2016
DOI: 10.1007/978-3-319-44188-7_1
|View full text |Cite
|
Sign up to set email alerts
|

Deep Active Learning for Autonomous Navigation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2016
2016
2021
2021

Publication Types

Select...
4
2
1

Relationship

2
5

Authors

Journals

citations
Cited by 9 publications
(7 citation statements)
references
References 24 publications
0
7
0
Order By: Relevance
“…To overcome this limitation, recent developments combine RL techniques with the significant feature extraction and processing capabilities of deep learning models in a framework known as Deep Q-Network (DQN) [6]. This approach exploits deep neural networks for both feature selection and Q-function approximation, hence enabling unprecedented performance in complex settings such as learning efficient playing strategies from unlabeled video frames of Atari games [7], robotic manipulation [8], and autonomous navigation of aerial [9] and ground vehicles [10].…”
Section: Introductionmentioning
confidence: 99%
“…To overcome this limitation, recent developments combine RL techniques with the significant feature extraction and processing capabilities of deep learning models in a framework known as Deep Q-Network (DQN) [6]. This approach exploits deep neural networks for both feature selection and Q-function approximation, hence enabling unprecedented performance in complex settings such as learning efficient playing strategies from unlabeled video frames of Atari games [7], robotic manipulation [8], and autonomous navigation of aerial [9] and ground vehicles [10].…”
Section: Introductionmentioning
confidence: 99%
“…The results are conducted on a 2D navigation task and show that the proposed reward shaping approach speeds up and improves deep reinforcement learning and provides increased stability against exploration policies. Our next step is to test the proposed approach on learning various navigation tasks in a more realistic simulator [38]. We also aim to incorporate reward shaping from demonstration with A3C [6] which is considered the current state of the art in deep reinforcement learning.…”
Section: Discussionmentioning
confidence: 99%
“…For example, [70] proposes to use imitation learning to perform navigation tasks. The visual environment and actions taken by the teacher viewed from a first-person perspective are used as the training set.…”
Section: Video Processingmentioning
confidence: 99%
“…When performing tasks, students use deep convolutional neural networks for feature extraction, learn imitation strategies, and further use the AL method to select samples with insufficient confidence, which are added to the training set to update the action strategy. [70] significantly improves the initial strategy using fewer samples. DeActive [66] proposed a DAL activity recognition model.…”
Section: Video Processingmentioning
confidence: 99%