Motor babbling is a process of repeatedly performing a

random In common usage, randomness is the apparent or actual lack of pattern or predictability in events. A random sequence of events, symbols or steps often has no :wikt:order, order and does not follow an intelligible pattern or combination. Ind ...

motor command for a short duration. It is similar to the vocal babbling of infants, where the brain learns the relation between vocal muscle activities and the resulting sounds. However, it was found that the general motor-control system is already exploring itself in the womb, in animals, in a similar way. Originally, the random spasms and convulsions of the embryo were seen as the non-functional consequences of growth. Later it was realized that the motor system is already calibrating its sensorimotor system before birth. After birth, motor babbling in primates continues in the random grasping movements towards visual targets, training the eye-hand coordination system. These insights are used since the early nineteen nineties in models of biological movement control and in robotics. In robotics, it is a system of

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 ...

whereby a robotic system can autonomously develop an internal model of its self-body and its environment. Early work is by Kuperstein (1991) using a robot randomly positioning a stick in its workspace, while being observed by two cameras, using a

neural network A neural network is a network or circuit of biological neurons, or, in a modern sense, an artificial neural network, composed of artificial neurons or nodes. Thus, a neural network is either a biological neural network, made up of biological ...

(

multilayer perceptron A multilayer perceptron (MLP) is a fully connected class of feedforward artificial neural network (ANN). The term MLP is used ambiguously, sometimes loosely to mean ''any'' feedforward ANN, sometimes strictly to refer to networks composed of mul ...

) to associate poses of the stick with joint angles of the arm. This type of research has led to the research field of

developmental robotics Developmental robotics (DevRob), sometimes called epigenetics, epigenetic robotics, is a scientific field which aims at studying the developmental mechanisms, architectures and constraints that allow lifelong and open-ended learning of new skills a ...

. The random exploration of the motor-control state and its effects can lead to the identification of parameters for a

inverse kinematics In computer animation and robotics, inverse kinematics is the mathematical process of calculating the variable joint parameters needed to place the end of a kinematic chain, such as a robot manipulator or animation character's skeleton, in a g ...

and

inverse dynamics Inverse dynamics is an inverse problem. It commonly refers to either inverse rigid body dynamics or inverse structural dynamics. Inverse rigid-body dynamics is a method for computing forces and/or moments of force (torques) based on the kinematic ...

model, which the robot can use to find appropriate control signals, given a particular task that requires positioning and/or force control.

References

{{Reflist Humanoid robots Motor control

See also

References