Engineering in Action
Training AI not to misbehave
As robots, self-driving cars and other intelligent machines weave AI into everyday life, a new way of designing algorithms can help machine-learning developers build in safeguards against specific, undesirable outcomes like racial and gender bias, to help earn societal trust. Video created by Deboki Chakravarti.
Can tiny medical implants treat disease?
Using ultrasound technology that functions by signaling microsized implants inside the body to communicate could revolutionize personalized, on-demand health care and lessen the need for traumatic surgeries. For more information on this research, read the Stanford Engineering article: http://stanford.io/2AVAraK For more information on the Arbabian Lab, visit their website: https://arbabianlab.stanford.edu/research/implants
Stretchable electrodes pave way for flexible electronics
This robotic test instrument is stretching a flexible electrode over a curved surface. The nearly-transparent electrode is based on a special plastic developed in the lab of Stanford chemical engineer Zhenan Bao. Even while being stretched the plastic continues to send electronic signals to the grid of transistors at the top of the curve. The stiff wires in today’s electronics can’t do this. The stretchy electrode helps pave the way for flexible electronics.
A time-lapse look at how Alzheimer’s spreads
This computer simulation shows how two forms of Alzheimer’s disease spread through the brain over a 30 year period. The orange shading shows how clumps of defective amyloid-beta proteins form memory-destroying plaques. The blue shading shows how defects involving the tau protein follow a different progression. The final sequences show how each of these contagions come to engulf the brain. Read the full story: https://stanford.io/dementia
Robot hand moves a ping pong ball
Stanford researchers developed the skin-like touch sensors that enable this robotic hand to deliver just the right amount of pressure to lift and move a ping pong ball without crushing it. In this demonstration they programmed the hand. One day they hope to create control systems to enable a robot to perceive the characteristics of objects and autonomously calculate how much force to apply. Video courtesy of the Bao Lab.
Robot gently touches a raspberry
Stanford researchers developed the skin-like sensor on the fingertip of this robotic hand, and programmed it to touch the fruit without damage. One day they hope to create control systems to enable a robot to perceive the characteristics of objects and autonomously calculate how much force to apply. Video courtesy of the Bao Lab. Read more here: stanford.io/2P94Ic8