A search and rescue robot search method based on flower pollination algorithm and Q-learning fusion algorithm.

Search algorithm plays an important role in the motion planning of the robot, it determines whether the mobile robot complete the task. To solve the search task in complex environments, a fusion algorithm based on the Flower Pollination algorithm and Q-learning is proposed. To improve the accuracy, an improved grid map is used in the section of environment modeling to change the original static grid to a combination of static and dynamic grids. Secondly, a combination of Q-learning and Flower Pollination algorithm is used to complete the initialization of the Q-table and accelerate the efficiency of the search and rescue robot path search. A combination of static and dynamic reward function is proposed for the different situations encountered by the search and rescue robot during the search process, as a way to allow the search and rescue robot to get better different feedback results in each specific situation. The experiments are divided into two parts: typical and improved grid map path planning. Experiments show that the improved grid map can increase the success rate and the FIQL can be used by the search and rescue robot to accomplish the task in a complex environment. Compared with other algorithms, FIQL can reduce the number of iterations, improve the adaptability of the search and rescue robot to complex environments, and have the advantages of short convergence time and small computational effort.

A path planning approach for mobile robots using short and safe Q-learning.

Path planning is a major challenging problem for mobile robots, as the robot is required to reach the target position from the starting position while simultaneously avoiding conflicts with obstacles. This paper refers to a novel method as short and safe Q-learning to alleviate the short and safe path planning task of mobile robots. To solve the slow convergence of Q-learning, the artificial potential field is utilized to avoid random exploration and provides a priori knowledge of the environment for mobile robots. Furthermore, to speed up the convergence of the Q-learning and reduce the computing time, a dynamic reward is proposed to facilitate the mobile robot towards the target point. The experiments are divided into two parts: short and safe path planning. The mobile robot can reach the target with the optimal path length in short path planning, and away from obstacles in safe path planning. Experiments compared with the state-of-the-art algorithm demonstrate the effectiveness and practicality of the proposed approach. Concluded, the path length, computing time and turning angle of SSQL is increased by 2.83%, 23.98% and 7.98% in short path planning, 3.64%, 23.42% and 12.61% in safe path planning compared with classical Q-learning. Furthermore, the SSQL outperforms other optimization algorithms with shorter path length and smaller turning angles.

A Path-Planning Approach Based on Potential and Dynamic Q-Learning for Mobile Robots in Unknown Environment.

The path-planning approach plays an important role in determining how long the mobile robots can travel. To solve the path-planning problem of mobile robots in an unknown environment, a potential and dynamic Q-learning (PDQL) approach is proposed, which combines Q-learning with the artificial potential field and dynamic reward function to generate a feasible path. The proposed algorithm has a significant improvement in computing time and convergence speed compared to its classical counterpart. Experiments undertaken on simulated maps confirm that the PDQL when used for the path-planning problem of mobile robots in an unknown environment outperforms the state-of-the-art algorithms with respect to two metrics: path length and turning angle. The simulation results show the effectiveness and practicality of the proposal for mobile robot path planning.

Reactive Molecular Dynamics Calculation and Ignition Delay Test of the Mixture of an Additive and 2-Azido-N,N-dimethylethanamine with Dinitrogen Tetroxide.

In order to shorten the ignition delay of 2-azido-N,N-dimethylethanamine (DMAZ) and dinitrogen tetroxide (NTO), four amines [tert-butylamine, pyrrole, N,N,N',N'-tetramethyl ethylenediamine (TMEDA), and diethylenetriamine (DABH)] with a mass fraction of 5% were added to DMAZ, and the potential energy change and the product change during the reaction of the mixture of an additive and DMAZ with NTO were analyzed by Reactive molecular dynamics (ReaxFF MD) calculation. Then, the ignition delay of the mixture of the additive and DMAZ as well as pure DMAZ with NTO was measured by a drop experiment with a photoelectric sensor and high-speed camera. The results show that the addition of pyrrole greatly reduced the time to reach the maximum system energy and greatly increased the rate of HNO2 formation. The dripping of the fuel was approximately a uniform linear motion, and the expression was y = 43.13 + 7.16x. The ignition delay time recorded by the camera was in good agreement with that of the optical signal. The measured ignition delay time for DMAZ with NTO was 261.5 ms. The mixture of pyrrole and DMAZ with NTO had the shortest ignition delay time of 100 ms, and the proportion of shortening the ignition delay time was the largest. The results of the droplet experiment were consistent with those of ReaxFF MD simulation, indicating that HNO2 plays an important role in the ignition delay, that is, the formation rate of HNO2 is positively correlated with the ignition delay.