Double BP Q-Learning Algorithm for Local Path Planning of Mobile Robot

Aiming at the dimension disaster problem, poor model generalization ability and deadlock problem in special obstacles environment caused by the increase of state information in the local path planning process of mobile robot, this paper proposed a Double BP Q-learning algorithm based on the fusion of Double Q-learning algorithm and BP neural network. In order to solve the dimensional disaster problem, two BP neural network fitting value functions with the same network structure were used to replace the two Q value tables in Double Q-Learning algorithm to solve the problem that the Q value table cannot store excessive state information. By adding the mechanism of priority experience replay and using the parameter transfer to initialize the model parameters in different environments, it could accelerate the convergence rate of the algorithm, improve the learning efficiency and the generalization ability of the model. By designing specific action selection strategy in special environment, the deadlock state could be avoided and the mobile robot could reach the target point. Finally, the designed Double BP Q-learning algorithm was simulated and verified, and the probability of mobile robot reaching the target point in the parameter update process was compared with the Double Q-learning algorithm under the same condition of the planned path length. The results showed that the model trained by the improved Double BP Q-learning algorithm had a higher success rate in finding the optimal or sub-optimal path in the dense discrete environment, besides, it had stronger model generalization ability, fewer redundant sections, and could reach the target point without entering the deadlock zone in the special obstacles environment.

Ectopic expression of AANAT or HIOMT improves melatonin production and enhances UV-B tolerance in transgenic apple plants

Melatonin is involved in plant responses to various environmental stresses.Although many studies have demonstrated that the tolerance of plants to stress is improved by exogenous melatonin,the role of endogenous melatonin metabolism in the response of apples to UV-B stress remains unclear.Here,the human melatonin biosynthesis-related enzyme genes AANAT or HIOMT were transformed into‘GL-3'apple,and the transgenic lines were treated with UV-B stress.The ectopic expression of AANAT or HIOMT significantly increased the melatonin content in apples.After UV-B stress,the tolerance of apple lines with ectopic expression of AANAT or HIOMT was markedly improved.The decrease in chlorophyll fluorescence,the generation of reactive oxygen species and the shrinkage of stomata caused by UV-B stress were alleviated by AANAT or HIOMT ectopic expression.In addition,the total phenolic content was markedly increased in the transgenic lines compared with the WT(wild type).The increase in phenolic compounds was related to the increase in benzoic acid,hydroxycinnamic acid,dihydrochalcones and flavanols,among which increases in chlorogenic acid,phloridzin and procyanidin B1 content were most prominent.Furthermore,the transgenic lines did not only promote the expression of genes related to phenolic synthesis under UV-B stress,but they also increased the accumulation of phenolic compounds by inhibiting the expression of MdPPO and MdPOD related to phenolic degradation.In summary,our results demonstrate that AANAT-or HIOMT-mediated melatonin synthesis improved the tolerance of apples to UV-B stress,mainly by scavenging reactive oxygen species,increasing photosynthetic capacity and increasing total phenolic content.