Computationally efficient navigation system for Unmanned Ground Vehicles
| Autor: | Peyman Moghadam, Saba Salehi, Wijerupage Sardha Wijesoma |
|---|---|
| Rok vydání: | 2011 |
| Předmět: |
Engineering
business.industry Autonomous Navigation System Feature extraction Principal (computer security) Navigation system Mobile robot Remotely operated underwater vehicle Machine learning computer.software_genre Support vector machine Feature (computer vision) Artificial intelligence business computer |
| Zdroj: | 2011 IEEE Conference on Technologies for Practical Robot Applications. |
| DOI: | 10.1109/tepra.2011.5753495 |
| Popis: | This paper proposes to enhance the existing methods of Self-Supervised Learning (SSL) with application to autonomous navigation systems through efficient computational approaches that are the principal requirements in a practical system. First, confidence-based auto labeling for self-supervised learning is introduced which identifies and eliminates the input samples with low confidence level that are susceptible to be mislabeled. Then, a biologically inspired saliency detection approach for feature biasing is presented which is able to detect the salient features through top-down task specific guidance. The proposed methods are general and can be applied to a variety of applications. Finally, experimental results on real datasets from the DARPA-LAGR program are given to illustrate the effectiveness of the proposed approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|