Title | ||
---|---|---|
Action effect generalization, recognition and execution through Continuous Goal-Directed Actions |
Abstract | ||
---|---|---|
Programming by demonstration (PbD) allows matching the kinematic movements of a robot with those of a human. The presented Continuous Goal-Directed Actions (CGDA) is able to additionally encode the effects of a demonstrated action, which are not encoded in PbD. CGDA allows generalization, recognition and execution of action effects on the environment. In addition to analyzing kinematic parameters (joint positions/velocities, etc.), CGDA focuses on changes produced on the object due to an action (spatial, color, shape, etc.). By tracking object features during action execution, we create a trajectory in an n-dimensional feature space that represents object temporal states. Discretized action repetitions provide us with a cloud of points. Action generalization is accomplished by extracting the average point of each sequential temporal interval of the point cloud. These points are interpolated using Radial Basis Functions, obtaining a generalized multidimensional object feature trajectory. Action recognition is performed by comparing the trajectory of a query sample with the generalizations. The trajectories discrepancy score is obtained by using Dynamic Time Warping (DTW). Robot joint trajectories for execution are computed in a simulator through evolutionary computation. Object features are extracted from sensors, and each evolutionary individual fitness is measured using DTW, comparing the simulated action with the generalization. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICRA.2014.6907098 | Robotics and Automation |
Keywords | Field | DocType |
automatic programming,generalisation (artificial intelligence),image recognition,learning (artificial intelligence),radial basis function networks,robot kinematics,robot programming,robot vision,action effect execution,action effect generalization,action effect recognition,continuous goal-directed actions,discretized action repetitions,dynamic time warping,evolutionary computation,evolutionary individual fitness,generalized multidimensional object feature trajectory,interpolation,n-dimensional feature space,object feature extraction,object feature tracking,object temporal states,point cloud,programming by demonstration,radial basis functions,robot joint trajectories,robot kinematic movements,sequential temporal interval | Programming by demonstration,Kinematics,Dynamic time warping,Control theory,Artificial intelligence,Trajectory,Computer vision,Feature vector,Generalization,Evolutionary computation,Algorithm,Point cloud,Mathematics | Conference |
Volume | Issue | ISSN |
2014 | 1 | 1050-4729 |
Citations | PageRank | References |
7 | 0.53 | 8 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Santiago Morante | 1 | 25 | 4.46 |
Juan G. Victores | 2 | 51 | 9.82 |
Alberto Jardón | 3 | 35 | 8.95 |
C. Balaguer | 4 | 144 | 28.36 |