Genetic Algorithm Based Deep Learning Parameters Tuning for Robot Object Recognition and Grasping
نویسندگان
چکیده
This paper concerns with the problem of deep learning parameters tuning using a genetic algorithm (GA) in order to improve the performance of deep learning (DL) method. We present a GA based DL method for robot object recognition and grasping. GA is used to optimize the DL parameters in learning procedure in term of the fitness function that is good enough. After finishing the evolution process, we receive the optimal number of DL parameters. To evaluate the performance of our method, we consider the object recognition and robot grasping tasks. Experimental results show that our method is efficient for robot object recognition and grasping. Keywords—Deep learning, genetic algorithm, object recognition, robot grasping.
منابع مشابه
A Q-learning Based Continuous Tuning of Fuzzy Wall Tracking
A simple easy to implement algorithm is proposed to address wall tracking task of an autonomous robot. The robot should navigate in unknown environments, find the nearest wall, and track it solely based on locally sensed data. The proposed method benefits from coupling fuzzy logic and Q-learning to meet requirements of autonomous navigations. Fuzzy if-then rules provide a reliable decision maki...
متن کاملParameters Identification of an Experimental Vision-based Target Tracker Robot Using Genetic Algorithm
In this paper, the uncertain dynamic parameters of an experimental target tracker robot are identified through the application of genetic algorithm. The considered serial robot is a two-degree-of-freedom dynamic system with two revolute joints in which damping coefficients and inertia terms are uncertain. First, dynamic equations governing the robot system are extracted and then, simulated nume...
متن کاملManipulation Control of a Flexible Space Free Flying Robot Using Fuzzy Tuning Approach
Cooperative object manipulation control of rigid-flexible multi-body systems in space is studied in this paper. During such tasks, flexible members like solar panels may get vibrated that in turn may lead to some oscillatory disturbing forces on other subsystems, and consequently produces error in the motion of the end-effectors of the cooperative manipulating arms. Therefore, to design and dev...
متن کاملهمکاری رباتها در جابجایی جسم نامعین توسط کنترلر امپدانسچندگانه
Parameter identification techniques are particularly attractive to determine the inertial parameters of robot manipulators and manipulated payloads. These parameters are particularly needed in implementation of a model-based controller for robot manipulators. In this paper, the inertial parameters of a manipulated rigid-body object have been estimated. The Newton-Euler equations will be employe...
متن کاملGrasping of Unknown Objects using Deep Convolutional Neural Networks based on Depth Images
We present a data-driven, bottom-up, deep learning approach to robotic grasping of unknown objects using Deep Convolutional Neural Networks (DCNNs). The approach uses depth images of the scene as its sole input for synthesis of a single-grasp solution during execution, adequately portraying the robot’s visual perception during exploration of a scene. The training input consists of precomputed h...
متن کامل