Utilizing high-dimensional features for real-time robotic applications: Reducing the curse of dimensionality for recursive Bayesian estimation
| Autor: | Jacob Abernethy, Paul Ozog, Matthew Johnson-Roberson, Ryan M. Eustice, Jie Li |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
0209 industrial biotechnology
Bayes estimator Computer science business.industry Deep learning 0206 medical engineering 02 engineering and technology Kalman filter computer.software_genre Machine learning 020601 biomedical engineering Sonar 020901 industrial engineering & automation Artificial intelligence Data mining Hidden Markov model business Recursive Bayesian estimation Feature learning computer Curse of dimensionality |
| Zdroj: | IROS |
| DOI: | 10.1109/iros.2016.7759205 |
| Popis: | Feature learning has become popular in robotics due to recent advances in machine learning. In this paper, we propose a novel method to utilize the high-dimensional features from these techniques as observations in Bayesian estimation problems in a real-time manner. We develop an approach that: 1) pre-processes the observations and maps them into a new space with both reduced dimensions and a linear relationship to the estimation states; and 2) estimates the uncertainty of resulting outputs using data perturbation. The result is that deep learning approaches can be combined with more traditional filtering approaches like the Kalman filter (KF) to achieve state-of-the-art real-time performance. We validate the method by presenting the first real-time application of underwater robot localization using an imaging sonar. The proposed technique shows similar localization accuracy to benchmark approaches while simultaneously achieving real-time performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|