Robots learn to create language
Researchers at the University of Queensland and Queensland University of Technology have created a pair of robots who are creating their own language. The bots, which are being taught how to speak but not given specific languages, are learning to create a lexicon of their own
The go-to game allows the agents to test their toponymic lexicon by specifying a target location (B) to meet at. Image credit: Ruth Schulz
Here's the basic gist of how it works. The Lingodroids assign a randomly chosen syllable combination to name a specific location. Once they've agreed on the meaning of that initial word, they have the foundation for a language. From there the robots continue to make up and agree on words for different spots, directions, and approximate spatial distances (near, far, medium-far, and so on). The result is this exceedingly polite conversation in Lingodroidese:
Lingodroids
Once they have a toponymic lexicon, they can expand their concepts by playing generative games to form concepts for distances and directions.
With distances and directions, they can now expand the places they can talk about, and actually meet at these new locations, should they become accessible, for example, if office doors are opened.
Lingodroid Robots Invent Their Own Spoken Language - IEEE Spectrum
In the future, researchers hope to enable the Lingodroids to "talk" about even more elaborate concepts, like descriptions of how to get to a place or the accessibility of places on the map. Ultimately, techniques like this may help robots to communicate with each other more effectively, and may even enable novel ways for robots to talk to humans.
Schulz and her colleagues -- Arren Glover, Michael J. Milford, Gordon Wyeth, and Janet Wiles -- describe their work in a paper, "Lingodroids: Studies in Spatial Cognition and Language," presented last week at the IEEE International Conference on Robotics and Automation (ICRA), in Shanghai.











