Body schema acquisition through active learning

We present an active learning algorithm for the problem of body schema learning, i. e. estimating a kinematic model of a serial robot. The learning process is done online using Recursive Least Squares (RLS) estimation, which outperforms gradient methods usually applied in the literature. In addiction, the method provides the required information to apply an active learning algorithm to find the optimal set of robot configurations and observations to improve the learning process. By selecting the most informative observations, the proposed method minimizes the required amount of data. We have developed an efficient version of the active learning algorithm to select the points in real-time. The algorithms have been tested and compared using both simulated environments and a real humanoid robot.

Authors

• Ruben Martinez-Cantin
• Manuel Lopes 0001
• Luis Montesano

Keywords

• Robot sensing systems
• Kinematics
• Orbital robotics
• Least squares approximation
• Humanoid robots
• Space exploration
• Recursive estimation
• Cost function
• Robotics and automation
• Resonance light scattering
• Active Learning
• Body Schema
• Least-squares
• Learning Process
• Least Squares Estimation
• Gradient Method
• Humanoid Robot
• Real Robot
• Recursive Least Squares
• Robot Configuration
• Degrees Of Freedom
• Parameter Estimates
• Posterior Probability
• Prediction Error
• Central Point
• Global Optimization
• Active Strategies
• Online Learning
• Optimal Efficiency
• Kinematic Chain
• Active Learning Strategies
• Base Frame
• Extended Kalman Filter
• Closed Set
• Robotic Arm
• Configuration Space
• Global Convergence
• External Sensors
• Active Learning Methods