Biologically inspired metaheuristic algorithms for control and scheduling of intelligent robotic systems
No Thumbnail
Lecture (Published version)
,
Prof. Marta Kosior-Kazberuk
Metadata
Show full item recordAbstract
For the implementation of stereo image-based visual servoing algorithm in the eye-in-hand robotics applications, one of the main concerns is the accurate point feature detection and matching algorithm. Since the visual servoing is carried out in the textureless environment, the feature detection process is even more challenging. To fulfil the requirement of a robust and reliable point feature detection process, in this paper we present the novel deep learning-based algorithm. The approach based on convolutional neural networks and algorithm for detection of manufacturing entities is proposed and detected regions of interest are utilized for the improvement of the point feature detection algorithm. The proposed algorithm is experimentally evaluated in real-world settings by using wheeled nonholonomic mobile robot RAICO equipped with stereo vision system. The experimental results show the improvement of 58% in the accuracy of matched point features in the images obtained during the visua...l servoing process. Moreover, with the implementation of the proposed deep learning-based approach, the number of successful experimental runs has increased by 80%.
Conclusions (Single mobile robot scheduling):
- А new biologically-inspired methods (Grey Wolf Optimization (GWO) algorithm, PSO algorithm, GA) are proposed to optimize combinatorial NP-hard single mobile robot scheduling problem;
- The optimal schedule sequence is the result of the single-objective optimization procedure and it is found based on minimum transportation time of the mobile robot;
- Experimental results indicate that the proposed biologically inspired optimization algorithms can be sucessfully applied to solve single mobile robot scheduling problem;
- The learning (optimization) goal is to find such a sequence of actuator commands using the information from the demonstration dataset that produce minimal error in the final robot pose;
Four different chaotic bioinspired methods are proposed: CGWO, CBA, CFA, CAPSO;
- Novel Grey Wolf Optimizer based on chaos (named CGWO) is evaluated on two complex trajectories with different length and unequal number of actuator commands;
Real world experiment on a nonholonomic mobile robot in indoor environment confirm effectiveness of the proposed approach based on CGWO.
Keywords:
Biologically inspired metaheuristic algorithms / Single mobile robot scheduling / Nonholonomic mobile robot RAICO / Grey Wolf Optimization (GWO) algorithm / PSO algorithm / Genetic algorithms (GA) / Optimization of combinatorial NP-hard single mobile robot scheduling problem / The optimal schedule sequence / Minimum transportation time of the mobile robot / Chaotic bioinspired methods / Novel Grey Wolf Optimizer based on chaos (named CGWO) / Real world experiment / Indoor structured environmentSource:
The International Erasmus Week at the Białystok University of Technology, Bialystok, Poland, 2018Publisher:
- The Białystok University of Technology, Bialystok, Poland
Funding / projects:
- An innovative ecologically based approach to implementation of intelligent manufacturing systems for production of sheet metal parts (RS-MESTD-Technological Development (TD or TR)-35004)
Note:
- This invited lecture was presented within the International Erasmus+ Week at the Białystok University of Technology, held from 3rd until 7th December 2018, in Bialystok, Poland.
Collections
Institution/Community
Mašinski fakultetTY - GEN AU - Petrović, Milica AU - Miljković, Zoran PY - 2018 UR - https://machinery.mas.bg.ac.rs/handle/123456789/6628 AB - For the implementation of stereo image-based visual servoing algorithm in the eye-in-hand robotics applications, one of the main concerns is the accurate point feature detection and matching algorithm. Since the visual servoing is carried out in the textureless environment, the feature detection process is even more challenging. To fulfil the requirement of a robust and reliable point feature detection process, in this paper we present the novel deep learning-based algorithm. The approach based on convolutional neural networks and algorithm for detection of manufacturing entities is proposed and detected regions of interest are utilized for the improvement of the point feature detection algorithm. The proposed algorithm is experimentally evaluated in real-world settings by using wheeled nonholonomic mobile robot RAICO equipped with stereo vision system. The experimental results show the improvement of 58% in the accuracy of matched point features in the images obtained during the visual servoing process. Moreover, with the implementation of the proposed deep learning-based approach, the number of successful experimental runs has increased by 80%. Conclusions (Single mobile robot scheduling): - А new biologically-inspired methods (Grey Wolf Optimization (GWO) algorithm, PSO algorithm, GA) are proposed to optimize combinatorial NP-hard single mobile robot scheduling problem; - The optimal schedule sequence is the result of the single-objective optimization procedure and it is found based on minimum transportation time of the mobile robot; - Experimental results indicate that the proposed biologically inspired optimization algorithms can be sucessfully applied to solve single mobile robot scheduling problem; - The learning (optimization) goal is to find such a sequence of actuator commands using the information from the demonstration dataset that produce minimal error in the final robot pose; Four different chaotic bioinspired methods are proposed: CGWO, CBA, CFA, CAPSO; - Novel Grey Wolf Optimizer based on chaos (named CGWO) is evaluated on two complex trajectories with different length and unequal number of actuator commands; Real world experiment on a nonholonomic mobile robot in indoor environment confirm effectiveness of the proposed approach based on CGWO. PB - The Białystok University of Technology, Bialystok, Poland T2 - The International Erasmus Week at the Białystok University of Technology, Bialystok, Poland T1 - Biologically inspired metaheuristic algorithms for control and scheduling of intelligent robotic systems UR - https://hdl.handle.net/21.15107/rcub_machinery_6628 ER -
@misc{ author = "Petrović, Milica and Miljković, Zoran", year = "2018", abstract = "For the implementation of stereo image-based visual servoing algorithm in the eye-in-hand robotics applications, one of the main concerns is the accurate point feature detection and matching algorithm. Since the visual servoing is carried out in the textureless environment, the feature detection process is even more challenging. To fulfil the requirement of a robust and reliable point feature detection process, in this paper we present the novel deep learning-based algorithm. The approach based on convolutional neural networks and algorithm for detection of manufacturing entities is proposed and detected regions of interest are utilized for the improvement of the point feature detection algorithm. The proposed algorithm is experimentally evaluated in real-world settings by using wheeled nonholonomic mobile robot RAICO equipped with stereo vision system. The experimental results show the improvement of 58% in the accuracy of matched point features in the images obtained during the visual servoing process. Moreover, with the implementation of the proposed deep learning-based approach, the number of successful experimental runs has increased by 80%. Conclusions (Single mobile robot scheduling): - А new biologically-inspired methods (Grey Wolf Optimization (GWO) algorithm, PSO algorithm, GA) are proposed to optimize combinatorial NP-hard single mobile robot scheduling problem; - The optimal schedule sequence is the result of the single-objective optimization procedure and it is found based on minimum transportation time of the mobile robot; - Experimental results indicate that the proposed biologically inspired optimization algorithms can be sucessfully applied to solve single mobile robot scheduling problem; - The learning (optimization) goal is to find such a sequence of actuator commands using the information from the demonstration dataset that produce minimal error in the final robot pose; Four different chaotic bioinspired methods are proposed: CGWO, CBA, CFA, CAPSO; - Novel Grey Wolf Optimizer based on chaos (named CGWO) is evaluated on two complex trajectories with different length and unequal number of actuator commands; Real world experiment on a nonholonomic mobile robot in indoor environment confirm effectiveness of the proposed approach based on CGWO.", publisher = "The Białystok University of Technology, Bialystok, Poland", journal = "The International Erasmus Week at the Białystok University of Technology, Bialystok, Poland", title = "Biologically inspired metaheuristic algorithms for control and scheduling of intelligent robotic systems", url = "https://hdl.handle.net/21.15107/rcub_machinery_6628" }
Petrović, M.,& Miljković, Z.. (2018). Biologically inspired metaheuristic algorithms for control and scheduling of intelligent robotic systems. in The International Erasmus Week at the Białystok University of Technology, Bialystok, Poland The Białystok University of Technology, Bialystok, Poland.. https://hdl.handle.net/21.15107/rcub_machinery_6628
Petrović M, Miljković Z. Biologically inspired metaheuristic algorithms for control and scheduling of intelligent robotic systems. in The International Erasmus Week at the Białystok University of Technology, Bialystok, Poland. 2018;. https://hdl.handle.net/21.15107/rcub_machinery_6628 .
Petrović, Milica, Miljković, Zoran, "Biologically inspired metaheuristic algorithms for control and scheduling of intelligent robotic systems" in The International Erasmus Week at the Białystok University of Technology, Bialystok, Poland (2018), https://hdl.handle.net/21.15107/rcub_machinery_6628 .
Related items
Showing items related by title, author, creator and subject.
-
Single Mobile Robot Scheduling Problem: A Survey of Current Biologically Inspired Algorithms, Research Challenges and Real-World Applications
Miljković, Zoran; Petrović, Milica (The Academy of Sciences and Arts of Bosnia and Herzegovina, Sarajevo, 2019) -
Q-Learning Algorithm for a Mobile Robot Obstacle Avoidance in an Unknown Environment Based on Artificial Neural Networks
Miljković, Zoran; Mitić, Marko; Babić, Bojan; Diryag, Ali (The Aristotle University of Thessaloniki, 2011) -
Stereo vision-based algorithm for control of nonholonomic mobile robot
Đokić, Lazar; Jokić, Aleksandar; Petrović, Milica; Miljković, Zoran (Proceedings of selected papers and abstracts of the The Third International Students Scientific Conference "Multidisciplinary Approach to Contemporary Research - Cultural and Industrial Heritage", Belgrade, 21-22.12. 2019, 2019)