Performance evaluation of sensorimotor primitives using eigenvector learning method

We present a method to evaluate the performance of an eigenvector learned sensorimotor primitive for mobile robots. At runtime, the learning system projects sensor data onto the eigenspace using eigenvectors determined in training. The result of the projection is a set of sensor values and actuator values. We developed an error metric based on comparing the projected values with the actual sensor values. When the system performs closely to how it was trained, the difference between projected and actual sensors is small and hence the error metric is small. The error increases as the performance degrades. This method is not task specific and can be used for any eigenvector learned primitive. Two example applications of the error metric are shown using wall following skills for a mobile robot. First, the metric is used as a transition cue for multiprimitive sequential tasks. Second, the error metric is used to create an adaptive system that chooses the best performing skill.

Authors

• Michael S. Sutton
• Amy C. Larson
• Richard M. Voyles

Keywords

• Learning systems
• Robotics and automation
• Robot sensing systems
• Actuators
• Robot programming
• Sensor systems
• Mobile robots
• Adaptive systems
• Programming profession
• Artificial neural networks
• Adaptive System
• Sensor Data
• Project Outcomes
• Active Sensors
• Mobile Robot
• Sequential Task
• Error Metrics
• Sensor Values
• Eigenspace
• Training Data
• Artificial Neural Network
• Variety Of Situations
• Left Wall
• Sensor Noise
• Average Vector
• Back Wall
• Training Vectors