Saved in:
Bibliographic Details
Main Authors: Kulecki, Bartłomiej, Belter, Dominik
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.07542
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917421400457216
author Kulecki, Bartłomiej
Belter, Dominik
author_facet Kulecki, Bartłomiej
Belter, Dominik
contents This manuscript investigates the integration of positional encoding -- a technique widely used in computer graphics -- into the input vector of a binary classification model for self-collision detection. The results demonstrate the benefits of incorporating positional encoding, which enhances classification accuracy by enabling the model to better capture high-frequency variations, leading to a more detailed and precise representation of complex collision patterns. The manuscript shows that machine learning-based techniques, such as lightweight multilayer perceptrons (MLPs) operating in a low-dimensional feature space, offer a faster alternative for collision checking than traditional methods that rely on geometric approaches, such as triangle-to-triangle intersection tests and Bounding Volume Hierarchies (BVH) for mesh-based models.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07542
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Machine Learning-Based Robot Self-Collision Checking with Input Positional Encoding
Kulecki, Bartłomiej
Belter, Dominik
Robotics
This manuscript investigates the integration of positional encoding -- a technique widely used in computer graphics -- into the input vector of a binary classification model for self-collision detection. The results demonstrate the benefits of incorporating positional encoding, which enhances classification accuracy by enabling the model to better capture high-frequency variations, leading to a more detailed and precise representation of complex collision patterns. The manuscript shows that machine learning-based techniques, such as lightweight multilayer perceptrons (MLPs) operating in a low-dimensional feature space, offer a faster alternative for collision checking than traditional methods that rely on geometric approaches, such as triangle-to-triangle intersection tests and Bounding Volume Hierarchies (BVH) for mesh-based models.
title Improving Machine Learning-Based Robot Self-Collision Checking with Input Positional Encoding
topic Robotics
url https://arxiv.org/abs/2509.07542