Evolutionary artificial potential fields and their application in real time robot path planning

  title={Evolutionary artificial potential fields and their application in real time robot path planning},
  author={Prahlad Vadakkepat and Kay Chen Tan and Wang Ming-Liang},
  journal={Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512)},
  pages={256-263 vol.1}
A new methodology named Evolutionary Artificial Potential Field (EAPF) is proposed for real-time robot path planning. The artificial potential field method is combined with genetic algorithms, to derive optimal potential field functions. The proposed EAPF approach is capable of navigating robot(s) situated among moving obstacles. Potential field functions for obstacles and goal points are also defined. The potential field functions for obstacles contain tunable parameters. The multi-objective… 
An Evolutionary Artificial Potential Field Algorithm for Dynamic Path Planning of Mobile Robot
A new APF method for path-planning of mobile robots in a dynamic environment where the target and obstacles are moving is proposed, and the new force function and the relative threat coefficient function are defined.
Optimal Path Planning Generation for Mobile Robots using Parallel Evolutionary Artificial Potential Field
This innovative proposal integrates the original APF, evolutionary computation and parallel computation for taking advantages of novel processors architectures, to obtain a flexible path planning navigation method that takes all the advantages of using the APF and the EAPF, strongly reducing their disadvantages.
Mobile robot navigation using PSO-optimized fuzzy artificial potential field with fuzzy control
A new method based on combination of a modified APF algorithm with fuzzy logic (i.e. FAPF) is proposed to overcome the problems of the classical APF especially the local minima and enhances the navigation in complex environments.
A Hybrid Artificial Potential Field: Genetic Algorithm Approach to Mobile Robot Path Planning in Dynamic Environments
A hybrid Artificial Potential Field—Genetic Algorithm approach is developed and implemented for mobile robot path planning in dynamic environments that uses an evolutionary population initialization and genetic operators to make the evolutionary process converge very efficiently.
New potential functions for multi robot path planning : SWARM or SPREAD
This paper enables distributed path planning in multi-robot with real-time using suggested APF, which uses priority selection scheme between multi robots and calculates a new potential functions based on priority, and then solves local minimum problem in multi -robot APF.
An Improved Path Planning Method Based on Artificial Potential Field for a Mobile Robot
Comparison of the improved method proposed in this paper and the traditional artificial potential field method is performed by simulation and results show that the improved algorithm gets rid of the drawbacks, such as local minima and unreachable goal.
Modified artificial potential field method for online path planning applications
This paper presents a modified potential field method for mobile robots and intelligent vehicles local navigation. The approach overcomes the well-known artificial potential field (APF) method issue,
An Optimization Path Planning Method Based on Evolutionary Artificial Potential Field
  • F. Li
  • Computer Science
  • 2013
An evolutionary way for the robot to plan path based on the Evolutionary Artificial Potential Field approach is presented and it is shown that the optimized algorithm is an effective way to solve the local minimum problem.


An evolutionary method for active learning of mobile robot path planning
  • Byoung-Tak Zhang, Sung-Hoon Kim
  • Computer Science
    Proceedings 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA'97. 'Towards New Computational Principles for Robotics and Automation'
  • 1997
A new method for evolutionary path planning which can be used online in real-time, which uses an evolutionary algorithm as a means for active learning of a route map for the path planner to generate online a path for the source-destination pair.
Fast path planning available for moving obstacle avoidance by use of Laplace potential
A new navigation function for path planning that is available for moving obstacle avoidance for an autonomous mobile robot by the use of the Laplace potential is feasible to guide, in real time, a mobile robot avoiding arbitrarily moving obstacles and reaching the goal.
Genetic-based adaptive fuzzy controller for robot path planning
This methodology uses a genetic-based adaptive fuzzy controller to navigate the robot from the starting location to the goal location safely and smoothly and shows robust learning capability and better performance.
An evolutionary algorithm for collision free motion planning of multi-arm robots
This paper presents an evolutionary algorithm for collision-free path planning of multi-arm robots that uses evolutionary techniques to minimise path lengths, uneven distribution of via-points on the paths to minimising variation in velocity and to minimised the collision between the robots.
Collision avoidance planning of a robot manipulator by using genetic algorithm. A consideration for the problem in which moving obstacles and/or several robots are included in the workspace
  • N. Baba, N. Kubota
  • Business
    Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence
  • 1994
It is shown that path planning and the collision avoidance planning problem of a robot manipulator whose workspace includes moving obstacles can be solved successfully by using a genetic algorithm.
A comparative study on the path length performance of maze-searching and robot motion planning algorithms
  • V. Lumelsky
  • Computer Science
    IEEE Trans. Robotics Autom.
  • 1991
A comparison shows that the special structure of graphs that correspond to planar environments with obstacles actually makes it possible to exceed the efficiency of general maze-searching algorithms.
Genetic path planning for mobile robots
  • M. Gerke
  • Computer Science
    Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251)
  • 1999
A genetic approach to path optimization of autonomous mobile robot guidance and control during outdoor missions, where a lack of vehicular resources has to be handled, and Evolutionary computation is used to carry out path optimization.
The vector field histogram-fast obstacle avoidance for mobile robots
A real-time obstacle avoidance method for mobile robots which has been developed and implemented is described. This method, named the vector field histogram (VFH), permits the detection of unknown
Global and local path planning in natural environment by physical modeling
  • Benoit Chanclou, Annie Luciani
  • Computer Science
    Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96
  • 1996
A new physically based potential method is introduced to find paths such as, for instance, a winding path to a pass in natural sites where vehicles have to cope with a geometrically unstable environment and thus have a complex dynamic behavior.
A neural network-based navigation system for mobile robots
This neural network-based navigation system offers a method of determining the mobile robot's position-a 3D landmark sensing system with neural estimator, and a neural net-based feedforward controller designed to accurately track a desired path and a sensor-based local path planning capability to adapt to complex and changing environments.