Showing posts with label human-like. Show all posts
Showing posts with label human-like. Show all posts

Tuesday, September 20, 2022

Whatever Happened To Good Old Fashioned Robots


Twisted soft robots navigate mazes without human or computer guidance
May 2022, phys.org

Physical intelligence vs Computational intelligence, active matter, and the Internet of Everything.
Also, Translucent Rotini:

The soft robots are made of liquid crystal elastomers in the shape of a twisted ribbon, resembling translucent rotini. 

When you place the ribbon on a surface that is at least 55 degrees Celsius (131 degrees Fahrenheit), which is hotter than the ambient air, the portion of the ribbon touching the surface contracts, while the portion of the ribbon exposed to the air does not. This induces a rolling motion in the ribbon. And the warmer the surface, the faster it rolls.

"It's much like the robotic vacuums that many people use in their homes," Yin says. "Except the soft robot we've created draws energy from its environment and operates without any computer programming."

via North Carolina State University: Twisting for Soft Intelligent Autonomous Robot in Unstructured Environments, Proceedings of the National Academy of Sciences (2022). DOI: 10.1073/pnas.2200265119



A marsupial robotic system that combines a legged and an aerial robot
Jun 2022, phys.org

"Our idea comes from a very simple concept: the complementarity of walking and flying robots," De Petris explained.

via DARPA Subterranean Challenge and winning team CERBERUS of NTNU, UNR, ETH Zurich, UC Berkley, Oxford and Flyability: Paolo De Petris et al, Marsupial walking-and-flying robotic deployment for collaborative exploration of unknown environments. arXiv:2205.05477v1 [cs.RO], arxiv.org/abs/2205.05477


Robotic lightning bugs take flight
Jun 2022, phys.org

Electroluminescent soft artificial muscles for flying, insect-scale robots that communicate with each other. 

These researchers previously demonstrated a new fabrication technique to build soft actuators, or artificial muscles, that flap the wings of the robot. and are made by alternating ultrathin layers of elastomer and carbon nanotube electrode in a stack and then rolling it into a squishy cylinder. When a voltage is applied to that cylinder, the electrodes squeeze the elastomer, and the mechanical strain flaps the wing. Electroluminescent zinc sulfate particles into the elastomeric artificial muscles. 

via MIT: Suhan Kim et al, FireFly: An Insect-Scale Aerial Robot Powered by Electroluminescent Soft Artificial Muscles, IEEE Robotics and Automation Letters (2022). DOI: 10.1109/LRA.2022.3179486


Robotic arms connected directly to brain of partially paralyzed man allows him to feed himself
Jul 2022, phys.org

A person with very limited upper body mobility, who hasn't been able to use his fingers in about 30 years, has just fed himself dessert using his mind and some smart robotic hands.

The new paper outlines an innovative model for shared control that enables a human to maneuver a pair of robotic prostheses with minimal mental input. "This shared control approach is intended to leverage the intrinsic capabilities of the brain machine interface and the robotic system, creating a 'best of both worlds' environment where the user can personalize the behavior of a smart prosthesis,"

via Johns Hopkins Applied Physics Laboratory and the Department of Physical Medicine and Rehabilitation in the Johns Hopkins School of Medicine: Shared control of bimanual robotic limbs with a BMI for self-feeding, Frontiers in Neurorobotics (2022). DOI: 10.3389/fnbot.2022.918001


Extra 'eye' movements are the key to better self-driving cars
Jul 2022, phys.org
 
With the help of Levy patterns, also called a foraging behavior model:

When tested with shifted images that mimicked naturally altered visual input that would occur when the eyes move, performance dropped drastically to chance level. Classification improved significantly after training the network with shifted images, as long as the direction and size of the eye movements that resulted in the shift were also included. Adding the eye movements and their corresponding motor commands to the network model allowed the system to better cope with visual noise in the images. "This advancement will help avoid dangerous mistakes in machine vision,"

via RIKEN: Andrea Benucci et al, Motor-related signals support localization invariance for stable visual perception, PLOS Computational Biology (2022). DOI: 10.1371/journal.pcbi.1009928

Learning From Scratch


Engineers build a robot that learns to understand itself, rather than the world around it
Jul 2022, phys.org

A Columbia Engineering team announced today they have created a robot that—for the first time—is able to learn a model of its entire body from scratch, without any human assistance. In a new study published by Science Robotics, the researchers demonstrate how their robot created a kinematic model of itself, and then used its self-model to plan motion, reach goals, and avoid obstacles in a variety of situations. It even automatically recognized and then compensated for damage to its body.

The researchers placed a robotic arm inside a circle of five streaming video cameras. The robot watched itself through the cameras as it undulated freely.

After about three hours, the robot stopped. Its internal deep neural network had finished learning the relationship between the robot's motor actions and the volume it occupied in its environment.

Yeah I'm creeped out.

via Columbia University School of Engineering and Applied Science: Boyuan Chen, Fully body visual self-modeling of robot morphologies, Science Robotics (2022). DOI: 10.1126/scirobotics.abn1944.



DayDreamer: An algorithm to quickly teach robots new behaviors in the real world
Jul 2022, phys.org

Their approach, introduced in a paper pre-published on arXiv, is based on learning models of the world that allow robots to predict the outcomes of their movements and actions.

The algorithm builds a world model based on its past "experiences" to teach robots new behaviors based on "imagined" interactions, reducing the need for extensive trial and error training in the real-world.

"We saw the robots adapt to changes in lighting conditions, such as shadows moving with the sun over the course of a day," 

via University of California, Berkeley: Philipp Wu et al, DayDreamer: world models for physical robot learning. arXiv:2206.14176v1 [cs.RO], arxiv.org/abs/2206.14176


Post Script:
"A promising direction would be to train the robots to explore their surroundings in the absence of a task through artificial curiosity, and then later adapt to solve tasks specified by users even faster," Hafner added.

Further Readings:
Ted Chiang's Digients (in Lifecycle of Software Objects)