Robotic Grinding Skills Learning Based on Geodesic Length Dynamic Motion Primitives

2025-04-24

AI Summary

To address the low orientation accuracy, asynchrony between pose and contact force, and poor generalization capability over curved surfaces in robotic grinding using Dynamic Movement Primitives (DMPs), this paper proposes Geodesic-length-based DMPs (Geo-DMPs). First, DMPs are extended to model model-free curved surfaces, enabling joint learning of position, orientation, and contact force. Second, a geodesic-length-driven phase function is introduced to ensure temporal synchronization among these three modalities. Third, SO(3) manifold distance metrics and intrinsic mean clustering are adopted to enhance orientation modeling fidelity. Experiments on chamfering and free-form surface grinding demonstrate that Geo-DMPs significantly improve geometric accuracy and cross-trajectory generalization performance, enabling high-quality grinding motion generation between arbitrary endpoints.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Machine Learning: Learning with Manifolds
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Learning grinding skills from human craftsmen via imitation learning has become a key research topic in robotic machining. Due to their strong generalization and robustness to external disturbances, Dynamical Movement Primitives (DMPs) offer a promising approach for robotic grinding skill learning. However, directly applying DMPs to grinding tasks faces challenges, such as low orientation accuracy, unsynchronized position-orientation-force, and limited generalization for surface trajectories. To address these issues, this paper proposes a robotic grinding skill learning method based on geodesic length DMPs (Geo-DMPs). First, a normalized 2D weighted Gaussian kernel and intrinsic mean clustering algorithm are developed to extract geometric features from multiple demonstrations. Then, an orientation manifold distance metric removes the time dependency in traditional orientation DMPs, enabling accurate orientation learning via Geo-DMPs. A synchronization encoding framework is further proposed to jointly model position, orientation, and force using a geodesic length-based phase function. This framework enables robotic grinding actions to be generated between any two surface points. Experiments on robotic chamfer grinding and free-form surface grinding validate that the proposed method achieves high geometric accuracy and generalization in skill encoding and generation. To our knowledge, this is the first attempt to use DMPs for jointly learning and generating grinding skills in position, orientation, and force on model-free surfaces, offering a novel path for robotic grinding.

Problem

• Improving orientation accuracy in robotic grinding tasks
• Synchronizing position, orientation, and force in grinding
• Enhancing generalization for surface trajectory learning

Innovation

• Geodesic length DMPs for accurate orientation learning
• Synchronization encoding for position-orientation-force modeling
• Normalized 2D kernel for geometric feature extraction