检索结果-内蒙古大学图书馆

IEEE International Conference on Intelligence and safety for Robotics (IsR)

作者： R. Yamaguchi Y. Aiyama Master's Program in Intelligent Interaction Technologies University of Tsukuba Tsukuba Japan Faculty of Engineering Information and Systems University of Tsukuba Tsukuba Japan

ISBN: (纸本)9781665438629;9781665411486

In this paper, we propose a method of compensating for absolute position and installation errors of a robot in the robot's workspace when an industrial robot stops working and needs to be replaced in a factory, for example. The proposed method uses multiple markers placed in the workspace and a camera to measure the robot, and estimates the position and orientation of the camera and the robot's link parameters in the workspace. In order to evaluate the proposed method, we compensate the position error of the robot by simulation. As a result, in the case where there is no measurement error of the camera, the hand position error at the work point is less than 0.5[mm]. In the case of the camera measurement error, the results varied depending on the way the measurement error occurred, and some errors were within 0.1 [mm] and some were close to 1 [mm].

关键词： Measurement errors service robots simulation Robot vision systems Measurement uncertainty Position measurement Cameras

来源：评论

学校读者我要写书评

暂无评论

Design of Wheel Mechanism of Inspection Mobile Robot Using Electro Permanent Magnet

Design of Wheel Mechanism of Inspection Mobile Robot Using E...

引用

sICE Annual Conference

作者： Li Xiaozhu Yamaguchi Tomoyuki Department of Master’s and Doctoral Programs in Intelligent and Mechanical Interaction Systems University of Tsukuba Ibaraki Japan Institute of Engineering Information and Systems University of Tsukuba Ibaraki Japan

In recent years, civil engineering and construction structures such as bridges and tunnels are aging, and periodic inspections are becoming necessary. Therefore, robotics is expected to inspect bridges more efficiently and safely, and robots for inspection of civil engineering and construction structures are widely researched. In this study, we propose a combination of a propeller mechanism and an EPM (Electro Permanent Magnet) wheel to allow the robot to move on bridges of different materials. On concrete and other parts, the robot is driven by a propeller. When it detects that the bridge material is iron, the propeller is turned off and moved by the magnetic force of the EPM wheel.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EEG analysis for surprise in VR traffic environment 15

EEG analysis for surprise in VR traffic environment

引用

15th Asia-Pacific Workshop on Mixed and Augmented Reality, APMAR 2023

作者： Tayama, Yuto Kameda, Yoshinari Master’s program in Intelligent and Mechanical Interacion Systems University of tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan Center for Computational Science University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan

On the assessment of user experience in VR traffic environments, a method to evaluate the mental state of subjects is required to measure the effects of dynamic events in the traffic environments. EEG is one of the promising devices for measuring the subject mental status. We propose to analyze EEG responses against traffic scenes, including traffic accidents, for the evaluation of the surprise feelings of subjects in VR traffic environments by a set of HMD and an EEG device. Throughout the experiments, we examined whether EEG can evaluate subjects’ emotional states in response to the events in VR space. Three traffic scenes and 10 subjects were prepared for the experiment. The EEG analysis was made on beta frequency band power related to surprise response. © 2023 Copyright for this paper by its authors.

关键词： Accidents

来源：评论

学校读者我要写书评

暂无评论

Ability evaluation of basketball players on responding to situations in VR simulator 16

Ability evaluation of basketball players on responding to si...

引用

16th Asia-Pacific Workshop on Mixed and Augmented Reality, APMAR 2024

作者： Tan, Zichen Nakazawa, shota Yoshida, Kenji Kameda, Yoshinari Master's Program in Intelligent and Mechanical and Interaction Systems University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba3058573 Japan Institute of Health and Sport Sciences University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8574 Japan Center for Computational Sciences University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8577 Japan

A basketball player's ability to respond to situations is an important factor that greatly influences the outcome of a game. In this study, we propose a method to evaluate the situational ability of basketball players using a VR simulator. The VR simulator replicates a 2-on-2 game scenario, and the system captures the players' line of sight and movements. The Head-Mounted Display (HMD) records the gaze, while the movement is tracked by capturing images of the player and estimating the player's skeletal structure using OpenPose. We then propose and analyze an index, derived from the collected data, that represents the player's situational responsiveness. From the collected data, we propose and analyze indicators of situational responsiveness. The indicators include gazing objects, number of head turns, body movement, movement trend, and average reaction time. In the experiment, we showed that the proposed indexes can be used to objectively evaluate the players' ability to respond to situations by analyzing them. This study was conducted to evaluate the complexity of a basketball player using a VR simulator. This research introduces and validates an innovative method for evaluating basketball players' ability to respond to complex situations using a VR simulator. We believe that this research has the potential to make a significant contribution to the field of sports analysis. © 2024 Copyright for this paper by its authors.

关键词： Helmet mounted displays

来源：评论

学校读者我要写书评

暂无评论

Explainable Reinforcement Learning via Causal Model Considering Agent's Intention

Explainable Reinforcement Learning via Causal Model Consider...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： seongIn Kim Takeshi shibuya Doctor's Program in Intelligent and Mechanical Interaction Systems University of Tsukuba Ibaraki Japan Faculty of Engineering Information and Systems University of Tsukuba Ibaraki Japan

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Explaining agent's decision can offer valuable insights for designers and end-users. One proposed method for explaining an agent's decision-making involves representing a causal relation between state components and action as a causal model and providing explanations for the decisions made using causal model. However, traditional causal model often faces structural limitation, restricting the range of representable control problems. Additionally, providing accurate explanation becomes challenging in control problems with various types of rewards because agent's intention of an action is unknown. In this study, we introduce a causal model capable of representing a broader range of control problems and a method to provide accurate explanations in control problems with various types of reward structures. Through redefining the relationships between nodes in the causal model, we have enabled a broader representation of control problems. Also, by incorporating agent's intention into the explanation, we have achieved to provide a more precise explanation. To validate the effectiveness of our proposed method, we conducted experiments using OpenAI's LunarLander environment. Using a proposed causal model, we defined the causal model of LunarLander, which could not be represented by conventional causal models. Furthermore, by incorporating the intentions of an agent into the explanation, novel interpretations previously inaccessible have become feasible.

关键词： Accuracy Decision making Reinforcement learning Faces Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Action Robust Reinforcement Learning with Highly Expressive Policy

Action Robust Reinforcement Learning with Highly Expressive ...

引用

IEEE International Conference on systems, Man and Cybernetics

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In traditional reinforcement learning, there can be a degradation in the control performance of the policy when the environmental parameters differ between the training and application phase. The policy that minimizes this degradation is referred to as a robust policy. A framework called Noisy action Robust Markov Decision Process (NR-MDP) was proposed for training robust policies, and the Action Robust Deep Determin-istic Policy Gradient (AR-DDPG) algorithm was introduced as a method for solving NR-MDP. The optimal policy in NR-MDP includes policies following various probability distributions, whereas AR-DDPG is restricted to deterministic policies. We propose a new robust reinforcement learning method called Action Robust Q-Learning (AR-QL) that enables the training of optimal policies in NR-MDP by leveraging various sampling techniques to extend the representational capacity of policies, targeting an improvement in policy robustness. To validate this, we confirmed that AR-QL can acquire the optimal policy for a simple NR-MDP problem, for which AR-DDPG fails to obtain the optimal policy. Furthermore, we confirmed that the robust performance of policy trained by AR-QL in the OpenAI's InvertedPendulum environment surpasses that of policy trained by AR-DDPG.

关键词： Training Degradation Q-learning Markov decision processes Toy manufacturing industry Probability distribution Robustness Computational efficiency Noise measurement Cybernetics

来源：评论

学校读者我要写书评

暂无评论

A Human-Flow Analysis Based on PCA:A Case study on Population Data Near Railway

A Human-Flow Analysis Based on PCA:A Case Study on Populatio...

引用

Robotics, Automation and Artificial Intelligence (RAAI), IEEE International Conference on

作者： seongIn Kim Takeshi shibuya shingo Toride Yasunori Endo Master’s Programs in Intelligent and Mechanical Interaction Systems University of Tsukuba Tsukuba Japan Faculty of Engineering Information and Systems University of Tsukuba Tsukuba Japan Disaster Information Research Division National Research Institute for Earth Science and Disaster Prevention Tsukuba Japan

The damage caused by natural disasters and accidents is increasing every year. To reduce such damage from spreading, it is important to detect an accident promptly. However, current sensing systems are difficult to use because they have narrow coverage and are specialized in few detectable accidents. In this paper, we propose a method to detect disasters and accidents by calculating the degree of an anomaly in human flow by treating a common human flow as a single large sensor. Human flow can be assumed to have typical patterns in people’s daily life, such as going to work and leaving work. Developing an anomaly detection method of human flow can lead to the discovery of any hidden causes such as accidents and disasters. In this paper, we study a method that aims to detect anomalies in human flow, considering the operational status of railways as an example. We confirm that our method can detect the actual suspension of operations.

关键词： Automation sociology Robot sensing systems Rail transportation sensors statistics Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

MAGNETOHYDRODYNAMIC sUBMARINE PROPULsION systems

引用

NAVAL ENGINEERs JOURNAL 1991年第3期103卷 141-157页

作者： sWALLOM, DW sADOVNIK, I GIBBs, Js GUROL, H NGUYEN, LV VANDENBERGH, HH Daniel W. Swallomis the director of military power systems at Avco Research Laboratory Inc. a subsidiary of Textron Inc. in Everett Mass. Dr. Swallom received his B.S. M.S. and Ph.D. degrees in mechanical engineering from the University of Iowa Iowa City Iowa in 1969 1970 and 1972 respectively. He has authored numerous papers in the areas of power propulsion and plasma physics and currently is a member of the Aerospace Power Systems Technical Committee of the AIAA. Dr. Swallom has directed various programs for the development of advanced power generation systems lightweight power conditioning systems and advanced propulsion systems for marine applications. His previous experience includes work with Odin International Corporation Maxwell Laboratories Inc. Argonne National Laboratory and the Air Force Aero Propulsion Laboratory. Currently Dr. Swallom is directing the technical efforts to apply magnetohydrodynamic principles to a variety of propulsion and power applications for various marine vehicles and power system requirements respectively. Isaac Sadovnikis a principal research engineer in the Energy Technology Office at Avco Research Laboratory Inc. a subsidiary of Textron Inc. He received his B.S. in engineering (1974) B.S. in physics (1975) M.S. in aeronautics and astronautics (1976) and Ph.D. in physics of fluids (1981) at the Massachusetts Institute of Technology. Dr. Sadovnik has been involved in research work funded by DARPA concerning the use of magnetohydrodynamics for underwater propulsion. He has built theoretical models that predict the hydrodynamic behavior of seawater flow through magnetohydrodynamic ducts and their interaction with the rest of the vehicle (thrust and drag produced). In addition Dr. Sadovnik has been involved in research investigations geared toward the NASP program concerning the use of magnetohydrodynamic combustion-driven accelerator channels. Prior to joining Avco Dr. Sadovnik was a research assistant at MIT where he conducted experimental and

Magnetohydrodynamic propulsion systems for submarines offer several significant advantages over conventional propeller propulsion systems. These advantages include the potential for greater stealth characteristics, increased maneuverability, enhanced survivability, elimination of cavitation limits, greater payload capability, and the addition of a significant emergency propulsion system. These advantages can be obtained with a magnetohydrodynamic propulsion system that is neutrally bouyant and can operate with the existing submarine propulsion system power plant. A thorough investigation of magnetohydrodynamic propulsion systems for submarine applications has been completed. During the investigation, a number of geometric configurations were examined. Each of these configurations and mounting concepts was optimized for maximum performance for a generic attack class submarine. The optimization considered each thruster individually by determining the optimum operating characteristics for each one and accepting only those thrusters that result in a neutrally buoyant propulsion system. The results of this detailed optimization study show that the segmented, annular thruster is the concept with the highest performance levels and greatest efficiency and offers the greatest potential for a practical magnetohydrodynamic propulsion system for attack class submarines. The optimization study results were used to develop a specific point design for a segmented, annular magnetohydrodynamic thruster for an attack class submarine. The design point case has shown that this thruster may be able to provide the necessary thrust to propel an attack class submarine at the required velocity with the potential for a substantial acoustic signature reduction within the constraints of the existing submarine power plant and the maintenance of neutral buoyancy. This innovative magnetohydrodynamic propulsion system offers an approach for submarine propulsion that can be an important contributio

关键词： ship Propulsion

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：