Improving Machine Learning-Based Robot Self-Collision Checking with Input Positional Encoding
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 classifi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2025-09-01
|
| Series: | Foundations of Computing and Decision Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/fcds-2025-0015 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849225052163145728 |
|---|---|
| author | Kulecki Bartłomiej Belter Dominik |
| author_facet | Kulecki Bartłomiej Belter Dominik |
| author_sort | Kulecki Bartłomiej |
| collection | DOAJ |
| description | 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 | Article |
| id | doaj-art-bda34348e2e647c1a12356d4bb2d425d |
| institution | Kabale University |
| issn | 2300-3405 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Foundations of Computing and Decision Sciences |
| spelling | doaj-art-bda34348e2e647c1a12356d4bb2d425d2025-08-25T06:11:49ZengSciendoFoundations of Computing and Decision Sciences2300-34052025-09-0150338340210.2478/fcds-2025-0015Improving Machine Learning-Based Robot Self-Collision Checking with Input Positional EncodingKulecki Bartłomiej0Belter Dominik11Institute of Robotics and Machine Intelligence, Poznan University of Technology, 60-965Poznań, Poland1Institute of Robotics and Machine Intelligence, Poznan University of Technology, 60-965Poznań, PolandThis 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.https://doi.org/10.2478/fcds-2025-0015collision checkingneural networkinput encoding |
| spellingShingle | Kulecki Bartłomiej Belter Dominik Improving Machine Learning-Based Robot Self-Collision Checking with Input Positional Encoding Foundations of Computing and Decision Sciences collision checking neural network input encoding |
| title | Improving Machine Learning-Based Robot Self-Collision Checking with Input Positional Encoding |
| title_full | Improving Machine Learning-Based Robot Self-Collision Checking with Input Positional Encoding |
| title_fullStr | Improving Machine Learning-Based Robot Self-Collision Checking with Input Positional Encoding |
| title_full_unstemmed | Improving Machine Learning-Based Robot Self-Collision Checking with Input Positional Encoding |
| title_short | Improving Machine Learning-Based Robot Self-Collision Checking with Input Positional Encoding |
| title_sort | improving machine learning based robot self collision checking with input positional encoding |
| topic | collision checking neural network input encoding |
| url | https://doi.org/10.2478/fcds-2025-0015 |
| work_keys_str_mv | AT kuleckibartłomiej improvingmachinelearningbasedrobotselfcollisioncheckingwithinputpositionalencoding AT belterdominik improvingmachinelearningbasedrobotselfcollisioncheckingwithinputpositionalencoding |