Event
Proposing unified spatiotemporal spline modeling for robot motion
1 reports · 1 sources
Boxuan Zhang, Ante Marić, and Sylvain Calinon propose a spline-based movement primitive representation that places spatial geometry and temporal progression into a single set of continuous variables to jointly estimate a shared Bezier curve, and allows the complexity of the spatial and temporal models to be adaptively adjusted independently. Simulation results show that the method can accurately recover joint trajectories, that adjusting model complexity and continuity yields refinement effects, and that it improves robustness to variance in the demonstration set; in a robot-assisted turning-over task, the study used a physical dummy to evaluate online retiming and synchronization capabilities.
Report timeline
- Spacetime Splines for Adaptive Robot Motions
This study proposes a spline-based movement primitive representation that unifies spatial geometry and temporal progression into a common set of continuous variables, jointly estimates a shared Bezier curve, and allows spatial and temporal model complexity to be adapted independently. Simulations validated joint recovery accuracy, refinement from modifications to model complexity and continuity, and improved robustness to variance in the demonstration set. In a robot-assisted patient-turning task, online retiming and synchronization capabilities were evaluated with a physical manikin.
arXiv cs.RO ·