Zhu, Mingchi and She, Haoping and Si, Weiyong and Li, Chuanjun (2024) Lightweight Imitation Learning Algorithm with Error Recovery for Human Direction Correction. In: 2024 29th International Conference on Automation and Computing (ICAC), 2024-08-28 - 2024-08-30, Sunderland.
Zhu, Mingchi and She, Haoping and Si, Weiyong and Li, Chuanjun (2024) Lightweight Imitation Learning Algorithm with Error Recovery for Human Direction Correction. In: 2024 29th International Conference on Automation and Computing (ICAC), 2024-08-28 - 2024-08-30, Sunderland.
Zhu, Mingchi and She, Haoping and Si, Weiyong and Li, Chuanjun (2024) Lightweight Imitation Learning Algorithm with Error Recovery for Human Direction Correction. In: 2024 29th International Conference on Automation and Computing (ICAC), 2024-08-28 - 2024-08-30, Sunderland.
Abstract
Existing imitation learning methods for human directional corrections may lead to learning incorrect behaviors due to erroneous artificial teaching, resulting in a significant increase in the required number of iterations and even non-convergence situations, which can affect the system's performance. Additionally, the high computational complexity makes it unsuitable for embedded real-time application scenarios. To address these two issues, this study proposes a lightweight imitation learning algorithm that pre-corrects human-directed corrections. This method utilizes a deep learning network trained on a small dataset to correct human directional corrections and designs a lower-dimensional cost function for imitation learning. The proposed approach is applied to the example of a drone passing through doorways. Through the construction of a simulation platform and conducting simulation verification, the results show that the algorithm incorporating the correction error detection mechanism achieves an accuracy of over 98% in discerning human corrections, reduces training time by 27.87% per iteration, and decreases the average number of rounds by approximately 40%. The results indicate that the algorithm, which combines correction detection based on deep learning and a low-dimensional cost function, improves the accuracy of algorithm iterations, reduces computational complexity, and enhances computational speed.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Uncontrolled Keywords: | Learning from demonstrations (LfD); cost function design; lightweight network; error recovery for human correction; small-dataset neural network |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 31 Oct 2024 11:08 |
Last Modified: | 31 Oct 2024 11:10 |
URI: | http://repository.essex.ac.uk/id/eprint/39524 |
Available files
Filename: Accepted_Manuscript.pdf