In this paper, we develop a novel approximate policy iteration reinforcement learning algorithm with unsupervised feature learning based on manifold regularization. The proposed algorithm can automatically learn data-...
In this paper, we develop a novel approximate policy iteration reinforcement learning algorithm with unsupervised feature learning based on manifold regularization. The proposed algorithm can automatically learn data-driven smooth basis representations for value function approximation, which can preserve the intrinsic geometry of the state space of Markov decision processes. Moreover, it can provide a direct basis extension for new samples in both policy learning and policy control processes. We evaluate the effectiveness and efficiency of the proposed algorithm on the inverted pendulum task. Simulation results show that this algorithm can learn smooth basis representations and excellent control policies.
In recent years, the rapid development of network and E-commerce technologies, promotes the development of human body big data. New technologies, such as 3D scanning and 3D printing will improve our life quality. The ...
详细信息
ISBN:
(纸本)9781509029280
In recent years, the rapid development of network and E-commerce technologies, promotes the development of human body big data. New technologies, such as 3D scanning and 3D printing will improve our life quality. The new socialized manufacturing network composed of IoT, advanced logistics network and 3D printers. Everyone is allowed to have chance to participate in any process of the whole production manufacturing lifecycle by some ways, such as crowdsourcing. Boosts the creation, production and consumption patterns of individuation, real-time transformation and E-commerce, possibly will lead to a new industrial revolution. In this revolutionary change wave, public concerns focus on the human body big data used for social manufacturing of wearable products or personalized medical treatment. Although many scholars have done a lot of research work, the collection of the human body shape big data still faces many challenges. There is no complete, separated theoretical research works in progress, it should be summarized and improved systematically. In this paper, we review that big data for human body shape is gaining momentum. The 3D scanning and 3D modeling of human body shape are summarized and concluded. The main applications of these big data are analyzed.
Structured light calibration is one of the most crucial parts in a visual sensing system of welding robots. And the main aspect of the structured light calibration is the accuracy. Besides, a practical and simplistic ...
详细信息
ISBN:
(纸本)9781467396769
Structured light calibration is one of the most crucial parts in a visual sensing system of welding robots. And the main aspect of the structured light calibration is the accuracy. Besides, a practical and simplistic calibration approach is preferable. In this paper, we propose a simple technique for structured light calibration. The vertical and horizontal lines are added to the planar object to facilitate points detection. The information from the camera calibration is fully used to detect the points on the light stripe. Then parameters of the structured light plane are estimated based on three non-collinear points definition. It could be said that the computation in this study is straight forward. Furthermore, it does not require any additional equipment. Thus, it is a truly simple and practical calibration method. According to the experimental results, the calibration errors are less than 0.2 mm. It shows that our proposed method is acceptable to measurement system of welding robots.
Real time bidding (RTB) is emerged with the rapid development and integration of Internet and big data, and it has become the most important business model for online computational advertising. In RTB-based advertisin...
详细信息
Real time bidding (RTB) is emerged with the rapid development and integration of Internet and big data, and it has become the most important business model for online computational advertising. In RTB-based advertising markets, Demand Side Platforms (DSPs) aim to help the advertisers buy ad impressions matched with their target audiences. Due to the existence of discount rate, the advertising effect may be diminished when displaying the advertisements multiple times to the same target audience. As such, frequency capping is widely considered as a crucial issue faced by most advertisers. In this paper, we mainly consider the frequency capping problems in RTB advertising markets, and establish a two-stage optimization model for advertisers and DSPs. Utilizing the computational experiment approach, we design two experiments to validate our model. The experimental results show that under different discount rates, the optimal frequency caps are different. Moreover, when considering all the discount rates, there exists an optimal frequency cap, at which the expected maximum revenue can be obtained in the long run.
Internet inquiry is playing an increasingly important role as the complement of the traditional medical service system,especially the similar cases *** can not only save the patients' waiting time,but also make us...
详细信息
Internet inquiry is playing an increasingly important role as the complement of the traditional medical service system,especially the similar cases *** can not only save the patients' waiting time,but also make use of the historical resources,for many cases with the same purpose have been solved ***,because of the diversity and non-standard of the patients' descriptions,the inquiry platform cannot find the cases with similar semantic *** traditional retrieval methods require the overlap of two sentences,and this is not suitable with the diversity and non-standard *** this paper,we try to utilize the sentences' semantic representation in a continuous space to understand the cases,and then recommend the similar *** also incorporate it into query likelihood language models,trying to get better *** experimental data are all collected from a real internet inquiry platform,and the results show that our methods significantly outperform the state-of-the-art translation based methods for similar cases recommendation.
This paper describes a novel amphibious robot, which adopts a dual-swing-legs propulsion mechanism, proposing a new locomotion mode. The robot is called FroBot, since its structure and locomotion are similar to frogs....
详细信息
This paper describes a novel amphibious robot, which adopts a dual-swing-legs propulsion mechanism, proposing a new locomotion mode. The robot is called FroBot, since its structure and locomotion are similar to frogs. Our inspiration comes from the frog scooter and breaststroke. Based on its swing leg mechanism, an unusual universal wheel structure is used to generate propulsion on land, while a pair of flexible caudal fins functions like the foot flippers of a frog to generate similar propulsion underwater. On the basis of the prototype design and the dynamic model of the robot, some locomotion control simulations and experiments were conducted for the purpose of adjusting the parameters that affect the propulsion of the robot. Finally, a series of underwater experiments were performed to verify the design feasibility of FroBot and the rationality of the control algorithm.
This paper studies a coordinated transportation problem of a group of unmanned ground vehicles(UGVs). These ground vehicles belong to two categories: master vehicles and slave vehicles. A two-step strategy is proposed...
详细信息
ISBN:
(纸本)9781467374439
This paper studies a coordinated transportation problem of a group of unmanned ground vehicles(UGVs). These ground vehicles belong to two categories: master vehicles and slave vehicles. A two-step strategy is proposed to solve this problem. First, let the master vehicles move along ideal trajectories. Then, let the slave vehicles move into the area surrounded by master vehicles and move together with them. By the two-step strategy, the coordinated transportation problem is divided into a tracking problem and a containment problem. A P In-type tracking protocol and a P In-type containment protocol(P and I stand for Proportion and Integration, respectively;Inimplies that the protocol includes high-order integral terms) are proposed to solve these two problems. It is proved that the coordinated transportation problem can be solved by two proposed protocols with proper parameters if for each follower there exists at least one leader which has a directed path to this follower. Finally, a simulation example is presented to demonstrate the effectiveness of the proposed algorithms.
In recent years, microblog has become one of the most widely used social media for people to exchange ideas and express emotions. As information propagates fast in social network, it's crucial for governments and ...
详细信息
ISBN:
(纸本)9781479998906
In recent years, microblog has become one of the most widely used social media for people to exchange ideas and express emotions. As information propagates fast in social network, it's crucial for governments and public agencies to effectively monitor public sentiment implied in user-generated content. Most previous work of public sentiment analysis takes tweets of different users as a whole without considering the diverse word use of people. Thus, some sentiment words may be neglected in the process of analysis because they are only used by people of specific groups. Inspired by previous psychological findings that personality influences the ways people write and talk, we propose a personality based sentiment classification method. In order to capture more useful but not widely used sentiment words, our approach extracts textual features for people of different personality traits based on the Big Five model. Moreover, we adopt an ensemble learning strategy to utilize both personality related and commonly used textual features. Experimental study shows the effectiveness of our method.
In this paper, we present a novel robotic fish capable of maneuverability and yet with less joints. The maneuverability of the robotic fish is researched on two aspects: straight swimming and performing a turn before ...
详细信息
ISBN:
(纸本)9781479970995
In this paper, we present a novel robotic fish capable of maneuverability and yet with less joints. The maneuverability of the robotic fish is researched on two aspects: straight swimming and performing a turn before which, the mechanical structure, dynamic formula and posture of robotic fish are respectively designed and analyzed. Besides, the CPG-based control and the analysis of variation regulation in the oscillation amplitude of the fish tail are combined to determine the posture of the robotic fish. Next, underwater tests are performed on the robotic fish for collecting the data which provides the information to draw many conclusions.
In this paper, we establish a neural-network-based online learning algorithm to solve the finite horizon linear quadratic regulator (FHLQR) problem for partially unknown continuous-time systems. To solve the FHLQR pro...
详细信息
In this paper, we establish a neural-network-based online learning algorithm to solve the finite horizon linear quadratic regulator (FHLQR) problem for partially unknown continuous-time systems. To solve the FHLQR problem with partially unknown system dynamics, we develop a time-varying Riccati equation. A critic neural network is used to approximate the value function and the online learning algorithm is established using the policy iteration technique to solve the time-varying Riccati equation. An integral policy iteration method and a tuning law are used when the algorithm is implemented without the knowledge of the system drift dynamics. We give a simulation example to show the effectiveness of this algorithm.
暂无评论