1 October 2023 in IEEE Journal on Selected Areas in Communications
27 October 2022 in IEEE Transactions on Intelligent Transportation Systems
Route planning over dynamic road networks is an increasingly fundamental problem of modern transportation systems for human society, especially in the field of Intelligent Supply Chain (ISC). Due to the high degree of urbanization and the high number of vehicles, longer response time caused by massive concurrent queries, as well as more attacks caused by malicious vehicles, results in low efficiency of the transportation system and huge waste of computation resources. Thus, it is necessary to provide an efficient and safe transportation service for intelligent transportation planning. To achieve it, we utilize and improve the trust model to prevent the waste of computation resources. Meanwhile, we introduce a Trusted Parallel Optimization on Route Planning () based on Dual-level Grid (DLG) index to continuously handle the process of route planning in parallel. Considering the evolving traffic condition, we employ an LSTM (Long Short-Term Memory) neural network to periodically predict the weights of roads. Experimental results indicate that is effective to sorts of trust model attacks and reduces the response time by an average of about 46.7% and saves the processing time by an average of about 27.6% compared with CANDS (Continuous Optimal Navigation via Distributed Stream Processing) algorithm.
18 August 2022 in IEEE Transactions on Intelligent Transportation Systems
Automated vehicle(AV) based on reinforcement learning is an important part of the intelligent transportation system. However, currently, the performance of AV heavily that relies on the quality of maps and mapless navigation is one potential method for navigation in a strange and dynamic changing environment. Although many efforts are made on mapless navigation, they either need prior knowledge, rely on an exceptional constructed environment or simple feature fusion mechanism in the networks. In this paper, we proposed a deep reinforcement learning method, namely TC-DDPG, which is consisted of DDPG, multi-challenge deep learning networks and time-critical reward function. By comparing to existing approaches, TC-DDPG takes the cost of time into consideration and achieves better performance and converges more easily. A new open source simulator is proposed and extensive experiments are conducted to demonstrate the performance of the TC-DDPG, which outperforms comparing methods and achieves 62.9% less in time cost, 12.0% less in distance cost and about 90% fewer in numbers of model parameters.