Operating articulated objects based on experience

Many tasks that would be of benefit to users in domestic environments require that robots manipulate articulated objects such as doors and drawers. In this paper, we present a novel approach that simultaneously estimates the kinematic model of an articulated object based on the trajectory described by the robot's end effector, and uses this model to predict the future trajectory of the end effector. One advantage of our approach is that the robot can directly use these predictions to generate an equilibrium point control path for operating the mechanism. Additionally, our approach can improve these predictions based on previously learned articulation models. We have implemented and tested our approach on a real mobile manipulator. Through 40 trials, we show that the robot can reliably open various household objects, including cabinet doors, sliding doors, office drawers, and a dishwasher. Furthermore, we demonstrate that using the information from previous interactions as a prior significantly improves the prediction accuracy.

Authors

• Jürgen Sturm
• Advait Jain
• Cyrill Stachniss
• Charles C. Kemp
• Wolfram Burgard

Keywords

• Trajectory
• Data models
• Kinematics
• Predictive models
• Computational modeling
• End effectors
• Articulated Objects
• Kinematic
• Equilibrium Point
• Joint Model
• End-effector
• Dishwasher
• Mobile Manipulator
• Model Fit
• Model Selection
• Set Of Models
• Prediction Error
• Bayesian Information Criterion
• Prior Information
• Parametrized
• Parameter Vector
• Rotation Axis
• Open Door
• Coordinate Frame
• Cartesian Space
• Center Of Rotation
• Lowest Bayesian Information Criterion
• Plane Rotation
• Robot Operating
• Odometry
• Average Prediction Error