The human visual system has long been a source of inspiration for computer vision researchers, who aim to develop machines that can see and understand the world around them with the same level of efficiency and accuracy as humans. While machine vision systems have made significant progress in recent years, they still face major challenges when it comes to processing vast amounts of visual data while consuming minimal power.

One approach to overcoming these hurdles is through neuromorphic computing, which mimics the structure and function of biological neural systems. However, two major challenges persist: achieving color recognition comparable to human vision, and eliminating the need for external power sources to minimize energy consumption.

A recent breakthrough by a research team led by Associate Professor Takashi Ikuno from Tokyo University of Science has addressed these issues with a groundbreaking solution. Their self-powered artificial synapse is capable of distinguishing colors with remarkable precision, making it particularly suitable for edge computing applications where energy efficiency is crucial.

The device integrates two different dye-sensitized solar cells that respond differently to various wavelengths of light, generating its electricity via solar energy conversion. This self-powering capability makes it an attractive solution for industries such as autonomous vehicles, healthcare, and consumer electronics, where visual recognition capabilities are essential but power consumption is limited.

The researchers demonstrated the potential of their device in a physical reservoir computing framework, recognizing different human movements recorded in red, green, and blue with an impressive 82% accuracy. This achievement has significant implications for various industries, including autonomous vehicles, which could utilize these devices to efficiently recognize traffic lights, road signs, and obstacles.

In healthcare, self-powered artificial synapses could power wearable devices that monitor vital signs like blood oxygen levels with minimal battery drain. For consumer electronics, this technology could lead to smartphones and augmented/virtual reality headsets with dramatically improved battery life while maintaining sophisticated visual recognition capabilities.

The realization of low-power machine vision systems with color discrimination capabilities close to those of the human eye is within reach, thanks to this breakthrough research. The potential applications of self-powered artificial synapses are vast, and their impact will be felt across various industries in the years to come.

The University of Nebraska-Lincoln engineering team has made significant strides in developing soft robotics and wearable systems inspired by human and plant skin’s ability to self-heal injuries. Led by engineer Eric Markvicka, the team presented a groundbreaking paper at the IEEE International Conference on Robotics and Automation that showcased their innovative approach to creating an intelligent, self-healing artificial muscle.

The team’s strategy overcomes the long-standing problem of replicating traditional rigid systems using soft materials and incorporating nature-inspired design principles. Their multi-layer architecture enables the system to identify damage, pinpoint its location, and autonomously initiate a self-repair mechanism – all without external intervention.

The “muscle” or actuator features three layers: a damage detection layer composed of liquid metal microdroplets embedded in silicone elastomer, a self-healing component that uses thermoplastic elastomer to seal the wound, and an actuation layer that kick-starts the muscle’s motion when pressurized with water.

To begin the process, the team induces monitoring currents across the damage detection layer, which triggers formation of an electrical network between traces. Puncture or pressure damage causes this network to form, allowing the system to recognize and respond to the damage.

The next step is using electromigration – a phenomenon traditionally viewed as a hindrance in metallic circuits – to erase the newly formed electrical footprint. By further ramping up the current, the team can induce electromigration and thermal failure mechanisms that reset the damage detection network, effectively completing one cycle of damage and repair.

This breakthrough has far-reaching implications for various industries, particularly in agricultural states where robotics systems frequently encounter sharp objects. It could also revolutionize wearable health monitoring devices that must withstand daily wear and tear.

The technology has the potential to transform society more broadly by reducing electronic waste and mitigating environmental harm caused by consumer-based electronics’ short lifespans. Most consumer electronics have a lifespan of only one or two years, contributing billions of pounds of toxic waste each year.

“If we can begin to create materials that are able to passably and autonomously detect when damage has happened, and then initiate these self-repair mechanisms, it would really be transformative,” Markvicka said.

Rewritten Article:

In a breakthrough that’s straight out of science fiction, a team of engineers at Caltech has developed a real-life Transformer that can morph in mid-air, allowing it to smoothly transition from flying to rolling on the ground. This innovative technology has far-reaching implications for commercial delivery systems and robotic explorers, making it an exciting development in the field of robotics.

The new robot, dubbed ATMO (aerially transforming morphobot), uses four thrusters to fly but can transform into a ground-rolling configuration using a single motor that lifts its thrusters up or down. This unique design allows ATMO to change its shape and function seamlessly, enabling it to adapt to various environments and situations.

According to Ioannis Mandralis, the lead author of the research paper published in Communications Engineering, “We designed and built a new robotic system inspired by nature – by the way that animals can use their bodies in different ways to achieve different types of locomotion.” For example, birds fly and then change their body morphology to slow themselves down and avoid obstacles. Mandralis adds, “Having the ability to transform in the air unlocks a lot of possibilities for improved autonomy and robustness.”

However, mid-air transformation also poses challenges due to complex aerodynamic forces that come into play both because the robot is close to the ground and because it is changing its shape as it morphs. Mory Gharib, the Hans W. Liepmann Professor of Aeronautics and Medical Engineering, notes that “Even though it seems simple when you watch a bird land and then run, in reality this is a problem that the aerospace industry has been struggling to deal with for probably more than 50 years.”

To better understand these complex aerodynamic forces, the researchers ran tests in Caltech’s drone lab using load cell experiments and smoke visualization. They fed those insights into the algorithm behind a new control system they created for ATMO, which uses advanced model predictive control to continuously predict how the system will behave in the near future and adjust its actions accordingly.

“The control algorithm is the biggest innovation in this paper,” Mandralis says. “Quadrotors use particular controllers because of how their thrusters are placed and how they fly. Here we introduce a dynamic system that hasn’t been studied before. As soon as the robot starts morphing, you get different dynamic couplings – different forces interacting with one another. And the control system has to be able to respond quickly to all of that.”

The potential applications of ATMO are vast and exciting, from commercial delivery systems to robotic explorers. With its unique ability to transform in mid-air and adapt to various environments, this technology has the potential to revolutionize the field of robotics and beyond.