Robotics: Science and Systems XXII
Natural Functional Gradients for Smooth Trajectory Optimization
Kisang Park, Chan Woo Kim, Kyungjae Lee, Sungjoon ChoiAbstract:
Generating collision-free and smoothly executable motions is a persistent challenge in robotic manipulation, especially in cluttered workspaces and narrow passages where the feasible set is highly nonconvex and fragmented. We propose a trajectory optimization method that performs geometry-aware updates directly in function space via natural functional gradients. Our approach optimizes a Gaussian-smoothed surrogate objective that regularizes the landscape through trajectory perturbations while preserving trajectory-level structure. Because updates are defined intrinsically in function space, trajectory regularity is controlled independently of the time grid, avoiding discretization-tuned smoothness penalties. We derive a practical Monte-Carlo estimator of the natural functional gradient that requires only black-box cost evaluations, making the method applicable when analytic gradients are unavailable or unreliable due to collision checking and contact-rich simulation. Across manipulation benchmarks with dense clutter and narrow clearances, the proposed optimizer achieves higher success rates and produces trajectories with lower acceleration and jerk than representative state-of-the-art baselines.
Bibtex:
@INPROCEEDINGS{ParkK-RSS-26,
AUTHOR = {Kisang Park AND Chan Woo Kim AND Kyungjae Lee AND Sungjoon Choi},
TITLE = {{Natural Functional Gradients for Smooth Trajectory Optimization}},
BOOKTITLE = {Proceedings of Robotics: Science and Systems},
YEAR = {2026},
ADDRESS = {Sydney, Australia},
MONTH = {July},
DOI = {10.15607/RSS.2026.XXII.162}
}
