Skip to Main Content
This paper presents a new approach of task-oriented developmental learning for humanoid robots. It is capable of setting up multiple tasks representation automatically using real-time experiences, thereby enabling a robot to handle various tasks concurrently without the need of predefining the tasks. In the approach, an evolvable partitioned tree structure is used for task representation knowledgebase that is partitioned into different task domains. The search/update of task knowledge is focused on a particular task branch, without considering the whole task knowledgebase that is often large and time consuming in the process. A prototype of the proposed task-oriented developmental learning is designed and implemented using a Khepera robot. Experimental results show that the robot can redirect itself to new tasks through interactions with the environment, and a learned task can be easily updated in order to meet varying specifications in the real world.