Machine learning is a critical component of artificial intelligence and computer science that uses data and algorithms to emulate the way that humans learn and predict. Reinforcement learning, one of the many forms of...
详细信息
ISBN:
(数字)9798350352399
ISBN:
(纸本)9798350352405
Machine learning is a critical component of artificial intelligence and computer science that uses data and algorithms to emulate the way that humans learn and predict. Reinforcement learning, one of the many forms of machine learning, trains an agent through trial and error, with successful outcomes being rewarded and unsuccessful outcomes being penalized. The implementation of three reinforcement learning algorithms, Qlearning, Deep Q-Learning, and Double Deep Q-Learning, was tested using a series of ROS (Robot Operating System) packages in the Gazebo simulation environment. The Python openai_ros package and Gym libraries were used to input a robot into a configurable environment and test out the performance of a specific reinforcement learning algorithm. The agent’s action space was discretized into three specific actions, move forward, turn left, or turn right, that the robot could take. The reward or punishment was given after each step based on if the current action moved the robot towards the goal state or away from it. For each algorithm, the agent was first pre-trained on an obstacle free environment for 200 episodes and then was placed in an environment with two box-shaped obstacles to avoid. The algorithm/neural network parameters from the pre-training environment were loaded prior to the agent being tested in the new environment. The goal state at each episode was randomly generated and the robot’s performance was evaluated using the cumulative reward achieved per episode and the number of times it reached the goal.
Visual simultaneous localization and mapping (vSLAM), one of the most important applications in autonomous vehicles and robots to estimate the position and pose using inexpensive visual sensors, suffers from error acc...
详细信息
Visual simultaneous localization and mapping (vSLAM), one of the most important applications in autonomous vehicles and robots to estimate the position and pose using inexpensive visual sensors, suffers from error accumulation for long-term navigation without loop closure detection. Recently, deep neural networks (DNNs) are leveraged to achieve high accuracy for loop closure detection, however the execution time is much slower than those employing handcrafted visual features. In this paper, a parallel loop searching and verifying method for loop closure detection with both high accuracy and high speed, which combines two parallel tasks using handcrafted and DNN features, respectively, is proposed. A fast loop searching is proposed to link the bag-of-words features and histogram for higher accuracy, and it splits the images into multiple grids for high parallelism;meanwhile, a DNN feature extractor is utilized for further verification. A loop state control method based on a finite state machine to control these tasks is designed, wherein the loop closure detection is described as a context-related procedure. The framework is implemented on a real machine, and the top-2 best accuracy and fastest execution time of 80-543 frames per second (min: 1.84ms, and max: 12.45ms) are achieved on several public benchmarks compared with some existing algorithms.
Greenhouse vertical rack hydroponic systems offer a sustainable and efficient solution for meeting the increasing global food demand. This paper introduces an IoT-integrated automated system designed to perform labor ...
详细信息
This study discuss the development of an intelligent autonomous agricultural robot, designed to detect and treat diseases affecting herbaceous medicinal plants using artificial intelligence (AI) techniques. Herbaceous...
详细信息
ISBN:
(数字)9798350344134
ISBN:
(纸本)9798350344141
This study discuss the development of an intelligent autonomous agricultural robot, designed to detect and treat diseases affecting herbaceous medicinal plants using artificial intelligence (AI) techniques. Herbaceous plants are particularly prone to diseases and require regular monitoring due to their rapid growth and short flowering periods. Leveraging technologies such as Internet of Things (IoT) and artificial intelligence, farmers can now efficiently identify and address plant diseases at early stage. In this work, we present an intelligent autonomous robot capable of proactively identifying and treating herbaceous diseases as a preventive measure. We developed a robust algorithm to control the robot's movements within predefined areas inside plant greenhouses. Through the use of Pixy camera, the robot can detect plant yellowing, prompting it to halt and direct a nozzle towards the identified plant, initiating a preventive spraying process at predetermined times and positions. Furthermore, the robot is equipped with a companion computer responsible for disease identification using deep learning algorithms. This identification capability enables farmers to make immediate decisions and initiate disease treatments promptly. The entire system was developed, implemented, and initially tested outside our labs. The testing results corroborate the system's practicality and demonstrate that the prototype may be simply implemented to provide an added-value to the farmers of herbaceous medicinal plants.
Greenhouse vertical rack hydroponic systems offer a sustainable and efficient solution for meeting the increasing global food demand. This paper introduces an IoT-integrated automated system designed to perform labor ...
详细信息
ISBN:
(数字)9798331521950
ISBN:
(纸本)9798331521967
Greenhouse vertical rack hydroponic systems offer a sustainable and efficient solution for meeting the increasing global food demand. This paper introduces an IoT-integrated automated system designed to perform labor intensive and repetitive tasks in hydroponic farming. The proposed system integrates a robotic platform for transplanting and inspecting plants, as well as an intelligent controller to control and monitor greenhouse conditions and nutrient solution parameters. To enhance performance and accessibility, the system is integrated with an IoT platform, which includes a user-friendly web interface, enabling remote monitoring and control. Key features such as computervisiontechniques and advanced control algorithms are implemented to maximize operational efficiency. Experimental results validate its ability to reduce labor, improve productivity, and ensure consistent crop quality. This solution highlights the potential for scalable and sustainable advancements in modern agriculture.
This research addresses the challenges faced by mobile robots in efficiently navigating complex environments. A novel approach is proposed, leveraging deep learning techniques, and introducing the Neo model. The metho...
详细信息
This paper presents a simulation-based approach to robotic object recognition and rearrangement using the KUKA KR5 HW-2 manipulator. The research focuses on developing and implementing advanced algorithms for object d...
详细信息
ISBN:
(数字)9798350378115
ISBN:
(纸本)9798350378122
This paper presents a simulation-based approach to robotic object recognition and rearrangement using the KUKA KR5 HW-2 manipulator. The research focuses on developing and implementing advanced algorithms for object detection, classification, and manipulation within a virtual environment. The KUKA KR5 HW-2, a versatile industrial robot, is modelled in the simulation to perform complex pick and place operations. It emphasizes the integration of computervisiontechniques with the robot’s kinematic model to enhance its ability to recognize various object geometries and efficiently plan rearrangement tasks. The simulation environment allows for rapid prototyping and testing of different scenarios, enabling the optimization of trajectory planning and grip strategies. Our results demonstrate significant improvements in the manipulator’s adaptability to diverse object types and arrangement patterns. This work contributes to the advancement of flexible automation in manufacturing and logistics, offering insights into the potential of simulation-based development for robotic manipulation tasks.
Although deep learning has achieved satisfactory performance in computervision, a large volume of images is required. However, collecting images is often expensive and challenging. Many image augmentation algorithms ...
详细信息
The integration of computervisiontechniques for the accomplishment of autonomous interaction tasks represents a challenging research direction in the context of aerial robotics. In this paper, we consider the proble...
详细信息
ISBN:
(纸本)9781728162126
The integration of computervisiontechniques for the accomplishment of autonomous interaction tasks represents a challenging research direction in the context of aerial robotics. In this paper, we consider the problem of contact-based inspection of a textured target of unknown geometry and pose. Exploiting state of the art techniques in computer graphics, tuned and improved for the task at hand, we designed a framework for the projection of a desired trajectory for the robot end-effector on a generically-shaped surface to be inspected. Combining these results with previous work on energy-based interaction control, we are laying the basis of what we call vision-based impedance control paradigm. To demonstrate the feasibility and the effectiveness of our methodology, we present the results of both realistic ROS/Gazebo simulations and preliminary experiments with a fully-actuated hexarotor interacting with heterogeneous curved surfaces whose geometric description is not available a priori, provided that enough visual features on the target are naturally or artificially available to allow the integration of localization and mapping algorithms.
Collaborative robotics, in conjunction with artificial intelligence (AI), offers a contemporary and effective paradigm for secure machine-human interactions. This synergy branches out into a variety of industries, inc...
详细信息
ISBN:
(数字)9798350360165
ISBN:
(纸本)9798350360172
Collaborative robotics, in conjunction with artificial intelligence (AI), offers a contemporary and effective paradigm for secure machine-human interactions. This synergy branches out into a variety of industries, including education and entertainment, in addition to industrial uses. Two intriguing board games that offer a platform for examining the potential of cooperative robotic systems are chess and checkers. An intelligent and cooperative robotic system designed for use in Italian checkers games is described in this context by the study being presented. To record the game state, the gadget employs a camera. To physically move pieces across the board, a pick-and-place mechanism is used. An algorithm is used to automatically choose the optimal moves that comply with the rules. The system respects the kinematic restrictions of the manipulator while optimizing minimum-time trajectories live for every manipulation, guaranteeing a smooth and dynamic gaming experience. An experimental validation employing a seven-degree-of-freedom Franka Emika arm verifies the effectiveness of the proposed approach in real-world settings.
暂无评论