In Canadian author Margaret Atwood’s book “Blind Assassins,” she says that “touch comes before sight, before speech. It’s the first language and the last, and it always tells the truth.”
While our sense of touch gives us a channel to feel the physical world, our eyes help us immediately understand the full picture of these tactile signals.
Robots that have been programmed to see or feel can’t use these signals quite as interchangeably. To better bridge this sensory gap, researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have come up with a predictive artificial intelligence (AI) that can learn to see by touching, and learn to feel by seeing.
The team’s system can create realistic tactile signals from visual inputs, and predict which object and what part is being touched directly from those tactile inputs. They used a KUKA robot arm with a special tactile sensor called GelSight, designed by another group at MIT.
Using a simple web camera, the team recorded nearly 200 objects, such as tools, household products, fabrics, and more, being touched more than 12,000 times. Breaking those 12,000 video clips down into static frames, the team compiled “VisGel,” a dataset of more than 3 million visual/tactile-paired images.
“By looking at the scene, our model can imagine the feeling of touching a flat surface or a sharp edge”, says Yunzhu Li, CSAIL PhD student and lead author on a new paper about the system.
“By blindly touching around, our model can predict the interaction with the environment purely from tactile feelings. Bringing these two senses together could empower the robot and reduce the data we might need for tasks involving manipulating and grasping objects.”
Recent work to equip robots with more human-like physical senses, such as MIT’s 2016 project using deep learning to visually indicate sounds, or a model that predicts objects’ responses to physical forces, both use large datasets that aren’t available for understanding interactions between vision and touch.
The team’s technique gets around this by using the VisGel dataset, and something called generative adversarial networks (GANs).
GANs use visual or tactile images to generate images in the other modality. They work by using a “generator” and a “discriminator” that compete with each other, where the generator aims to create real-looking images to fool the discriminator. Every time the discriminator “catches” the generator, it has to expose the internal reasoning for the decision, which allows the generator to repeatedly improve itself.
Vision to touch
Humans can infer how an object feels just by seeing it. To better give machines this power, the system first had to locate the position of the touch, and then deduce information about the shape and feel of the region.
The reference images — without any robot-object interaction — helped the system encode details about the objects and the environment. Then, when the robot arm was operating, the model could simply compare the current frame with its reference image, and easily identify the location and scale of the touch.
This might look something like feeding the system an image of a computer mouse, and then “seeing” the area where the model predicts the object should be touched for pickup — which could vastly help machines plan safer and more efficient actions.
Touch to vision
For touch to vision, the aim was for the model to produce a visual image based on tactile data. The model analyzed a tactile image, and then figured out the shape and material of the contact position. It then looked back to the reference image to “hallucinate” the interaction.
For example, if during testing the model was fed tactile data on a shoe, it could produce an image of where that shoe was most likely to be touched.
This type of ability could be helpful for accomplishing tasks in cases where there’s no visual data, like when a light is off, or if a person is blindly reaching into a box or unknown area.
Two Apps to monitor quarantined individuals in Thailand
Two mobile applications, namely “AOT Airports” and “SydeKick for ThaiFightCOVID”, can now be used to track quarantined passengers and people who are under home quarantine.
The impact of COVID-19 on the tourism sector in Thailand is apparent. The number of passengers using Suvarnabhumi Airport has declined sharply, as many countries have closed their borders and airlines have suspended flights.(more…)
Cyber incidents top most important business risks for Asia-Pacific companies
For the first time ever, Cyber incidents (35% of responses) rank as the most important business risk in Asia-Pacific in the ninth Allianz Risk Barometer 2020
Alibaba confirms $13bn listing in Hong Kong
Alibaba will offer 500 million shares at a maximum of HK$188 apiece, the company said. The number eight is considered auspicious in China.
Chinese technology giant Alibaba on Friday confirmed plans to list in Hong Kong in what it called a $13 billion vote of confidence in the turbulent city’s markets and a step forward in its plans to go global.(more…)
What is Forex Trading and how it works?
Why do the investors choose Forex trading? Forex trading is traded by currency pairs. This is because all currency trading...
APRIL International Care opens up TeleHEALTH service to address Coronavirus worries
The TeleHEALTH service means policyholders do not have to leave their home or workplace to “see” a doctor, with a...
Thailand rolls out New Investment Measures to Boost Economy
The new definition of qualified applicants now includes businesses that have not previously received BOI promotion privileges as long as...