3D-CovDiffusion: 3D-Aware Diffusion Policy for Coverage Path Planning

2025-10-03

AI Summary

Traditional coverage path planning methods rely on predefined trajectory parameterizations, resulting in poor generalization and limited adaptability. To address this, we propose a 3D-perception-aware, end-to-end diffusion policy model tailored for industrial surface treatment tasks. Our approach eliminates explicit trajectory parameterization by directly generating long-horizon, smooth, and geometrically adaptive 3D coverage paths via a progressive denoising mechanism. The model integrates point-cloud conditional encoding with context-guided noise scheduling, enabling unified modeling across diverse workpiece categories and zero-shot generalization to unseen geometries. Experiments demonstrate significant improvements over state-of-the-art methods: a 98.2% reduction in Chamfer distance, a 97.0% improvement in trajectory curvature continuity, and a 61% increase in surface coverage. These results underscore substantial gains in generalization to complex, previously unseen shapes and enhanced robustness for real-world deployment.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Motion and Path Planning

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Diffusion models, as a class of deep generative models, have recently emerged as powerful tools for robot skills by enabling stable training with reliable convergence. In this paper, we present an end-to-end framework for generating long, smooth trajectories that explicitly target high surface coverage across various industrial tasks, including polishing, robotic painting, and spray coating. The conventional methods are always fundamentally constrained by their predefined functional forms, which limit the shapes of the trajectories they can represent and make it difficult to handle complex and diverse tasks. Moreover, their generalization is poor, often requiring manual redesign or extensive parameter tuning when applied to new scenarios. These limitations highlight the need for more expressive generative models, making diffusion-based approaches a compelling choice for trajectory generation. By iteratively denoising trajectories with carefully learned noise schedules and conditioning mechanisms, diffusion models not only ensure smooth and consistent motion but also flexibly adapt to the task context. In experiments, our method improves trajectory continuity, maintains high coverage, and generalizes to unseen shapes, paving the way for unified end-to-end trajectory learning across industrial surface-processing tasks without category-specific models. On average, our approach improves Point-wise Chamfer Distance by 98.2% and smoothness by 97.0%, while increasing surface coverage by 61% compared to prior methods. The link to our code can be found href{https://anonymous.4open.science/r/spraydiffusion_ral-2FCE/README.md}{here}.

Problem

• Generating smooth trajectories for industrial surface coverage tasks
• Overcoming limitations of predefined trajectory shapes in conventional methods
• Enabling generalization to unseen shapes without manual redesign

Innovation

• Uses diffusion models for robot trajectory generation
• Iteratively denoises trajectories with learned noise schedules
• Generates smooth high-coverage paths for industrial tasks