Artificial brains could imitate biological neural networks and make robots smarter. The latest developments in robotics have made it possible to perform complex tasks that were previously risky for human workers. There is no surprise that robots are gaining unparalleled interest as companies are looking to deliver perfect customer experience. Today the robots have the potential to pick up a soft drink can or cooking food, exactly the way the humans do. Still, they have to learn a lot more things as they require to locate an object, infer its shape, to determine the right amount of strength, and hold the object without letting it slip. To do such tasks properly, robots need an extraordinary sense of touch equivalent to the human skin.
In this, a team of computer scientists and materials engineers from the National University of Singapore has recently developed a sensory integrated artificial brain system. The system mimics biological neural networks and can work on a power-efficient neuromorphic processor, such as the Loihi chip from Intel. The system also comprehends artificial skin and vision sensors that can equip a robot with the ability to draw exact conclusions about an object it grasps based on the data collected by the vision and touch sensors in real-time. As the robotic manipulation field had made remarkable progress in recent years, fusing both vision and tactile information to provide a highly precise response in milliseconds remains a technology challenge.
Researchers nowadays are exploring to enable a sense of touch for robots just like humans. In recent years we have seen a great stride towards it. The researchers from NUS built Asynchronous Coded Electronic Skin (ACES), an advanced artificial skin for the latest robotic system. The skin has ultra-high responsiveness and defensiveness to damage and can be matched with any kind of sensor skin layers to work effectively as an electronic skin. ACES is built of a network of sensors attached through a single electrical conductor and varies from current electronic skins that have interconnected wiring systems that can make them sensitive to damage and detailed to scale up. This novel sensor senses touch over 1,000 times rapidly than the human sensory nervous system. Scientists across the world are exploring ways to give robots a sense of touch just like humans.