Abstract In the original paradigm, robots had to play the focal role of considering all situations under which they made decisions and operate. Such paradigm makes it difficult to respond efficiently to the dynamicall...
详细信息
Abstract In the original paradigm, robots had to play the focal role of considering all situations under which they made decisions and operate. Such paradigm makes it difficult to respond efficiently to the dynamically shifting environment. In order to handle situations that change dynamically in an efficient manner, a technology that allows a dynamic execution of data transmission and connection between robots based on scenarios is required. In this paper, we represent an evolutionary robot that adapts to any given environment and executes scenarios with an R-Object model. Scenario-based R-Object models allow dynamic reconstruction and they've been tested and validated through simulators. The proposed R-Object model will propose an effective control mechanism for dynamically shifting environments.
This paper proposes a new learning approach for evolving dynamic gaits of a hexapod robot. The controller that coordinates the leg movements consists of fully connected recurrent neural networks (FCRNNs). To automate ...
详细信息
This paper proposes a new learning approach for evolving dynamic gaits of a hexapod robot. The controller that coordinates the leg movements consists of fully connected recurrent neural networks (FCRNNs). To automate the FCRNN parameter design, a symbiotic species-based particle swarm optimization (SSPSO) algorithm is proposed. There are multiple swarms in the SSPSO, where a swarm only optimizes the relevant parameters to a single node. The number of swarms is equal to the number of nodes in an FCRNN. The symbiotic behavior of particles from different swarms corresponds to the symbiotic structure of different nodes in an FCRNN. For a particle update, particles in different swarms update independently using a local version of particle swarm optimization (PSO) based on speciation. In each swarm, species are formed adaptively in each iteration according to both particle distance and performance. The design of FCRNNs using the SSPSO for temporal sequence generation and hexapod robot dynamic gait evolution for forward movement is conducted. For the latter, a multiple-FCRNN controller is first designed using a simulated hexapod robot. The designed controller is then successfully applied to a real hexapod robot gait control. The SSPSO is compared with the genetic algorithm and different PSO algorithms to verify its efficiency and effectiveness.
This paper proposes the design of an interval type-2 fuzzy controller (IT2FC) using a rule-based continuous ant colony optimization (RCACO). The design approach is then applied to control a mobile robot for wall follo...
详细信息
ISBN:
(纸本)9781467320566
This paper proposes the design of an interval type-2 fuzzy controller (IT2FC) using a rule-based continuous ant colony optimization (RCACO). The design approach is then applied to control a mobile robot for wall following task. The IT2FC uses interval type-2 fuzzy sets in the antecedent part. The RCACO finds solutions in a real space by using ant path selection and refinement by group-best-ant attraction operations. All of the free-parameters in an IT2FC are optimized using the RCACO to find an accurate control result. In the robot wall-following control application, a new cost function is proposed to accurately measure the wall-following performance. With the proposed cost function and the RCACO-designed IT2FC, neither a priori training data collection nor human expert knowledge is required in designing the IT2FC, which eases the design effort. Simulation results verify the effectiveness of the design approach and the noise resistance ability of the type-2 fuzzy controller.
In this paper, a navigation method is proposed for cooperative load-carrying mobile robots. The behavior mode manager is used efficaciously in the navigation control method to switch between two behavior modes, wall-f...
详细信息
In this paper, a navigation method is proposed for cooperative load-carrying mobile robots. The behavior mode manager is used efficaciously in the navigation control method to switch between two behavior modes, wall-following mode (WFM) and goal-oriented mode (GOM), according to various environmental conditions. Additionally, an interval type-2 neural fuzzy controller based on dynamic group artificial bee colony (DGABC) is proposed in this paper. Reinforcement learning was used to develop the WFM adaptively. First, a single robot is trained to learn the WFM. Then, this control method is implemented for cooperative load-carrying mobile robots. In WFM learning, the proposed DGABC performs better than the original artificial bee colony algorithm and other improved algorithms. Furthermore, the results of cooperative load-carrying navigation control tests demonstrate that the proposed cooperative load-carrying method and the navigation method can enable the robots to carry the task item to the goal and complete the navigation mission efficiently.
暂无评论