Hod Lipson builds "self-aware" robots. Maze. A maze is a tour puzzle in the form of a complex branching passage through which the solver must find a route. The pathways and walls in a maze are fixed, and puzzles in which the walls and paths can change during the game are categorised as tour puzzles. The Cretan labyrinth is the oldest known maze.[1] Technically the maze is distinguished from the labyrinth, which has a single through-route with twists and turns but without branches, and is not designed to be as difficult to navigate.
In everyday speech, both maze and labyrinth denote a complex and confusing series of pathways.[2] Maze construction[edit] A small maze with one entrance and one exit Mazes have been built with walls and rooms, with hedges, turf, corn stalks, hay bales, books, paving stones of contrasting colors or designs, and brick,[3] or in fields of crops such as corn or, indeed, maize. Generating mazes[edit] Maze generation is the act of designing the layout of passages and walls within a maze. Solving mazes[edit] H. The Limits of Intelligence. Santiago Ramón y Cajal, the Spanish Nobel-winning biologist who mapped the neural anatomy of insects in the decades before World War I, likened the minute circuitry of their vision-processing neurons to an exquisite pocket watch.
He likened that of mammals, by comparison, to a hollow-chested grandfather clock. Indeed, it is humbling to think that a honeybee, with its milligram-size brain, can perform tasks such as navigating mazes and landscapes on a par with mammals. A honeybee may be limited by having comparatively few neurons, but it surely seems to squeeze everything it can out of them. At the other extreme, an elephant, with its five-million-fold larger brain, suffers the inefficiencies of a sprawling Mesopotamian empire. Signals take more than 100 times longer to travel between opposite sides of its brain—and also from its brain to its foot, forcing the beast to rely less on reflexes, to move more slowly, and to squander precious brain resources on planning each step. Harvard's Kilobot project does swarm robots on the cheap (video) Brain-like computing a step closer to reality. The development of 'brain-like' computers has taken a major step forward today with the publication of research led by the University of Exeter.
Published in the journal Advanced Materials and funded by the Engineering and Physical Sciences Research Council, the study involved the first ever demonstration of simultaneous information processing and storage using phase-change materials. This new technique could revolutionise computing by making computers faster and more energy-efficient, as well as making them more closely resemble biological systems. Computers currently deal with processing and memory separately, resulting in a speed and power 'bottleneck' caused by the need to continually move data around.
This is totally unlike anything in biology, for example in human brains, where no real distinction is made between memory and computation. Their study demonstrates conclusively that phase-change materials can store and process information simultaneously. Lingodroid Robots Invent Their Own Spoken Language. When robots talk to each other, they're not generally using language as we think of it, with words to communicate both concrete and abstract concepts.
Now Australian researchers are teaching a pair of robots to communicate linguistically like humans by inventing new spoken words, a lexicon that the roboticists can teach to other robots to generate an entirely new language. Ruth Schulz and her colleagues at the University of Queensland and Queensland University of Technology call their robots the Lingodroids. The robots consist of a mobile platform equipped with a camera, laser range finder, and sonar for mapping and obstacle avoidance. The robots also carry a microphone and speakers for audible communication between them. To understand the concept behind the project, consider a simplified case of how language might have developed. From this fundamental base, the robots can play games with each other to reinforce the language. Schulz and her colleagues -- Arren Glover, Michael J. The Paradox of Artificial Intelligence. What do we mean by "intelligence" in practical terms.
And once we adopt an operational definition does it defeat the whole idea of "artificial intelligence"? The solution might be to realize that intelligence isn't a property but a relationship. There is a longstanding problem that people working on artificial intelligence have had to cope with. Whenever you create your latest amazing program that does something that previously only a human could do then the intelligence sort of melts away as if it never was. Look at the early days when it seemed to be right to try to create artificial intelligence by writing programs that could play chess, say. Only of course once you have built a program that solves the chess problem you realise that it is nothing of the sort.
That is there are a set of problems that when approached using the wetware of the human brain seem to embody the idea of intelligent thought. So some attempts at creating artificial intelligence do nothing of the sort. Human speech recognition pathway identified. Neuroscientists at Georgetown University Medical Center (GUMC) have defined, for the first time, three different processing stages that a human brain needs to identify sounds such as speech — and discovered that they are the same as ones identified in non-human primates. In the June 22 issue of the Journal of Neuroscience, the researchers say their discovery — made possible with the help of 13 human volunteers who spent time in a functional MRI machine — could potentially offer important insights into what can go wrong when someone has difficulty speaking, which involves hearing voice-generated sounds, or understanding the speech of others. But more than that, the findings help shed light on the complex, and extraordinarily elegant, workings of the "auditory" human brain, says Josef Rauschecker, PhD, a professor in the departments of physiology/ biophysics and neuroscience and a member of the Georgetown Institute for Cognitive and Computational Sciences at GUMC.
Features - Evolving Pathfinding Algorithms Using Genetic Programming. Introduction Pathfinding AIs tend to fall short in one of two ways: either they are so incredibly effective and efficient that they don't convey intelligence as much as omniscience, or they are so incredibly inept that human observers can't help but feel frustration watching them. The first case is exemplified by an agent which ignores locally acceptable paths in favor of the ideal global path, thereby giving away the secret that it has knowledge of the entire map. The second case can be seen in a wide variety of stupid behavior, but my favorite example is the agent which travels along a river to avoid the relatively small penalty of crossing water, only to plow through an enemy camp and ultimately meet its doom.
Anyone familiar with real-time-strategy gaming has no doubt met this breed of pathfinder before. Genetic Programming Genetic programming is a technique which uses the genetic operators of reproduction, mutation and cross-breeding to find programs which solve a given problem. Lovotics, the new science of human-robot love. By harnessing a new sphere of science called “lovotics”, Hooman Samani, an artificial intelligence researcher at the Social Robotics Lab at the National University of Singapore, believes it is possible to engineer love between humans and robots. Across 11 research papers, Samani has outlined — and begun to develop — an extremely complex artificial intelligence that simulates psychological and biological systems behind human love.
To do this, Samani’s robots are equipped with artificial versions of the human “love” hormones — Oxytocin, Dopamine, Seratonin, and Endorphin — that can increase or decrease, depending on their state of love. On a psychological level, by using MRI scans of human brains to mirror the psychology of love, the robots are also equipped with an artificial intelligence that tracks their “affective state”; their level of affection for their human lover. Read more at Technology Review.