Exoskeleton-aided motor physiotherapy raised the need to reduce the bulkiness and mass of the designed devices. It is typically realised based on an engineer’s experience or numerical optimisation. However, these rar...
详细信息
ISBN:
(数字)9798350394276
ISBN:
(纸本)9798350394283
Exoskeleton-aided motor physiotherapy raised the need to reduce the bulkiness and mass of the designed devices. It is typically realised based on an engineer’s experience or numerical optimisation. However, these rarely consider an appropriate selection of drives. The paper presents the methodology of an algorithm for optimal search for driving systems. The method was initially designed for the EXOTIC exoskeleton from Aalborg University but remains universal for structures with different kinematic chains and designs. This paper includes a case study of selecting the drives with gearboxes for the ExoReha exoskeleton from ŁUKASIEWICZ Research Network – Industrial Research Institute for automation and Measurements PIAP. The method selects the best combination from the defined database based on the inverse dynamics computation with the multibody model of the device. The selection was realised for fourteen different cases with different reduction priorities. The outcomes enabled a reduction of mass even by 85% and dimensions by up to 77.5%. Furthermore, it was possible to add two additional drives into passive joints while reducing the total mass of the driving systems by 68.5%. However, the selected drives come from different manufacturers, which can cause problems in the control of the exoskeleton. Moreover, their combination often limits the backdriveability of the systems. Hence, the possible modifications will not be implemented before redesigning the ExoReha exoskeleton into a fully wearable device.
In the context of manufacturing platformization, a growing number of businesses are adopting cloud manufacturing platforms (CMPs) across various scales. To boost competitiveness and network externalities, CMPs offer v...
详细信息
ISBN:
(数字)9798331518493
ISBN:
(纸本)9798331518509
In the context of manufacturing platformization, a growing number of businesses are adopting cloud manufacturing platforms (CMPs) across various scales. To boost competitiveness and network externalities, CMPs offer value-added services to both suppliers and demanders, often necessitating the sharing of proprietary information. It is crucial for CMP operations to encourage information sharing and select service strategies that maximize benefits for all participants within the platform. This paper develops a tripartite evolutionary game theory model that simulates interactions among numerous participants and describes dynamic game processes more comprehensively than traditional game theories. It is used to analyze strategic decisions of cloud manufacturing platforms (CMPs) that utilize proprietary information to provide value-added services. The study analyzes evolutionary stability and conducts numerical simulations based on real-world scenarios. Findings suggest that the platform and suppliers play dominant roles in this tripartite evolution, with their cooperation encouraging demanders to share more information. These insights are valuable for the future management of CMPs.
In this work, we introduce REFORMA, a novel robust reinforcement learning (RL) approach to design controllers for unmanned aerial vehicles (UAVs) robust to unknown disturbances during flights. These disturbances, typi...
详细信息
ISBN:
(数字)9798350384574
ISBN:
(纸本)9798350384581
In this work, we introduce REFORMA, a novel robust reinforcement learning (RL) approach to design controllers for unmanned aerial vehicles (UAVs) robust to unknown disturbances during flights. These disturbances, typically due to wind turbulence, electromagnetic interference, temperature extremes and many other external physical interference, are highly dynamic and difficult to model. REFORMA can perform a real-time online adaptation to these disturbances and generate appropriate velocity actions as countermeasures to stabilize the drone. REFORMA consists of two components: a base policy trained completely in simulation using model-free RL and an adaptation module trained via supervised learning with on-policy datasets. By varying the disturbance strength in an adaptation module, i.e., adopting adaptive adversary, the policy is then able to handle extreme cases when the velocity of the drone is immediately affected by disturbances. Finally, we demonstrate the effectiveness of our method through extensive simulated experiments. To the best of our knowledge, REFORMA is the first robust RL approach that uses adaptive adversaries to tackle uncertain disturbances in drone tasks.
In this article, two environment modeling methods and two methods are used to solve the pursuit-evasion game problem. It separately introduces several methods based on graph and geometry - all with the same goal of re...
详细信息
Anecdotes play a significant role in human communication and understanding. Inference on individual experiences and isolated cases is defined as anecdotal inference here. This study employs complex network methods to ...
详细信息
In the context of tunnel blasting, a significant amount of manual labor is required for borehole explosive filling. Given the challenges posed by harsh blasting conditions, the high precision required for filling oper...
详细信息
ISBN:
(数字)9798350344721
ISBN:
(纸本)9798350344738
In the context of tunnel blasting, a significant amount of manual labor is required for borehole explosive filling. Given the challenges posed by harsh blasting conditions, the high precision required for filling operations, and the vast number of fillings, a specialized explosive-filling robot has been designed. Utilizing the YOLOv5 object detection framework and integrating machine vision technology, an automated tunnel borehole identification method rooted in YOLOv5 has been proposed, aiming to enhance the efficiency and safety of tunnel blasting procedures. Through the collection and annotation of a vast number of tunnel blasting project images, a borehole dataset was established. With the deployment of the YOLOv5 deep learning object detection framework for training, coupled with machine vision and deep learning techniques, this methodology can autonomously identify and locate boreholes in intricate subterranean settings. Experimental findings indicate that this approach exhibits stellar performance even in complex tunnel situations, boasting an accuracy rate exceeding 80% in borehole detection. The system displays exceptional real-time performance, making it viable for practical applications in tunnel blasting operations, thus elevating the efficiency and safety of engineering tasks.
Bio-robots continue to receive attention because of their small size and low power consumption. Unfortunately, it currently faces two major obstacles before practical application. The first is the habituation issue, i...
详细信息
ISBN:
(数字)9798331509644
ISBN:
(纸本)9798331509651
Bio-robots continue to receive attention because of their small size and low power consumption. Unfortunately, it currently faces two major obstacles before practical application. The first is the habituation issue, insects are difficult to be effectively controlled for a long time by electrical stimuli signals. The other one is the lack of model for motion control. In this research, we established a stimuli-response model for cockroach bio-robot based on long time current. A more convenient optic lobe implantation method has been proposed, which has lower attenuation and better stimuli effect. Constant electrical stimuli also significantly increased the number of effective controls for crawling. A cockroach bio-robot stimuli distance response model was established and validated with experiment data. Five parameters were including in this model, namely sex, length, weight, current amplitude and equivalent stiumated-number. This model can predict the movement distance of biological robots well.
The mathematical model of the decision support system under uncertainty conditions is considered. The model is based on the semiotic model of the situation. methods for solving the inverse problem for finding formal s...
详细信息
ISBN:
(数字)9798331532178
ISBN:
(纸本)9798331532185
The mathematical model of the decision support system under uncertainty conditions is considered. The model is based on the semiotic model of the situation. methods for solving the inverse problem for finding formal solutions to achieve the goal are proposed. To interpret the solutions, it is proposed to use vector models of language obtained by training neural networks with a large corpus of text. Examples of interpreting solutions using vector models of language are considered and their capabilities for decision-making are analyzed. A method for assessing the quality of explaining solutions by a deep learning neural network is proposed.
The paper exposes a brief overview of existing models of linear, discrete, and time-invariant systems and then offers a guide to utilizing these models in MATLAB. Embedded functions for modeling in MATLAB and Signal P...
详细信息
ISBN:
(数字)9798350376449
ISBN:
(纸本)9798350376456
The paper exposes a brief overview of existing models of linear, discrete, and time-invariant systems and then offers a guide to utilizing these models in MATLAB. Embedded functions for modeling in MATLAB and Signal Processing Toolbox and examples for transforming from one model to another are given. The “Digital Signal Processing” course for “Information and Communication Technologies” and “Internet and Mobile Communications” bachelor students incorporates these issues into its teaching methods. An attractive way of presenting the material for easier adoption by students is proposed in the paper.
Driving energy consumption plays a major role in the navigation of mobile robots in challenging environments, especially if they are left to operate unattended under limited on-board power. This paper reports on first...
详细信息
ISBN:
(纸本)9781728190778
Driving energy consumption plays a major role in the navigation of mobile robots in challenging environments, especially if they are left to operate unattended under limited on-board power. This paper reports on first results of an energy-aware path planner, which can provide estimates of the driving energy consumption and energy recovery of a robot traversing complex uneven terrains. Energy is estimated over trajectories making use of a self-supervised learning approach, in which the robot autonomously learns how to correlate perceived terrain point clouds to energy consumption and recovery. A novel feature of the method is the use of 1D convolutional neural network to analyse the terrain sequentially in the same temporal order as it would be experienced by the robot when moving. The performance of the proposed approach is assessed in simulation over several digital terrain models collected from real natural scenarios, and is compared with a heuristic inclination-based energy model. We show evidence of the benefit of our method to increase the overall prediction r2 score by 66.8 % and to reduce the driving energy consumption over planned paths by 5.5 %.
暂无评论