12 April 2024 in Data Technologies and Applications
Purpose: The purpose of this research is to achieve multi-task autonomous driving by adjusting the network architecture of the model. Meanwhile, after achieving multi-task autonomous driving, the authors found that the trained neural network model performs poorly in untrained scenarios. Therefore, the authors proposed to improve the transfer efficiency of the model for new scenarios through transfer learning.Design/methodology/approach: First, the authors achieved multi-task autonomous driving by training a model combining convolutional neural network and different structured long short-term memory (LSTM) layers. Second, the authors achieved fast transfer of neural network models in new scenarios by cross-model transfer learning. Finally, the authors combined data collection and data labeling to improve the efficiency of deep learning. Furthermore, the authors verified that the model has good robustness through light and shadow test.Findings: This research achieved road tracking, real-time acceleration–deceleration, obstacle avoidance and left/right sign recognition. The model proposed by the authors (UniBiCLSTM) outperforms the existing models tested with model cars in terms of autonomous driving performance. Furthermore, the CMTL-UniBiCL-RL model trained by the authors through cross-model transfer learning improves the efficiency of model adaptation to new scenarios. Meanwhile, this research proposed an automatic data annotation method, which can save 1/4 of the time for deep learning.Originality/value: This research provided novel solutions in the achievement of multi-task autonomous driving and neural network model scenario for transfer learning. The experiment was achieved on a single camera with an embedded chip and a scale model car, which is expected to simplify the hardware for autonomous driving.
1 June 2019 in Journal of Instrumentation
A neutron time projection chamber can locate the approximate direction of a neutron hot spot with high efficiency and a 4π field of view. The angular resolution can be significantly improved by adding several plastic scintillation detectors and using coincidence events. The specific performances of such a coincidence imaging system are studied based on theoretical calculations and experimental results. The calculated value of the angular resolution is approximately 2o for the current system, which agrees well with the experimental results and sets an upper limit for the angular resolution of traditional back projection based online reconstruction methods. Although the statistical iterative method can breakthrough this limit and further improve the angular resolution, the time consumption is usually a problem. The coincidence imaging system can be further optimized for future applications based on the theoretical model.