative disease
2021-07-21
UT Southwestern researchers have identified an immune protein tied to the rare neurodegenerative condition known as Niemann-Pick disease type C. The END ...
New study confirms relationship between toxic pollution, climate risks to human health
2021-07-21
For more than 30 years, scientists on the U.N.'s Intergovernmental Panel on Climate Change have focused on human-induced climate change. Their fifth assessment report led to the Paris Agreement in 2015 and, shortly after, a special report on the danger of global warming exceeding 1.5 degrees Celsius above pre-industrial levels. The Nobel Prize-winning team stressed that mitigating global warming "would make it markedly easier to achieve many aspects of sustainable development, with greater potential to eradicate poverty and reduce inequalities."
In a first-of-its-kind study that combines assessments of the risks of toxic emissions (e.g., fine particulate matter), ...
Exoskeletons have a problem: They can strain the brain
2021-07-21
COLUMBUS, Ohio - Exoskeletons - wearable devices used by workers on assembly lines or in warehouses to alleviate stress on their lower backs - may compete with valuable resources in the brain while people work, canceling out the physical benefits of wearing them, a new study suggests.
The study, published recently in the journal Applied Ergonomics, found that when people wore exoskeletons while performing tasks that required them to think about their actions, their brains worked overtime and their bodies competed with the exoskeletons rather than working in harmony with them. The study indicates that exoskeletons may place enough burden on the brain that potential benefits to the body are negated.
"It's almost like dancing with a really bad partner," said ...
New approach eradicates breast cancer in mice
2021-07-21
CHAMPAIGN, Ill. -- A new approach to treating breast cancer kills 95-100% of cancer cells in mouse models of human estrogen-receptor-positive breast cancers and their metastases in bone, brain, liver and lungs. The newly developed drug, called ErSO, quickly shrinks even large tumors to undetectable levels.
Led by scientists at the University of Illinois Urbana-Champaign, the research team reports the findings in the journal Science Translational Medicine.
"Even when a few breast cancer cells do survive, enabling tumors to regrow over several months, the tumors that regrow remain completely ...
LAST 30 PRESS RELEASES:
Cellular hazmat team cleans up tau. Could it prevent dementia?
Innovation Crossroads startup revolutionizes wildfire prevention through grid hardening
ICCUB astronomers lead the most ambitious study of runaway massive stars in the Milky Way
Artificial Intelligence can generate a feeling of intimacy
Antidepressants not associated with serious complications from TBI
Evasive butterfly mimicry reveals a supercharged biodiversity feedback loop
Hearing angry or happy human voices is linked to changes in dogs’ balance
Microplastics are found in a third of surveyed fish off the coasts of remote Pacific Islands
De-stigmatizing self-reported data in health care research
US individuals traveling from strongly blue or red US counties may favor everyday travel to like-minded destinations
Study reveals how superionic state enables long-term water storage in Earth's interior
AI machine learning can optimize patient risk assessments
Efficacy of immunosuppressive regimens for survival of stem cell-derived grafts
Glowing bacterial sensors detect gut illness in mice before symptoms emerge
GLP-1 RAs and prior major adverse limb events in patients with diabetes
Life-course psychosocial stress and risk of dementia and stroke in middle-aged and older adults
Cells have a built-in capacity limit for copying DNA, and it could impact cancer treatment
Study finds longer hospital stays and higher readmissions for young adults with complex childhood conditions
Study maps how varied genetic forms of autism lead to common features
New chip-sized, energy-efficient optical amplifier can intensify light 100 times
New light-based platform sets the stage for future quantum supercomputers
Pesticides significantly affect soil life and biodiversity
Corals sleep like us, but their symbiosis does not rest
Huayuan biota decodes Earth’s first Phanerozoic mass extinction
Beyond Polymers: New state-of-the-art 3D micro and nanofabrication technique overcomes material limitations
New platform could develop vaccines faster than ever before
TF-rs1049296 C>T variant modifies the association between hepatic iron stores and liver fibrosis in metabolic dysfunction-associated steatotic liver disease
ASH publishes clinical practice guidelines on diagnosis of light chain amyloidosis
SLAS receives grant from Alfred P. Sloan Foundation to develop lab automation educational guidelines
Serum interleukin-8 for differentiating invasive pulmonary aspergillosis from bacterial pneumonia in patients with HBV-associated acute-on-chronic liver failure
[Press-News.org] New simulator helps robots sharpen their cutting skillsA simulation engine developed by University of Southern California and NVIDIA researchers predicts the forces acting on a knife as it cuts through soft materials, a capability that could have applications for safer food processing and surgical robotics