KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Has files: NoSubject: search.filters.subject.A

Search Results

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Obstacle Avoidance Path Planning for Apple Picking Robotic Arm Incorporating Artificial Potential Field and A∗Algorithm
    (2023-01-01)
    Zhuang, Min
    ;
    Li, Ge
    ;
    Ding, Kexin
    With the development and maturity of the automated robotics industry, more and more apple plantations are introducing automated picking robotic arms for fruit picking. However, the complex environment in which apple fruit is picked has made it an urgent problem to optimise the robot's picking performance through obstacle avoidance path planning. The experiment selects the Six degrees of freedom manipulator as the research object, and on the basis of its Kinematics analysis, introduces the introduction of artificial potential field (APF) to carry out the path planning of the manipulator. At the same time, it integrates it with A∗ algorithm to jointly achieve the optimization of the parameters of the obstacle avoidance path of the manipulator. In addition, in order to avoid parameter optimization falling into local extremum during the path planning process, the IRRT algorithm is incorporated to re plan the path, improve the smoothness of the path, and finally verify its obstacle avoidance effect through simulation experiments. The results showed that in the convergence comparison, the research method had the minimum loss function value and the stable fitness value as soon as the iteration proceeded to the 50th and 20th generation, respectively. A On the dataset, the research method had the minimum MAPE value when the iteration proceeded to the 45th generation, with a value close to 0. At the same moment, the MAPE values of the IAPF algorithm, the IRRT algorithm and the literature were 0.052%, 0.108% and 0.218%, respectively. In the practical application analysis, when the robot arm starts running in three different starting positions a, b and c, the IRRT algorithm's obstacle avoidance path has a larger arc and tends to reach the target location through a longer path, while the research method tends to find a relatively closer obstacle avoidance path that can be passed smoothly. The above results show that the research method is highly adaptable to robotic arm path avoidance planning and can complete obstacle avoidance path planning faster and more reasonably, providing new technical support for optimising the path planning system of apple picking robots.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Optimal A∗ Path Planning with Ant Colony Optimization on Multi-Robot Task Allocation for Manufacturing Model
    (2021-04-23)
    Praserttaweelap, Rawinun
    ;
    Kiatwanidvilai, Somyot
    This paper presents the optimal path planning by using A∗ with ant colony optimization based on the multi-robot systems. The purpose of this research is to design an appropriate path planning model for manufacturing. The safety path and the processing time are the priority of the manufacturing. The main contribution of this study is the A∗ for path planning with the ant colony optimization for the lowest risk of collision (RC) searching. The 5 robots condition is the best condition for the minimum RC and the minimum processing time. The simulation results represent the suitable path planning prediction model for manufacturing systems.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Multidestination Indoor Navigation Using Path Planning and WiFi Fingerprint Localization
    (2018-09-11)
    Chitsobhuk, Orachat
    ;
    Warunsin, Kulwarun
    ;
    Udomthanapong, Sornchai
    This paper presents an indoor navigation system based on multi-destination path planning and WiFi fingerprint localization. A user is allowed to specify multiple destinations and can detour the route at any time. Path planning will automatically update path using 2-opt and A∗ algorithms. The revised route will be analyzed according to user's current position supplied from the WiFi RSS fingerprint positioning. Naïve Bayes classification is adopted to learn from the RSS fingerprint priors stored in the database. Extensive experiments are conducted and performance comparison is analyzed and demonstrates significant performance improvement and higher noise tolerance with integration of the probabilistic priors. It can be seen that the proposed system enables user experience for indoor navigation service with support for automatic route updating and navigation refinement according to localization.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Improving ID3 Algorithm by Using A∗ Search
    (2018-08-21)
    Kaewrod, Nicha
    ;
    Jearanaitanakij, Kietikul
    ID3 is one of the most widely used algorithms for creating a classification decision tree. However, the traditional ID3 algorithm has a difficulty when there are equally important attributes during the decision node construction. It randomly selects one of the most important attributes to serve as the current decision node. This behavior may lead to the resulting decision tree which contains unnecessary depths and suboptimal accuracy. The purpose of this paper is to find the near optimal depth decision tree of the dataset, which contains an equally important attributes problem, by using the A-Star (A∗) search. The experiment results on four standard datasets from UCI indicate that the proposed algorithm can significantly reduce the decision tree's depth and still maintain the classification accuracy.