Spacetime splines improve robot motion timing and path control
Spacetime Splines for Adaptive Robot Motions
Robotics
Summary
Robots often rely on timed steps or phases to follow paths, but this can make their movements rigid or hard to adjust. The authors of this paper created a new method that treats the robot's path shape and timing as connected parts of one smooth curve, but also lets them be adjusted separately. This approach helps robots learn from incomplete examples and adapt movements like speed changes more naturally. They tested this method in simulations and on a robot helping with patient turning, showing better timing and synchronization.
What this means in practice
- •For robotics engineers: Build robot controllers that adapt motion timing and paths from partial or varied demonstrations more robustly.
- •For assistive robotics developers: Improve synchronization and real-time adjustment of robot actions in patient care tasks like assisted turning.
Authors
Boxuan Zhang, Ante Marić, Sylvain Calinon
Abstract
Movement primitives commonly represent robot mo- tions through basis functions indexed by time or phase. Inspired by spacetime representations employed in physics, we propose a spline-based formulation in which spatial geometry and temporal progression are represented within a common set of continuous variables. The proposed method jointly estimates a shared Bezier curve, while allowing spatial and temporal model complexity to be adapted independently (e.g., demonstration-specific phase modulation). As use case, we consider an alternating optimization process that simultaneously estimates path intervals observed in partial demonstrations. Simulation experiments demonstrate accurate joint recovery, refinement through modifications in model complexity and continuity, and improved robustness to variance in the demonstration set. Finally, we demonstrate online retiming and synchronization capabilities in a patient-turning task assisted by a robot, evaluated with a physical manikin.