Search

For the issues of the ant colony algorithm (ACO) to solving the problems in mobile robot path planning, such as the slow optimization speed and the redundant paths in planning results, a high-precision improved ant colony algorithm (IPACO) with fast optimization and compound prediction mechanism is proposed. Firstly, aiming at maximizing the possibility of optimal node selection in the process of path planning, a composite optimal node prediction model is introduced to improve the state transition function. Secondly, a pheromone model with initialize the distribution and “reward or punishment” update mechanism is used to updates the global pheromone concentration directionally, which increases the pheromone concentration of excellent path nodes and the heuristic effect; Finally, a prediction-backward mechanism to deal with the “deadlock” problem in the ant colony search process is adopted in the IPACO algorithm, which enhance the success rate in the ACO algorithm path planning. Five groups of different environments are selected to compare and verify the performance of IPACO algorithm, ACO algorithm and three typical path planning algorithms. The experimental simulation results show that, compared with the ACO algorithm, the convergence speed and the planning path accuracy of the IPACO algorithm are improved by 57.69% and 12.86% respectively, and the convergence speed and the planning path accuracy are significantly improved; the optimal path length, optimization speed and stability of the IPACO algorithm are improved. Which verifies that the IPACO algorithm can effectively improve the environmental compatibility and stability of the ant colony algorithm path planning, and the effect is significantly improved.

In designing BP neural network, it is difficult to determine the network parameters and weights, or to achieve the best effect under random perturbation, and impossible to satisfy the real-time requirement of system. To solve these problems, this paper introduces an evolutionary neural network and puts forward some improvements on conventional evolutionary programming. This algorithm is then used in the integrated navigation system. Experiment results indicate that BP neural network based on evolutionary programming can not only overcome the shortcomings of BP artificial neural network, but also avoid problems of genetic algorithms caused by binary-coded and cross operation. Also the navigation system based on this algorithm can get rid of the problems of kalman filter when the outside observation data are unreliable. Finally, the normal operation of kalman filter is ensured with a higher accuracy.

Poor environment of ship-based navigation system usually leads to decrease in navigation precision and even leads to divergence. BP neural network is introduced to solve this problem. According to characteristics of the navigation system, conventional BP algorithm is improved. And the improved algorithm is used in the ship-based navigation system. The simulation results show that the algorithm can overcome the problem of the navigation system, and ensure the normal operation of the filter.

There are matters of non-linear, computing errors, dimension tragedy, and model errors in conventional data fusion algorithms in integrated navigation. Fuzzy neural networks based on genetic algorithms not only has the capacity of the fuzzy neural networks, such as expressing approximate and qualitative knowledge, study, and expressing non-linear, but also has the competence of fast global searching of the genetic algorithms. So fuzzy neural networks based on genetic algorithms can be treated as an effective data fusion algorithms. And it was used in integrated navigation in this paper; the simulation results testified its validity.