A New Algorithm for Robot Path Planning Based on Scout Ant Cooperation

According to the realistic duty of robot, it's necessary to find a short path to avoid obstacles and carry limited goods, and then the added constrains let the problem is more complex and more practical. The paper proposes a tabu-genetic algorithm for robot path planning. By utilizing the main frame of parallel search supplied by genetic algorithm and embed the individual serial search mode of tabu search algorithm, this method can enlarge search space. And in order to enhance optimized speed and quality, also improve the algorithm performance, fitness function and amendatory policy are designed. Besides, algorithm convergence is analyzed based on the model of Markov chains. The results of simulations show that the method proposed in this paper, which can find an optimal path quickly and improve convergence speed and solution quality greatly.

Aiming at the problem of robot path planning in complex maps, an algorithm of robot path planning based on triangular grid graph is proposed. Firstly, a weighted undirected loop graph and a feasible domain of nodes are obtained by discretizing the triangular mesh map. Next, the Dijkstra search algorithm is applied to find the feasible shortest path from an initial to a final configuration. Finally, The Douglas-Peucker algorithm is applied to remove duplicate and redundant nodes in the feasible path, and the waypoint are extracted. The final path is a curve that is obtained by connecting the several extracted waypoint. The proposed algorithm is tested for various maps. Compared with probabilistic roadmap method, the experimental results show that the proposed method can overcome the shortcomings of the random sampling method. Furthermore, the experimental result of triangular mesh map method used in two labyrinth maps show that the triangular mesh map method can solve the robot path planning problem in complex map very well, and it is an excellent algorithm for robot path planning.

A modified dueling DQN algorithm for robot path planning incorporating priority experience replay and artificial potential fields

Recently, genetic algorithms (GAs) have attracted great interest owing to efficiency and flexibility against complex robot path planning problems. To accelerate the convergence speed, preceding researches adapted conventional GAs by using problem-specific techniques. However, such approaches increase computational burden and algorithmic complexity, resulting in subsequent additional problems. In this paper, we used Population-Based Incremental Learning (PBIL) algorithm for robot path planning as a probabilistic evolutionary approach. In addition to PBIL, we also proposed the probabilistic model of nodes and the edge bank to generate promising paths. The experimental results demonstrate that the proposed method gave markedly better performance than its conventional counter-parts(GA,kGA,fGA) in terms of success rates and the quality of obtained paths.

The authors previously (1994) showed that the potential field method combined with the navigating fuzzy logic controller (NFLC) can produce a safe and smooth paths for a robot. When the robot is trapped in undesired local minimum, the fuzzy tracking controller (FTC) can be employed to escape the trapping. Since the rules of the NFLC and the FTC is developed by expert's experiences, the learning of the rules is necessary to improve the performance. In this paper, an auto tuning technique called the cache genetic algorithm (CGA) is proposed to adjust the rules. The proposed CGA performs the fast operation of selection, crossover and mutation in a cache pool to obtain best fuzzy parameters. Computer simulations showed that the proposed fuzzy potential approach (FP) with the proposed cache genetic learning algorithm can improve the overall performance with fast tuning speed.

In view of high dimension, the difficulty of training, the problem of slow learning speed in the application of BP neural network in mobile robot path planning, an algorithm of reinforcement Q learning based on extreme learning machine (Q-ELM algorithm) is proposed in this paper. Firstly, the characteristic of reinforcement learning is combining the dynamic network with supervised learning, and the algorithm obtains the state information of the environment and the robot by the characteristic. After that, it is used to analyze the state to get the rewards and punishments of the current state by extreme learning machine. Secondly, it is used to solve the problem of slow training speed by the characteristic of less parameter settings and better generalization performance; Finally the autonomic learning performance of the learning algorithm is verified. The experimental results show that the Q-ELM learning algorithm not only improves the initiative of machine learning, but also improves the learning rate of 4 times than TD reinforcement learning methods, and verifies the stability and convergence of the algorithm.

This paper studies the obstacle avoidance and navigation of mobile robots in unstructured environments. Because of the shortcomings of one single sensor, the system integrates the stereo vision sensor blumblebee2 with the lidar sensor to detect the information surrounding the mobile robot’s surroundings. And then through data fusion to get a more complete, more accurate scene distribution. Then use the improved system of ant colony optimization to increase the convergence speed and precision of the algorithm in robot path planning. Finally, the simulation experiment is carried out in the environment of Matlab and Visual Studio, and the physical experiment is carried out under the ROS platform. The experimental results show the feasibility and effectiveness of the proposed method.

Uninhabited combat aerial vehicle (UCAV) path planning aims to obtain an optimal or near-optimal flight path considering the different kinds of threats and constraints in the combat field. This paper proposes a novel quantum encoding bat algorithm (QBA) for solving the path planning of UCAV. Using quantum rotation and quantum NOT gate are implemented to change the basic qubit states and to enhance global search capability. The QBA can find a feasible and global path for the UCAV to avoid the threats and constraints. The experimental results show that the proposed QBA algorithm is an effective and feasible method in solving UCAV path planning problem than some well-known algorithms.

In the introduction section of this paper, the importance of path planning for automatic self-navigation is outlined, along with the structure and basic model of neural networks, as well as numerous practical examples of using neural networks to solve the problem of traffic prediction and autonomous robot navigation. In the method section, the specific formulations and steps of how neural networks can be used to solve the path planning problem are explained in detail. Additionally, a variety of algorithms for solving the path planning problem with neural networks are introduced, and practical experiments are conducted to compare the results of these algorithms in various environments. In the RESULTS section, the characteristics are summarized and explained by comparing the experimental results. In the CONFUSION section, a fundamental outlook on the future of neural networks for solving path-planning problems is provided, as well as the possibility of cooperation between neural networks and other methods for solving path-planning problems.

Which path was the optimal path in a large parking guidance system? Obviously, only considering the shortest distance is not enough, only considering the shortest time is an ideal goal but not easy to realize, so introduced a feasible time-optimal evaluation in parking path planning. It can not only simplify hardware design of the guidance system, but also reduce the software cost. Mathematical model R (P, C, D, V) of the parking lot network diagram was established, the all nodes in R (P, C, D, V) were divided into two layers and different evaluation functions were built. According to the improved time-optimal evaluation, the design used the improved A-star algorithm to increase searching efficiency and precision. Finally, the result of running the program shows that the algorithm can quickly find out the different time-optimal path for different attribute parameter.

This paper discusses an approach to mo- bile robot path planning which utilizes a wavefront- like propagation method for determining near-optimal paths. This approach is different from previous wave propagation methods in three aspects: it attempts to find near-optimal paths from all locations in the free space to the destination instead of one optimal path from the source location to the destination, may per- form repeated propagations to converge to a solution, and is composed of simplified computations based on local information to facilitate a VLSI implementation. I. INTRODUCTION Wavefront propagation methods for robot path plan- ning have been proposed by other researchers. The tradi- tional approach is to start with a list containing only the destination point (or a region representing a small area around the destination point) and propagate a value rep- resenting the cost of traveling between the two regions to each unvisited neighbor of the region. The region is removed from the list and all its newly visited neighbors are added to the list. The list is sorted by increasing cost and the process is repeated with the lowest cost region in the list. This process terminates when the source region is reached. The actual path is then constructed between the endpoints using the computed cost values. Jahanbin and Fallside(l) have presented some wavefront propagation path planning algorithms consisting only of free-space and obstacles in configuration space. They pre- sented two solutions to the planning problem, one for uniform region sizes and another for non-uniform region sizes. The propagation was performed by the use of a mask which was placed over successive positions on the wavefront. Various shape wavefronts could be propagated depending on the weights in the mask. Once the propa- gation was completed the path was constructed from the source to the lowest cost neighbor and this process was repeated until the destination was reached. There are two

Trail network systems among ants have received a lot of scientific attention because of their various applications in problem solving of networks. Recent studies have shown that ants select the fastest available path when facing different velocities on different substrates, rather than the shortest distance. The progress of decision making by these ants is determined by pheromone-based maintenance of paths, which is a collective decision. However, path optimization through individual decision making remains mostly unexplored. Here, we present the first study of time-optimized path selection via individual decision making by scout ants. Megaponera analis scouts search for termite-foraging sites and lead highly organized raid columns to them. The path of the scout determines the path of the column. Through installation of artificial roads around M. analis nests, we were able to influence the pathway choice of the raids. After road installation, 59% of all recorded raids took place completely or partly on the road, instead of the direct, i.e. distance-optimized, path through grass from the nest to the termites. The raid velocity on the road was more than double that on the grass, and the detour thus saved 34.77±23.01% of the travel time compared with a hypothetical direct path. The pathway choice of the ants was similar to a mathematical model of least time, allowing us to hypothesize the underlying mechanisms regulating the behavior. Our results highlight the importance of individual decision making in the foraging behavior of ants and show a new procedure of pathway optimization.

This article addresses the problem of optimal flight path planning when surveying the field using several unmanned aerial vehicles (UAVs). The trajectories of the drones are configured in order to minimize the time of the sub-areas coverage (assigned to each drone in the group), provided that the whole field is completely covered. The algorithm consists of four stages: converting the coordinates of a given field into Cartesian (metric system); splitting the field into sub-areas assigned to be covered by each drone in the group; forming the flight trajectory (plan) for each drone; and iterative minimization of the maximum time needed to cover the assigned sub-areas. The algorithm for optimal flight path planning is more time-effective than the ones where the drone moves straight from one end of the field to the other with shifts (moving along the boundary of the field at a certain distance). To implement the developed, an additional software module of the virtual simulator has been developed. The workability and the adequacy of the proposed algorithm were experimentally confirmed using a three-dimensional model of a real agriculture field in the virtual simulator.

Path planning algorithms are the most significant area in the robotics field. Path planning (PP) can be defined as the process of determining the most appropriate navigation path before a mobile robot moves. Path planning optimization refers to finding the optimal or near-optimal path. Multi-objective optimization (MOO) is concerned with finding the best solution values that satisfy multiple objectives, such as shortness, smoothness, and safety. MOO present the challenge of making decisions while balancing these contradictory issues through compromise (tradeoff). As a result, there is no single solution appropriate for all purposes in MOO, but rather a range of solutions. Several objectives are considered as part of this study, including path security, length, and smoothness, when planning paths for autonomous mobile robots in a dynamic environment with a moving target. Particle swarm optimization (PSO) algorithms are combined with bat algorithms (BA) to make a balance between exploration and exploitation. PSO algorithms used to optimize two important parameters of the bat algorithm. The proposed solution is tested through several simulations based on varying scenarios. The results demonstrate that mobile robots can travel clearly and safely along short paths and smoothly, proving this method's efficiency.

This paper presents a novel approach to process 3D point cloud data to create a 3D grid evaluation map for path planning algorithm. In particular, it is aimed at solving the 3D navigation problem by using raw point cloud as path algorithm's input. After data processing, the gained 3D grid map is able to be implemented to path planning algorithms and allowing planning a safe and optimal path in it via repeated computation of nearby nodes. The proposed approach will integrate environment survey, environment reconstruction, and path planning as a completed task, which involves learning and planning. A competed simulation of the environment topology acquisition and route planning process is documented in this paper.