Date of Submission

Spring 2015

Academic Programs and Concentrations

Computer Science; Mind, Brain, and Behavior

Project Advisor 1

Keith O'Hara

Abstract/Artist's Statement

Research on developing personal humanoid robots that can assist, educate, protect and entertain has been rising for the past 50 years. To integrate themselves into human environments these machines will require high levels of autonomy that can only be developed and maintained through learning. Common learning approaches focus on teaching robots through specifically adapted methods that process input from their environment and improve using a feedback system. Some of them attempt to integrate human interaction into the learning process to improve the efficiency and adaptability of the robot’s actions and social behavior. This project investigates one possible approach to task-based learning on a NAO humanoid robot. In this case, the reproduction of handwritten characters is chosen. Using image processing methods to gather input data and turn it into a movement trajectory, the robot is expected to adapt its writing according to human feedback. This remains a work in progress.

Open Access Agreement

On-Campus only

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.

This work is protected by a Creative Commons license. Any use not permitted under that license is prohibited.

Bard Off-campus Download

Bard College faculty, staff, and students can login from off-campus by clicking on the Off-campus Download button and entering their Bard username and password.

Share

COinS