Detecting Changes on the ISS Autonomously with 3D Point Clouds: An Unsupervised Learning Approach Using GMM Clustering
| dc.contributor.author | Santos, Jamie | |
| dc.contributor.department | Chalmers tekniska högskola / Institutionen för mekanik och maritima vetenskaper | sv |
| dc.contributor.department | Chalmers University of Technology / Department of Mechanics and Maritime Sciences | en |
| dc.contributor.examiner | Wahde, Mattias | |
| dc.contributor.supervisor | Coltin, Brian | |
| dc.date.accessioned | 2023-07-07T11:02:57Z | |
| dc.date.available | 2023-07-07T11:02:57Z | |
| dc.date.issued | 2023 | |
| dc.date.submitted | 2023 | |
| dc.description.abstract | New space habitats, such as the Lunar Gateway and subsequent stations on Mars, will be increasingly difficult to continuously staff with astronauts, necessitating robotic support in the absence of humans. In this work, an unsupervised change detection algorithm requiring only 3D depth data as input is proposed in order to enable autonomous robotic caretaking. Scene change detection is necessary for robotic caretakers to accomplish many routine tasks, such as map updating and surveillance of the habitat. Upon the International Space Station (ISS), Astrobee is one such robot used for development and demonstration of these technologies under the Integrated System for Adaptive Autonomous Caretaking (ISAAC) project. Current scene analysis developed within the ISAAC project uses semantic localization to detect manually labeled objects within the map. However, this is not a sustainable approach for generalized change detection, as thousands of images must be captured and labeled for accurate results. In contrast, the proposed algorithm uses an unsupervised GMM clustering algorithm to compare “before” and “after” point clouds of the scene, and is therefore capable of detecting changes in the scene without being restricted to manually labeled objects. Experiments with data collected at NASA Ames’ Granite Lab, a mock-up of the ISS, successfully demonstrate the detection of one or more object appearances or disappearances in the scene with an initial average F1 score of 74% for volumetric reconstructed maps of the scene with two and three changed objects, and 70% for the comparison of single frames from the depth camera with one object. With a number of optimizations that can be made to improve the accuracy, the source code is released to the public to promote further research and development. | |
| dc.identifier.coursecode | MMSX30 | |
| dc.identifier.uri | http://hdl.handle.net/20.500.12380/306613 | |
| dc.language.iso | eng | |
| dc.setspec.uppsok | Technology | |
| dc.subject | robotics | |
| dc.subject | Gaussian mixture model | |
| dc.subject | earth mover’s distance | |
| dc.subject | change detection | |
| dc.subject | unsupervised learning | |
| dc.subject | expectation maximization | |
| dc.subject | point cloud | |
| dc.subject | ISS | |
| dc.title | Detecting Changes on the ISS Autonomously with 3D Point Clouds: An Unsupervised Learning Approach Using GMM Clustering | |
| dc.type.degree | Examensarbete för masterexamen | sv |
| dc.type.degree | Master's Thesis | en |
| dc.type.uppsok | H | |
| local.programme | Complex adaptive systems (MPCAS), MSc |