A path planning method using adaptive polymorphic ant colony algorithm for smart wheelchairs

doi:10.1016/j.jocs.2018.02.004

Journal of Computational Science

Volume 25, March 2018, Pages 50-57

https://doi.org/10.1016/j.jocs.2018.02.004 Get rights and content

Highlights

•
Determining the optimal combination parameters in accordance with actual situation.
•
Maintaining the randomness in searching the global optimal solution for smart wheelchairs.
•
Making the state transition to prevent the search ant from falling into local optimum for path planning.
•
Helping to accelerate convergence to improve the algorithm efficiency in searching the global optimal solution.

Abstract

In many cases, users of smart wheelchairs have difficulties with daily maneuvering tasks and would benefit from an automated navigation system. With multi-colony division and cooperation mechanism, the polymorphic ant colony algorithm is helpful to solve optimal path planning problems by greatly improving search and convergence speed. In this paper, a path planning method for smart wheelchairs is proposed based on the adaptive polymorphic ant colony algorithm. To avoid ant colony from getting into local optimum in the process of reaching a solution, the adaptive state transition strategy and the adaptive information updating strategy were employed in the polymorphic ant colony algorithm to guarantee the relative importance of pheromone intensity and desirability. Subsequently, the search ant maintains the randomness for the search of the global optimal solution, and then the deadlock problem is solved by means of the direction determination method that improves the global search ability of the algorithm. The target path planning and obstacle path planning are respectively carried out by using the adaptive polymorphic ant colony algorithm. Experimental results indicate that the proposed method provides better performance than the improved ant colony algorithm and the polymorphic ant colony algorithm. Furthermore, the efficiency of finding an optimum solution is higher than the average polymorphic ant colony algorithm. The proposed method, which achieves superior performance in path planning for smart wheelchairs, is even racing ahead of other state-of-the-art solutions. In addition, this study reveals the feasibility of using it as an effective and feasible planning path tool for future healthcare systems.

Introduction

Smart wheelchairs give people with disabilities not only mobility but also the necessary help and support to handle daily living activities. The smart wheelchair combines a variety of research fields, such as machine vision [1], robot navigation and positioning [2], pattern recognition [3], multi-sensor fusion [4] and human-machine interface [5]. Especially in automatic navigation, accurate path planning results will greatly improve the performance of a smart wheelchair [6]. It is desirable to use reliable path planning methods to enhance awareness of the status of contemporary smart wheelchair technology, and ultimately increase the functional mobility and productivity of users. Intelligent optimization algorithms, which are simple, efficient and adaptive, have been introduced to solve path planning problems, especially in infrastructures and facilities for healthcare [[7], [8], [9]]. Ant colony optimization is an intelligent search algorithm developed by Marco Dorigo’s doctoral thesis from a long-term observation of ant colony foraging behaviors [10]. Different from other path planning techniques, for instance, heuristic search or potential fields, it is a probabilistic technique for solving computational problems which can be reduced to finding good paths through graphs. Hence ant colony algorithm has widely used in transportation, logistics and distribution, network analysis, pipeline and other fields in recent years [[11], [12]].

At present, a large number of scholars are doing applied research on the ant colony algorithm. For instance, Xia et al. studied the issues of dynamic nature, instability and multi QoS property restrictions of Web service in the process of services combinatorial optimization, and proposed a multiple pheromone dynamically updated ant colony algorithm [13]. Sheng et al. proposed a credible service discovery method based on the improved ant colony algorithm for the service discovery problems in the unstructured P2P networks [14]. Luo et al. proposed an improved ant colony algorithm based on dynamic node planning for the problem of selection of optimal measuring points for analog circuit [15]. Shan et al. employed the ant colony algorithm to the smart wheelchair path planning method to solve the problems of local optimal in the path search process for the smart wheelchair [16]. Mohamed et al. proposed multi-division vehicle routing problems based on the hybrid ant colony algorithm by combining local search and basic ant colony algorithm [17]. Although the ant colony algorithm is widely used, and reflects good search features during the path optimization, it has shortcomings of likeliness to fall into local optimum and long search time, etc [[18], [19]].

In traditional ant colony algorithms, the paths are gradually explored by ants and the search efficiency of the algorithms is low. To solve this problem, many scholars put forward some improved methods to cope with such problem. Yao et al. put forward the adaptive parallel ant colony algorithm [20]. With the aid of this method, it can determine the optimal combination of parameters depending on the search stage to avoid stagnation to a certain extent. Hu et al. applied dynamic calls and the rule of increase of pheromone on the optimal path into the basic ant colony algorithm, and proposed the optimal path model with a number of path quality constraints [21]. Du et al. designed the improved polymorphic ant colony algorithm based on the secondary annealing mechanism according to the advantages of the polymorphic ant colony algorithm and the simulated annealing algorithm, allowing the pheromone release to reflect the path quality better than before [22]. Li et al. introduced the roulette method to the state transition rule, and classified the search into local search and global search. By doing so, it avoid the algorithm from falling into local optimum [23]. Yang et al. proposed the improved ant colony algorithm by combining group intelligence and local search, effectively solving the multi-dimensional problem in the traveling salesman problems [24].

Containing a variety of ant colonies and pheromones, the polymorphic ant colony algorithm combines local search and global search, allowing the searching speed and convergence speed to be greatly improved [[25], [26], [27]]. In this paper, an adaptive polymorphic ant colony algorithm is proposed to solve the path planning problem in smart wheelchairs. The search ant makes state transition according to the pseudo-random rule, and combines the state transition strategy and the adaptive parallel strategy of the search ant during the search to get the adaptive state transition strategy and the adaptive information strategy to avoid the algorithm from falling into local optimum. By employing the direction determining method, the deadlock problem was properly addressed and the increased efficiency of global search in a complex environment is achieved. The adaptive polymorphic ant colony algorithm proposed is applied separately to the target path and obstacle path planning experiments, and the experimental results are compared with the results obtained from the improved ant colony algorithm and the general polymorphic ant colony algorithm. The comparison shows, that the adaptive algorithm in this paper is better to implement the path planning for smart wheelchairs with fewer iterations and higher search efficiency.

Section snippets

Polymorphic ant colony algorithm

The multi-colony ant colony is introduced into the polymorphic ant colony algorithm based on the basic ant colony algorithm, which includes scouts, search and worker ants. Scouts take the path node of each wheelchair as the center and leave the investigation elements during the investigation, so that search ants may make a choice when they arrive at the path node. Scouts and search ants work in the polymorphic ant colony and perform tasks as follows:

Scouts: The scouts (quantity: m) are placed

Adaptive polymorphic ant colony algorithm

In the polymorphic ant colony algorithm, search ants may still fall into local optimum in the range determined by the investigation elements, and the pheromone intensity and the desired intensity are ignored in the iterations. Based on polymorphic ant colony algorithm, the adaptive parallel rule and the pseudo-random proportion rule are introduced in this paper to effectively avoid the problem of local optimum in the search process. Search ants makes a state transition in accordance with the

Experimental results

The traveling salesman problem (TSP) asks for an optimal tour through a specified set of points [33]. To solve a particular instance of the problem, it is necessary to find a shortest tour and verify that no better tour exists. Some techniques can be employed in the Concorde code for the TSP, focusing on the difficult verification task [34]. A typical one is to select a path for the wheelchair to visit every point exactly once and return to the initial position. Lots of previous work has

Conclusions

In this paper, the adaptive polymorphic ant colony algorithm is proposed as a path planning method for smart wheelchairs. The search ant can determine the optimal combination parameters in accordance with actual situation and make the state transition in the search process to effectively prevent the search ant from falling into local optimum to a certain extent. The direction determining method also employed to accelerate convergence, improving the efficiency of the algorithm in searching the

Acknowledgements

The authors would like to thank the reviewers and the editors for their valuable comments and suggestions on improving this paper. This work is supported by the University Natural Science Research Program of Jiangsu Province (No. 17KJB510003).

Zhuqing Jiao is presently an Associate Professor at the School of Information Science and Engineering, Changzhou University, China. He received his Ph.D. in Jiangnan University, Wuxi, in 2011. His current projects are in the areas of intelligent computing and healthcare system, etc.

References (34)

Yeounggwang Ji et al.
An intelligent wheelchair using situation awareness and obstacle detection
Proc. − Soc. Behav. Sci.
(2013)
Yudong Zhang et al.
A novel algorithm for all pairs shortest path problem based on matrix multiplication and pulse coupled neural network
Digital Signal Process.
(2011)
Changman Son
Intelligent rule-based sequence planning algorithm with fuzzy optimization for robot manipulation tasks in partially dynamic environments
Inform. Sci.
(2016)
Mohamed Abdulkader et al.
Hybridized ant colony algorithm for the multi compartment vehicle routing problem
Appl. Soft Comput.
(2015)
Adem Tuncer et al.
Dynamic path planning of mobile robots with improved genetic algorithm
Comput. Electr. Eng.
(2012)
Fanghong Guo et al.
A distributed hierarchical algorithm for multi-cluster constrained optimization
Automatica
(2017)
Yudong Zhang et al.
Binary PSO with mutation operator for feature selection using decision tree applied to spam detection
Knowl.-Based Syst.
(2014)
Hailong Huang et al.
Viable path planning for data collection robots in a sensing field with obstacles
Comput. Commun.
(2017)
Snehlata Yadav
Poonam sheoran smart wheelchairs – a literature review
Int. J. Innov. Emerg. Res. Eng.
(2016)
Jesse Leaman et al.
A comprehensive review of smart wheelchairs: past, present and future
IEEE Trans. Hum.-Mach. Syst.
(2017)

Mohammed-Amine Hadj-Abdelkader et al.

Haptic feedback control of a smart wheelchair

Appl. Bionics Biomech.

(2014)

Sarangi P. Parikh et al.

Integrating human inputs with autonomous behaviors on an intelligent wheelchair platform

IEEE Intell. Syst.

(2007)

BingFei Wu et al.

The graphic feature node based dynamic path planning and fuzzy based navigation for intelligent wheelchair robots

J. Converg. Inform. Technol.

(2013)

Yang Chen et al.

Curve-like structure extraction using minimal path propagation with backtracking

IEEE Trans. Image Process.

(2016)

Yudong Zhang et al.

Pathological brain detection in MRI scanning via Hu moment invariants and machine learning

J. Exp. Theor. Artif. Intell.

(2017)

Jingming Xu et al.

Polymorphic ant colony algorithm

J. Univ. Sci Technol. China

(2005)

Yudong Zhang et al.

Comparison of machine learning methods for stationary wavelet entropy-based multiple sclerosis detection: decision tree, k-nearest neighbors, and support vector machine

Simulation

(2016)

Cited by (72)

An enhanced ant colony optimization algorithm for global path planning of deep-sea mining vehicles
2024, Ocean Engineering
Due to the complex variations in slope within deep-sea mining areas, effective path planning for mining vehicle operations is crucial for minimizing energy consumption. However, traditional ant colony algorithms (ACO) neglect the effect of a terrain slope in mining areas. Additionally, these algorithms exhibit limitations such as slow convergence and susceptibility to local optima. To address these issues, this study proposes an enhanced ant colony algorithm, called DYACO, for mining vehicle path optimization. This algorithm dynamically adjusts heuristic information, pheromone volatilization factor, pheromone update strategy, and state transition probability during the iterative process to enhance traditional ACO. Simulation experiments were conducted to comprehensively assess the proposed model, revealing that DYACO not only generates optimal solutions but also demonstrates significant advantages in terms of convergence speed and turning times. Furthermore, DYACO converts the time required for mining vehicles to traverse different slope regions into distances, then incorporating slope effects to path planning for deep-sea mining vehicles. In comparison to ACO, DYACO achieves a 15.3% reduction in the length of an optimal path and a 70.0% decrease in the number of turn times.
Autonomous control of UAV trajectory based on RHC-Radau method in complex penetration combat environment
2024, Aerospace Science and Technology
Unmanned aerial vehicle (UAV) systems are required to independently make timely and accurate attack and control strategies according to dynamic battlefield situations. To optimize the trajectory control of UAVs for ground penetration combat, a 3-degree-of-freedom model and a dynamic model of UAV were established. Considering the constraints of initial and terminal conditions and flight performance, the penetration combat model under multiple constraints is established. A dynamic radar cross section (RCS) threat model is demonstrated based on characteristics of RCS. Combined with the hp-adaptive-Radau pseudo-spectral method and the receding horizon control algorithm under the optimal control model, the flight time and the threat probability of the UAV to the combat area were taken as the objective functions. An algorithm to adaptively adjust the weight coefficient of the performance index and switch the sub-objective function was used. The simulation results show that the proposed method can realize autonomous control of UAV attack trajectory under complex battlefield environment and multiple constraints. It can generate UAV flight path with little threat and short time and output relevant state and control parameters.
Path planning techniques for mobile robots: Review and prospect
2023, Expert Systems with Applications
Mobile robot path planning refers to the design of the safely collision-free path with shortest distance and least time-consuming from the starting point to the end point by a mobile robot autonomously. In this paper, a systematic review of mobile robot path planning techniques is presented. Firstly, path planning is classified into global path planning and local path planning according to the mastery of environmental information. In the global path planning, environment modeling methods and path evaluation method are introduced. The methods of environment modeling include grid method, topology method, geometric feature method and mixed representation method. In the local path planning, we introduce the sensors commonly used in the detection environment, including laser radar and visual sensor. Next, according to the characteristics of algorithms, mobile robot path planning algorithms are divided into three categories: classical algorithms, bionic algorithms and artificial intelligence algorithms. Among the classical algorithms, we introduce the cell decomposition method, sampling based method, graph search algorithm, artificial potential field method and dynamic window method. In the algorithm based on bionics, we introduce genetic algorithm, ant colony algorithm, gray wolf algorithm, etc. in detail. In artificial intelligence algorithm, we introduce neural network algorithm and fuzzy logic. Finally, we compare the key technologies of mobile robot path planning in the form of graphs and charts based on the classification statistics of the collected literature to provide references for future research.
An improved heuristic mechanism ant colony optimization algorithm for solving path planning
2023, Knowledge-Based Systems
With the development of artificial intelligence algorithms, researchers are attracted to intelligent path planning due to its broad applications and potential development. The ant colony optimization (ACO) algorithm is one of the most widely used methods to solve path planning. However, the traditional ACO has some shortcomings such as low search efficiency, easy stagnation, etc. In this study, a novel variant of ACO named improved heuristic mechanism ACO (IHMACO) is proposed. The IHMACO contains four improved mechanisms including adaptive pheromone concentration setting, heuristic mechanism with directional judgment, improved pseudo-random transfer strategy, and dynamic adjustment of the pheromone evaporation rate. In detail, the adaptive pheromone concentration setting and heuristic mechanism with directional judgment are presented to enhance the purposiveness and reduce turn times of planned path. The improved pseudo-random transfer strategy and dynamic adjustment of the pheromone evaporation rate are introduced to enhance search efficiency and global search ability, further avoiding falling into local optimum. Subsequently, a series of experiments are conducted to test effectiveness of the four mechanisms and verify the performance of the presented IHMACO. Compared with 15 existing approaches for solving path planning, including nine variants of ACO and six commonly used deterministic search algorithms. The experimental results indicate that the relative improvement percentages of the proposed IHMACO in terms of the path turn times are 33.33%, 83.33%, 35.29%, 38.46%, and 38.46% respectively, demonstrating the superiority of IHMACO in terms of the availability and high-efficiency.
Design of constrained dynamic path planning algorithms in large-scale 3D point cloud maps for UAVs
2023, Journal of Computational Science
The technology of unmanned aerial vehicles (UAVs) has been growing rapidly in recent years. To achieve highly autonomous flight capability, collision-free path generation becomes a key research topic. However, for a large-scale terrain map, an efficient path searching algorithm is always a challenging problem. Based on the Goal-bias Rapidly-exploring Random Tree Star (GB-RRT*) together with the aid of a bidirectional search technique, in this paper, a new constrained path planning algorithm, called Parent Revisited Goal and Parent Bias RRT* (PRGPB-RRT*), is proposed. Three major objectives are considered as the development benchmark: 1). shorter total distance, 2). smoother flight path, and 3). high computational efficiency. To meet different task requirements, a dynamic path planning method is investigated to diminish the high costs due to large-scale environments and keep track of the changing destination by finding local target points. In addition, unknown object avoidance is an essential part of flight path planning. As a consequence, the Fitting-Octree is presented to partition the point clouds into multiple cubes to represent the obstacles precisely. Moreover, the method of grouping point clouds into clusters effectively increases the efficiency of the implementation under a large number of obstacles. Finally, the feasibility of the proposed method is verified by a real-world 3D large-scale point cloud map. Experiments show that the proposed method successfully enhances the path generation efficiency as well as the trajectory smoothness. Moreover, the presented PRGPB-RRT* can be applied to different intelligent UAVs subject to flight kinematics constrain.
3D path planning for a robot based on improved ant colony algorithm
2024, Evolutionary Intelligence

View all citing articles on Scopus

Kai Ma is a Doctor’s Degree candidate at the College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, China. He received his Master’s Degree in Changzhou University, Changzhou, in 2017. His research interests encompass intelligent computing and complex networks.

Yiling Rong is presently a National Registered Urban Planner at Changzhou Urban Planning Compilation and Research Centre, China. She received her Master’s Degree in Southeast University, Nanjing, in 2011. Her research interests include overall plan and path plan.

Peng Wang is a Master’s Degree candidate at the Institute of Robotics, Changzhou University, China. He received his BS in Changzhou University, Changzhou, in 2015. His research interest is robot control system.

Hongkai Zhang is presently an Assistant Professor at the School of Electronic and Information Engineering, Anhui Jianzhu University, China. He received his Master’s Degree in Jiangnan University, Changzhou, in 2007. His current research focuses on artificial intelligence and pattern recognition technologies.

Shuihua Wang is currently an Assistant Professor at the Department of Informatics, University of Leicester, UK. She received her Ph.D. from Nanjing University, in 2016. Her research interest is biomedical image processing and computer aided diagnosis.

View full text

A path planning method using adaptive polymorphic ant colony algorithm for smart wheelchairs

Highlights

Abstract

Introduction

Section snippets

Polymorphic ant colony algorithm

Adaptive polymorphic ant colony algorithm

Experimental results

Conclusions

Acknowledgements

Proc. − Soc. Behav. Sci.

Digital Signal Process.

Inform. Sci.

Appl. Soft Comput.

Comput. Electr. Eng.

Automatica

Knowl.-Based Syst.

Comput. Commun.

Poonam sheoran smart wheelchairs – a literature review

Int. J. Innov. Emerg. Res. Eng.

A comprehensive review of smart wheelchairs: past, present and future

IEEE Trans. Hum.-Mach. Syst.

Haptic feedback control of a smart wheelchair

Appl. Bionics Biomech.

Integrating human inputs with autonomous behaviors on an intelligent wheelchair platform

IEEE Intell. Syst.

The graphic feature node based dynamic path planning and fuzzy based navigation for intelligent wheelchair robots

J. Converg. Inform. Technol.

Curve-like structure extraction using minimal path propagation with backtracking

IEEE Trans. Image Process.

Pathological brain detection in MRI scanning via Hu moment invariants and machine learning

J. Exp. Theor. Artif. Intell.

Polymorphic ant colony algorithm

J. Univ. Sci Technol. China

Comparison of machine learning methods for stationary wavelet entropy-based multiple sclerosis detection: decision tree, k-nearest neighbors, and support vector machine

Simulation