Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic models
© 2017 IEEE. The gap between our ability to collect interesting data and our ability to analyze these data is growing at an unprecedented rate. Recent algorithmic attempts to fill this gap have employed unsupervised tools to discover structure in data. Some of the most successful approaches have use...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2018
|
| Online Access: | http://hdl.handle.net/1721.1/115970 https://orcid.org/0000-0002-8293-0492 |
| _version_ | 1811091290941554688 |
|---|---|
| author | Girdhar, Yogesh Flaspohler, Genevieve Elaine Roy, Nicholas |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Girdhar, Yogesh Flaspohler, Genevieve Elaine Roy, Nicholas |
| author_sort | Girdhar, Yogesh |
| collection | MIT |
| description | © 2017 IEEE. The gap between our ability to collect interesting data and our ability to analyze these data is growing at an unprecedented rate. Recent algorithmic attempts to fill this gap have employed unsupervised tools to discover structure in data. Some of the most successful approaches have used probabilistic models to uncover latent thematic structure in discrete data. Despite the success of these models on textual data, they have not generalized as well to image data, in part because of the spatial and temporal structure that may exist in an image stream. We introduce a novel unsupervised machine learning framework that incorporates the ability of convolutional autoencoders to discover features from images that directly encode spatial information, within a Bayesian nonparametric topic model that discovers meaningful latent patterns within discrete data. By using this hybrid framework, we overcome the fundamental dependency of traditional topic models on rigidly hand-coded data representations, while simultaneously encoding spatial dependency in our topics without adding model complexity. We apply this model to the motivating application of high-level scene understanding and mission summarization for exploratory marine robots. Our experiments on a seafloor dataset collected by a marine robot show that the proposed hybrid framework outperforms current state-of-the-art approaches on the task of unsupervised seafloor terrain characterization. |
| first_indexed | 2024-09-23T15:00:10Z |
| format | Article |
| id | mit-1721.1/115970 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T15:00:10Z |
| publishDate | 2018 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1159702022-10-01T23:53:15Z Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic models Girdhar, Yogesh Flaspohler, Genevieve Elaine Roy, Nicholas Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Flaspohler, Genevieve Elaine Roy, Nicholas © 2017 IEEE. The gap between our ability to collect interesting data and our ability to analyze these data is growing at an unprecedented rate. Recent algorithmic attempts to fill this gap have employed unsupervised tools to discover structure in data. Some of the most successful approaches have used probabilistic models to uncover latent thematic structure in discrete data. Despite the success of these models on textual data, they have not generalized as well to image data, in part because of the spatial and temporal structure that may exist in an image stream. We introduce a novel unsupervised machine learning framework that incorporates the ability of convolutional autoencoders to discover features from images that directly encode spatial information, within a Bayesian nonparametric topic model that discovers meaningful latent patterns within discrete data. By using this hybrid framework, we overcome the fundamental dependency of traditional topic models on rigidly hand-coded data representations, while simultaneously encoding spatial dependency in our topics without adding model complexity. We apply this model to the motivating application of high-level scene understanding and mission summarization for exploratory marine robots. Our experiments on a seafloor dataset collected by a marine robot show that the proposed hybrid framework outperforms current state-of-the-art approaches on the task of unsupervised seafloor terrain characterization. NSF Graduate Research Fellowship Program award The John P. Chase Memorial Endowed Fund 2018-05-30T15:57:51Z 2018-05-30T15:57:51Z 2017-12 2018-04-09T17:34:56Z Article http://purl.org/eprint/type/ConferencePaper 978-1-5386-2682-5 http://hdl.handle.net/1721.1/115970 Flaspohler, Genevieve, Nicholas Roy, and Yogesh Girdhar. “Feature Discovery and Visualization of Robot Mission Data Using Convolutional Autoencoders and Bayesian Nonparametric Topic Models.” 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (September 2017). https://orcid.org/0000-0002-8293-0492 http://dx.doi.org/10.1109/IROS.2017.8202130 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) arXiv |
| spellingShingle | Girdhar, Yogesh Flaspohler, Genevieve Elaine Roy, Nicholas Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic models |
| title | Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic models |
| title_full | Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic models |
| title_fullStr | Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic models |
| title_full_unstemmed | Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic models |
| title_short | Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic models |
| title_sort | feature discovery and visualization of robot mission data using convolutional autoencoders and bayesian nonparametric topic models |
| url | http://hdl.handle.net/1721.1/115970 https://orcid.org/0000-0002-8293-0492 |
| work_keys_str_mv | AT girdharyogesh featurediscoveryandvisualizationofrobotmissiondatausingconvolutionalautoencodersandbayesiannonparametrictopicmodels AT flaspohlergenevieveelaine featurediscoveryandvisualizationofrobotmissiondatausingconvolutionalautoencodersandbayesiannonparametrictopicmodels AT roynicholas featurediscoveryandvisualizationofrobotmissiondatausingconvolutionalautoencodersandbayesiannonparametrictopicmodels |