Turing Learning: a new robot system that can learn by observing

Turing Learning
An e-puck robot fitted with a black ‘skirt’ and a top marker for motion tracking.

In a recent study, scientists develop a new robot system that can learn knowledge through observation. The finding is published in Swarm Intelligence.

Researchers from The University of Sheffield in the UK and Harvard University conducted the study.

The new robot system, Turing Learning, is a novel system identification method to infer the behavior of natural or artificial systems.

Turing Learning simultaneously optimizes two computer programs, one representing models of the behavior of the system, and the other representing classifiers.

Researchers obtain two sets of data samples by observing the behavior of the system as well as the behaviors produced by the models.

The classifiers are rewarded for discriminating between these two sets, that is, for correctly categorizing data samples as either genuine or counterfeit.

Conversely, the models are rewarded for ‘tricking’ the classifiers into categorizing their data samples as genuine.

Unlike other methods for system identification, Turing Learning does not require predefined metrics to calculate the difference between the system and its models.

Researchers present two case studies with swarms of simulated robots and prove that the underlying behaviors cannot be inferred by a metric-based system identification method.

By contrast, Turing Learning infers the behaviors with high accuracy. It also produces a useful by-product—the classifiers—that can be used to detect abnormal behavior in the swarm.

Moreover, researchers find that Turing Learning also successfully infers the behavior of physical robot swarms.

The finding suggests that collective behaviors can be directly inferred from motion trajectories of individuals in the swarm, which may have significant implications for the study of animal collectives.

Furthermore, Turing Learning could prove useful whenever a behavior is not easily characterizable using metrics, making it suitable for a wide range of applications.

Follow Knowridge Science Report on Facebook, Twitter, and LinkedIn.

Citation: Li W, et al. (2016). Turing learning: a metric-free approach to inferring behavior and its application to swarms. Swarm Intelligence, published online. DOI: 10.1007/s11721-016-0126-1.
Figure legend: This Knowridge.com image is credited to Li W et al.