Name
Abstract | ||
|---|---|---|
We investigate a classification problem using multiple mobile agents capable of collecting (partial) pose-dependent observations of an unknown environment. The objective is to classify an image over a finite time horizon. We propose a network architecture on how agents should form a local belief, take local actions, and extract relevant features from their raw partial observations. Agents are allowed to exchange information with their neighboring agents to update their own beliefs. It is shown how reinforcement learning techniques can be utilized to achieve decentralized implementation of the classification problem by running a decentralized consensus protocol. Our experimental results on the MNIST handwritten digit dataset demonstrates the effectiveness of our proposed framework. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/IROS40897.2019.8968129 | 2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) |
Field | DocType | Volume |
MNIST database,Network architecture,Artificial intelligence,Contextual image classification,Mathematics,Machine learning,Reinforcement learning,Finite time | Journal | abs/1905.04835 |
ISSN | Citations | PageRank |
2153-0858 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hossein K. Mousavi | 1 | 6 | 3.15 |
| MohammadReza Nazari | 2 | 8 | 2.18 |
| Martin Takác | 3 | 752 | 49.49 |
| Nader Motee | 4 | 181 | 28.18 |