Robot learning

Robot learning is a research field at the intersection of machine learning and robotics. It studies techniques allowing a robot to acquire novel skills or adapt to its environment through learning algorithms. The embodiment of the robot, situated in a physical embedding, provides at the same time specific difficulties (e.g. high-dimensionality, real time constraints for collecting data and learning) and opportunities for guiding the learning process (e.g. sensorimotor synergies, motor primitives).

Example of skills that are targeted by learning algorithms include sensorimotor skills such as locomotion, grasping, active object categorization, as well as interactive skills such as joint manipulation of an object with a human peer, and linguistic skills such as the grounded and situated meaning of human language. Learning can happen either through autonomous self-exploration or through guidance from a human teacher, like for example in robot learning by imitation.

Robot learning can be closely related to adaptive control, reinforcement learning as well as developmental robotics which considers the problem of autonomous lifelong acquisition of repertoires of skills. While machine learning is frequently used by computer vision algorithms employed in the context of robotics, these applications are usually not referred to as "robot learning".

Maya Cakmak, assistant professor of computer science and engineering at the University of Washington, is trying to create a robot that learns by imitating - a technique called "programming by demonstration". A researcher shows it a cleaning technique for the robot's vision system and it generalizes the cleaning motion from the human demonstration as well as identifying the "state of dirt" before and after cleaning.

Similarly the Baxter industrial robot can be be taught how to do something by grabbing its arm and showing it the desired movements. It can also use deep learning to teach itself to grasp an unknown object.

In Telex's "Million Object Challenge" the goal is robots that learn how to spot and handle simple items and upload their data to the cloud to allow other robots to analyze and use the information.

...
Wikipedia