Natural Functional Gradients for Smooth Trajectory Optimization
- URL: http://arxiv.org/abs/2605.28202v1
- Date: Wed, 27 May 2026 09:25:57 GMT
- Title: Natural Functional Gradients for Smooth Trajectory Optimization
- Abstract summary: We propose a trajectory optimization framework that performs geometry-aware updates directly in function space using natural functional gradients.<n>We derive a practical Monte-Carlo estimator of the natural functional gradient that requires only black-box trajectory evaluations.<n> Experiments on constrained robotic manipulation tasks demonstrate that the proposed method improves trajectory feasibility and produces smoother motions.
- Score: 11.331190543795914
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Generating collision-free and smooth motions remains a central challenge in robotic manipulation, particularly in cluttered environments and narrow passages where feasible regions are highly constrained and fragmented. We propose a trajectory optimization framework that performs geometry-aware updates directly in function space using natural functional gradients. The method optimizes a Gaussian-smoothed surrogate objective that regularizes the optimization landscape through smooth trajectory perturbations while preserving trajectory-level structure. Because the updates are defined intrinsically in function space, trajectory regularity can be controlled independently of a particular time discretization. We derive a practical Monte-Carlo estimator of the natural functional gradient that requires only black-box trajectory evaluations, making the method applicable when analytic gradients are unavailable or unreliable due to collision checking and contact-rich simulation. Experiments on constrained robotic manipulation tasks demonstrate that the proposed method improves trajectory feasibility and produces smoother motions than representative planning and trajectory optimization baselines in environments with narrow geometric clearances. Additional results, videos, and implementation details are available at the project page: https://kisangpark.github.io/natural-functional-gradient/
Related papers
- Spatially-Grounded Text-to-Video Generation via Inference-Time Gradient-Free Optimization [46.49480145234397]
Diffusion Transformer Text-to-Video models have achieved remarkable synthesis quality.<n>Fine-grained spatial controllability remains a significant challenge.<n>We present a novel training-free and gradient-free approach for precise spatial guidance.
arXiv Detail & Related papers (2026-08-13T10:05:16Z) - Motion Planning for Autonomous Vehicles using Optimization over Graphs of Convex Sets [0.6445605125467574]
Motion planning for autonomous vehicles requires generating collision-free and dynamically feasible trajectories under real-time constraints.<n>In this paper, we introduce a new geometric control method to approximate nonlinear motion planning problems.<n>The method provides a structured approximation of nonlinear motion planning problems, capturing dominant geometric dynamic effects while preserving convexity in the continuous relaxation.
arXiv Detail & Related papers (2026-05-13T23:29:54Z) - Spatially-Aware Adaptive Trajectory Optimization with Controller-Guided Feedback for Autonomous Racing [74.83272587893508]
We present a framework for autonomous raceline optimization that combines NURBS-based trajectory representation, CMA-ES global trajectory optimization, and controller-guided spatial feedback.<n>In simulation, our approach achieves a 17.38% lap time reduction compared to a controller parametrized with maximum static acceleration.<n>On real hardware, tested with different tire compounds ranging from high to low friction, we obtain a 7.60% lap time improvement without explicitly parametrizing friction.
arXiv Detail & Related papers (2026-02-17T15:10:44Z) - Fast Near Time-Optimal Motion Planning for Holonomic Vehicles in Structured Environments [8.195916347194315]
The approach aims to solve the problem of motion planning for planar motion systems using magnetic levitation.<n>The presented approach encodes the environment representation using free-space corridors and represents the motion of the vehicle through such a corridor using a motion primitive.<n>The method achieves significantly lower times compared to the state-of-the-art and is validated on a real-world Beckhoff XPlanar system.
arXiv Detail & Related papers (2026-02-02T21:26:30Z) - Optimizing Control-Friendly Trajectories with Self-Supervised Residual Learning [10.551597725130675]
Real-world physics can only be analytically modeled with a certain level of precision for modern intricate robotic systems.<n>This paper presents a self-supervised residual learning and trajectory optimization framework to address the aforementioned challenges.
arXiv Detail & Related papers (2026-01-06T06:01:58Z) - Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process [15.756895046886406]
We propose a novel spatial-temporal traversability assessment method, which aims to enable autonomous robots to navigate through complex terrains.<n>Our method outper- forms SOTA approaches in both accuracy and computational efficiency.<n>We develop an autonomous navigation framework integrated with the traversability map and validate it with a differential driven vehicle in complex outdoor envi- ronments.
arXiv Detail & Related papers (2025-03-06T06:26:57Z) - Neural Gradient Learning and Optimization for Oriented Point Normal
Estimation [53.611206368815125]
We propose a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation.
We learn an angular distance field based on local plane geometry to refine the coarse gradient vectors.
Our method efficiently conducts global gradient approximation while achieving better accuracy and ability generalization of local feature description.
arXiv Detail & Related papers (2023-09-17T08:35:11Z) - Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels [78.6096486885658]
We introduce lower bounds to the linearized Laplace approximation of the marginal likelihood.
These bounds are amenable togradient-based optimization and allow to trade off estimation accuracy against computational complexity.
arXiv Detail & Related papers (2023-06-06T19:02:57Z) - Neural Motion Fields: Encoding Grasp Trajectories as Implicit Value
Functions [65.84090965167535]
We present Neural Motion Fields, a novel object representation which encodes both object point clouds and the relative task trajectories as an implicit value function parameterized by a neural network.
This object-centric representation models a continuous distribution over the SE(3) space and allows us to perform grasping reactively by leveraging sampling-based MPC to optimize this value function.
arXiv Detail & Related papers (2022-06-29T18:47:05Z) - DiffSkill: Skill Abstraction from Differentiable Physics for Deformable
Object Manipulations with Tools [96.38972082580294]
DiffSkill is a novel framework that uses a differentiable physics simulator for skill abstraction to solve deformable object manipulation tasks.
In particular, we first obtain short-horizon skills using individual tools from a gradient-based simulator.
We then learn a neural skill abstractor from the demonstration trajectories which takes RGBD images as input.
arXiv Detail & Related papers (2022-03-31T17:59:38Z) - Self-Tuning Stochastic Optimization with Curvature-Aware Gradient
Filtering [53.523517926927894]
We explore the use of exact per-sample Hessian-vector products and gradients to construct self-tuning quadratics.
We prove that our model-based procedure converges in noisy gradient setting.
This is an interesting step for constructing self-tuning quadratics.
arXiv Detail & Related papers (2020-11-09T22:07:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.