Catalyzing next-generation artificial intelligence through neuroai

A Zador, S Escola, B Richards, B Ölveczky… - Nature …, 2023‏ - nature.com
Neuroscience has long been an essential driver of progress in artificial intelligence (AI). We
propose that to accelerate progress in AI, we must invest in fundamental research in …

Soft pneumatic actuators: A review of design, fabrication, modeling, sensing, control and applications

MS Xavier, CD Tawk, A Zolfagharian, J Pinskier… - IEEE …, 2022‏ - ieeexplore.ieee.org
Soft robotics is a rapidly evolving field where robots are fabricated using highly deformable
materials and usually follow a bioinspired design. Their high dexterity and safety make them …

A survey of embodied ai: From simulators to research tasks

J Duan, S Yu, HL Tan, H Zhu… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
There has been an emerging paradigm shift from the era of “internet AI” to “embodied AI,”
where AI algorithms and agents no longer learn from datasets of images, videos or text …

Physical reservoir computing—an introductory perspective

K Nakajima - Japanese Journal of Applied Physics, 2020‏ - iopscience.iop.org
Understanding the fundamental relationships between physics and its information-
processing capability has been an active research topic for many years. Physical reservoir …

[HTML][HTML] Recent advances in physical reservoir computing: A review

G Tanaka, T Yamane, JB Héroux, R Nakane… - Neural Networks, 2019‏ - Elsevier
Reservoir computing is a computational framework suited for temporal/sequential data
processing. It is derived from several recurrent neural network models, including echo state …

The neuromechanics of animal locomotion: From biology to robotics and back

P Ramdya, AJ Ijspeert - Science Robotics, 2023‏ - science.org
Robotics and neuroscience are sister disciplines that both aim to understand how agile,
efficient, and robust locomotion can be achieved in autonomous agents. Robotics has …

Designing neural networks through neuroevolution

KO Stanley, J Clune, J Lehman… - Nature Machine …, 2019‏ - nature.com
Much of recent machine learning has focused on deep learning, in which neural network
weights are trained through variants of stochastic gradient descent. An alternative approach …

Trends and challenges in robot manipulation

A Billard, D Kragic - Science, 2019‏ - science.org
BACKGROUND Humans have a fantastic ability to manipulate objects of various shapes,
sizes, and materials and can control the objects' position in confined spaces with the …

Biomedical applications of soft robotics

M Cianchetti, C Laschi, A Menciassi… - Nature Reviews Materials, 2018‏ - nature.com
Soft robotics enables the design of soft machines and devices at different scales. The
compliance and mechanical properties of soft robots make them especially interesting for …

[HTML][HTML] Physical intelligence as a new paradigm

M Sitti - Extreme Mechanics Letters, 2021‏ - Elsevier
Intelligence of physical agents, such as human-made (eg, robots, autonomous cars) and
biological (eg, animals, plants) ones, is not only enabled by their computational intelligence …