Learning confidence in a visual task

Learning a visual task by genetic programming

This work describes a hand-eye system that can learn from its experience. The task is to visually guide the hand to reach a target while avoiding obstacles. The motion planning problem is solved by genetic programming. The system learns the forward kinematics by building a lookup table and uses it in the simulation run to generate robot programs that perform the task. The genetically created pr...

Reinforcement Learning of a Simple Visual Task

Raw visual data must be interpreted in some fashion to result in spatial perception. Some models for this interpretation hypothesize visual routines as underlying mechanisms for distilling the properties of a scene. Visual routines must determine these properties quickly without higher–level information. We present an approach for learning an example of a visual routine using reinforcement. Rat...

Task and object learning in visual recognition

Human performance in object recognition changes with practice, even in the absence of feedback to the subject. The nature of the change can reveal important properties of the process of recognition. We report an experiment designed to distinguish between non-specific task learning and object-specific practice effects. The results of the experiment support the notion that learning through modifi...

Task and Object Learning in Visual Recognition

Learning task goals interactively with visual demonstrations

Humans are extremely good at quickly teaching and learning new tasks through situated instructions; tasks such as learning a novel game or household chore. From studying such instructional interactions, we have observed that humans excel at communicating information through multiple modalities, including visual, linguistic, and physical ones. Rosie is a tabletop robot implemented in the Soar ar...