Bio-inspired approach to learning robot motion trajectories and visual control commands
Abstract
In this paper, a novel bio-inspired learning control approach (BILCA) for mobile robots based on Learning from Demonstration (LfD), Firefly Algorithm (FA), and homography between current and target camera view is developed. BILCA consists of two steps: (i) first step in which the actuator commands are learned using FA and demonstrations of desired behavior, and (ii) second step in which the obtained wheel commands are evaluated through the real world experiment. Two different problems are considered in this study: trajectory reproduction, and generation of visual control commands for correction of robot orientation. Developed simulations are used to evaluate BILCA in the domain of learning actuator commands for reproduction of different complex trajectories. Results show that the bigger firefly swarms produce better results in terms of accuracy in the final mobile robot pose, and that the desired trajectory is reproduced with minimal error in final control iteration. Likewise, simulati...ons prove that the FA outperforms other metaheuristic techniques. Experiment conducted on a real mobile robot in indoor environment unifies two considered problems within a single transportation task. Depending of the feature position in the image plane, the homography controller for forward motion or the BILCA based controller for robot orientation correction is employed. Experimental results show the applicability and effectiveness of the developed intelligent approach in real world conditions.
Keywords:
Visual control / Particle Swarm Optimization / Mobile robot / Learning from Demonstration / Homography / Firefly Algorithm / Bat AlgorithmSource:
Expert Systems With Applications, 2015, 42, 5, 2624-2637Publisher:
- Pergamon-Elsevier Science Ltd, Oxford
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)
DOI: 10.1016/j.eswa.2014.10.053
ISSN: 0957-4174
WoS: 000348619900031
Scopus: 2-s2.0-84919363429
Collections
Institution/Community
Mašinski fakultetTY - JOUR AU - Mitić, Marko AU - Miljković, Zoran PY - 2015 UR - https://machinery.mas.bg.ac.rs/handle/123456789/2194 AB - In this paper, a novel bio-inspired learning control approach (BILCA) for mobile robots based on Learning from Demonstration (LfD), Firefly Algorithm (FA), and homography between current and target camera view is developed. BILCA consists of two steps: (i) first step in which the actuator commands are learned using FA and demonstrations of desired behavior, and (ii) second step in which the obtained wheel commands are evaluated through the real world experiment. Two different problems are considered in this study: trajectory reproduction, and generation of visual control commands for correction of robot orientation. Developed simulations are used to evaluate BILCA in the domain of learning actuator commands for reproduction of different complex trajectories. Results show that the bigger firefly swarms produce better results in terms of accuracy in the final mobile robot pose, and that the desired trajectory is reproduced with minimal error in final control iteration. Likewise, simulations prove that the FA outperforms other metaheuristic techniques. Experiment conducted on a real mobile robot in indoor environment unifies two considered problems within a single transportation task. Depending of the feature position in the image plane, the homography controller for forward motion or the BILCA based controller for robot orientation correction is employed. Experimental results show the applicability and effectiveness of the developed intelligent approach in real world conditions. PB - Pergamon-Elsevier Science Ltd, Oxford T2 - Expert Systems With Applications T1 - Bio-inspired approach to learning robot motion trajectories and visual control commands EP - 2637 IS - 5 SP - 2624 VL - 42 DO - 10.1016/j.eswa.2014.10.053 ER -
@article{ author = "Mitić, Marko and Miljković, Zoran", year = "2015", abstract = "In this paper, a novel bio-inspired learning control approach (BILCA) for mobile robots based on Learning from Demonstration (LfD), Firefly Algorithm (FA), and homography between current and target camera view is developed. BILCA consists of two steps: (i) first step in which the actuator commands are learned using FA and demonstrations of desired behavior, and (ii) second step in which the obtained wheel commands are evaluated through the real world experiment. Two different problems are considered in this study: trajectory reproduction, and generation of visual control commands for correction of robot orientation. Developed simulations are used to evaluate BILCA in the domain of learning actuator commands for reproduction of different complex trajectories. Results show that the bigger firefly swarms produce better results in terms of accuracy in the final mobile robot pose, and that the desired trajectory is reproduced with minimal error in final control iteration. Likewise, simulations prove that the FA outperforms other metaheuristic techniques. Experiment conducted on a real mobile robot in indoor environment unifies two considered problems within a single transportation task. Depending of the feature position in the image plane, the homography controller for forward motion or the BILCA based controller for robot orientation correction is employed. Experimental results show the applicability and effectiveness of the developed intelligent approach in real world conditions.", publisher = "Pergamon-Elsevier Science Ltd, Oxford", journal = "Expert Systems With Applications", title = "Bio-inspired approach to learning robot motion trajectories and visual control commands", pages = "2637-2624", number = "5", volume = "42", doi = "10.1016/j.eswa.2014.10.053" }
Mitić, M.,& Miljković, Z.. (2015). Bio-inspired approach to learning robot motion trajectories and visual control commands. in Expert Systems With Applications Pergamon-Elsevier Science Ltd, Oxford., 42(5), 2624-2637. https://doi.org/10.1016/j.eswa.2014.10.053
Mitić M, Miljković Z. Bio-inspired approach to learning robot motion trajectories and visual control commands. in Expert Systems With Applications. 2015;42(5):2624-2637. doi:10.1016/j.eswa.2014.10.053 .
Mitić, Marko, Miljković, Zoran, "Bio-inspired approach to learning robot motion trajectories and visual control commands" in Expert Systems With Applications, 42, no. 5 (2015):2624-2637, https://doi.org/10.1016/j.eswa.2014.10.053 . .