We propose a self-managing services architecture for automated manufacturing systems to enable sustainable manufacturing operations. The architecture utilises both software agents and IEC 61499 function blocks to real...
详细信息
We propose a self-managing services architecture for automated manufacturing systems to enable sustainable manufacturing operations. The architecture utilises both software agents and IEC 61499 function blocks to realise manufacturing systems that quickly respond to change while maintaining stable system operation and efficient use of available resources. To explore the system's ability to adapt to disturbances, a stochastic agent-based simulation of the automated manufacturing system with random equipment failures was developed. The results of the simulation demonstrate that the proposed self-managing services architecture is capable of rapidly reconfiguring part routings in order to reduce work in progress and maintain stable system operation. Copyright (C) 2024 The Authors.
Accurately estimating the six-degree-of-freedom pose of objects is essential for intelligentrobotics. Although significant progress has been made in this area, most studies fail to account for specific hardware limit...
详细信息
ISBN:
(纸本)9798350354416;9798350354409
Accurately estimating the six-degree-of-freedom pose of objects is essential for intelligentrobotics. Although significant progress has been made in this area, most studies fail to account for specific hardware limitations for model deployment, which remains a major challenge for resource-constrained scenarios. To address this issue, we propose Lite-HRPE, a lightweight RGB-based pose estimation method, which leverages a multi-branch parallel structure to extract spatial and semantic information of key points for pose estimation. Additionally, Lite-HRPE adopts the G-block and G-neck modular structure and streamlines the original feature extraction network to realize a compact network structure. This allows Lite-HRPE to strike a balance between pose estimation accuracy, parameter count, computational load, and runtime speed. Our evaluation on public datasets shows that Lite-HRPE achieves a 95.7% accuracy with only 10.8% of the number of parameters and 11.8% of the FLOPs compared to Hybridpose.
The evaluation of a robot's mechanical properties is crucial for optimizing its posture and trajectory during tasks. Traditional indexes and methods for evaluating robot mechanical properties often fall short in p...
详细信息
ISBN:
(纸本)9798350370010;9798350370003
The evaluation of a robot's mechanical properties is crucial for optimizing its posture and trajectory during tasks. Traditional indexes and methods for evaluating robot mechanical properties often fall short in providing accurate and quantitative evaluations based on diverse task requirements. In this paper, we introduce a method for evaluating the mechanical performance of serial robots that takes into account specific task requirements. The Ur5e robot was employed to validate the accuracy of the evaluation results. To showcase the potential usability of the proposed mechanical performance evaluation method, we evaluated the feasibility of employing the Ur5e robot for ultrasound scanning tasks.
Cooperative adaptive cruise control (CACC) allows connected vehicles in a platoon to maintain smaller headway, which has the potential to enhance driving safety and traffic efficiency. However, various network uncerta...
详细信息
With the progress of science and technology and the improvement of living standards, the role of electricity in human life is becoming increasingly important, and a large number of nonlinear devices will also be conne...
详细信息
ISBN:
(纸本)9798350344738;9798350344721
With the progress of science and technology and the improvement of living standards, the role of electricity in human life is becoming increasingly important, and a large number of nonlinear devices will also be connected to the power grid, which will cause harmonic pollution and seriously affect other electrical equipment in the power grid. To address this issue, active power filters have been proposed as one of the main methods for controlling harmonic pollution. However, active power filters can generate current and voltage surges during the startup process, which can pose a threat to the stability of the power system. Therefore, this article focuses on the starting process of parallel active power filters under three-phase three-wire system, and finally proposes a starting process based on auto-disturbance rejection control. Finally, simulation verifies that this control method is superior to PI control.
Bipedal robots with two legs are capable of traversing various terrains like level ground and staircases. Applying Reinforcement Learning (RL) based control can realize stable climbing stairs of bipedal robots. Prior ...
详细信息
ISBN:
(纸本)9798350385731;9798350385724
Bipedal robots with two legs are capable of traversing various terrains like level ground and staircases. Applying Reinforcement Learning (RL) based control can realize stable climbing stairs of bipedal robots. Prior knowledge of robots such as surrounding terrain information may improve the performance of climbing stairs. However, the impacts of prior knowledge on locomotion of bipedal robots across various terrains have not been systematically studied. In this work, we analyzed the effects of the amount of prior knowledge about terrain in front of the robot with RL-based control. Simulation results showed that introducing prior knowledge about terrain to bipedal robots can increase the maximum allowable ground height variation, realize smooth transition from level-ground walking to stair climbing, and improve disturbance rejection and energy efficiency. Prior knowledge is a trade-off between environmental information acquisition and computational complexity reduction. We find that there exists an optimal amount of prior knowledge for disturbance rejection and energy efficiency of stair climbing.
Large Language Models (LLMs) have been widely utilized to perform complex robotic tasks. However, handling external disturbances during tasks is still an open challenge. This paper proposes a novel method to achieve r...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Large Language Models (LLMs) have been widely utilized to perform complex robotic tasks. However, handling external disturbances during tasks is still an open challenge. This paper proposes a novel method to achieve robotic adaptive tasks based on LLMs and Behavior Trees (BTs). It utilizes ChatGPT to reason the descriptive steps of tasks. In order to enable ChatGPT to understand the environment, semantic maps are constructed by an object recognition algorithm. Then, we design a Parser module based on Bidirectional Encoder Representations from Transformers (BERT) to parse these steps into initial BTs. Subsequently, a BTs Update algorithm is proposed to expand the initial BTs dynamically to control robots to perform adaptive tasks. Different from other LLM-based methods for complex robotic tasks, our method outputs variable BTs that can add and execute new actions according to environmental changes, which is robust to external disturbances. Our method is validated with simulation in different practical scenarios.
In the past few decades, multi-legged robots have been widely used in agriculture, construction, rescue and other fields for their excellent flexibility and good adaptability. However, for most multi-legged robots, du...
详细信息
As a crucial process in autonomous driving systems, path tracking control determines the safety and ride comfort of intelligent vehicles. However, the response delay of the steering actuator is commonly not considered...
详细信息
The accurate representation of object shape, pose, and tool-object contact states is of paramount importance in complex robot tool manipulation tasks. These facets are comprehensively modeled using tactile sensors, wh...
详细信息
ISBN:
(纸本)9798350385731;9798350385724
The accurate representation of object shape, pose, and tool-object contact states is of paramount importance in complex robot tool manipulation tasks. These facets are comprehensively modeled using tactile sensors, which provide a wealth of information. The tactile-based manipulation control framework presented here consists of three core components: the explorer, modeler, and controller. In the context of contact state modeling, we collect the moving trend between the grasped object and the visual-tactile sensor, which could be used for estimating the contact state. Addressing the challenge of precise object modeling, including both shape and pose, we employ the visual-tactile joint exploration and geometric modeling approach introduced in this study. The controller leverages the modeled object's shape and pose while estimating contact states through the contact state classifier. In scenarios where contact states exhibit uncertainty, the robot autonomously engages in exploration, returning to its established contact mode to successfully conclude the manipulation. Peg-hole-insertion experiments featuring pegs and holes of varying shapes have been conducted to empirically validate the efficacy of the presented manipulation control framework.
暂无评论