One crucial problem for a humanoid service robot is to be able to communicate with humans naturally. This study focuses on this issue and develops a social interactive system for a humanoid robot to interact with huma...
详细信息
In the research of wheel-legged robots, trajectory tracking control is the inevitable requirement. In this paper, a trajectory tracking control scheme based on model predictive control for the parallel mechanism of si...
详细信息
In the research of wheel-legged robots, trajectory tracking control is the inevitable requirement. In this paper, a trajectory tracking control scheme based on model predictive control for the parallel mechanism of six wheel-legged robot is proposed. A dynamic model was employed to reduce the amount of calculations for planning and control. In the model, the dynamic nonlinear constraints such as the tire slip rate and the roll caused by the lateral acceleration need to be considered. Finally, the control method is verified in the dynamic model. The simulation results show that all dynamic constraints can be maintained within a given interval and the control method has obvious tracking effect improvement.
In this paper, a novel online Q-Iearning approach is proposed to solve the Infinite Horizon Linear Quadratic Regulator (IHLQR) problem for continuous-time (CT) linear time-invariant (LMI) systems. The proposed Q-Iearn...
详细信息
In this paper, a novel online Q-Iearning approach is proposed to solve the Infinite Horizon Linear Quadratic Regulator (IHLQR) problem for continuous-time (CT) linear time-invariant (LMI) systems. The proposed Q-Iearning algorithm employing off-policy reinforcement learning (RL) technology improves the exploration ability of Q-Iearning to the state space. During the learning process, the Q-Iearning algorithm can be implemented just using the data sets which just contains the information of the behavior policy and the corresponding system state, thus is data- driven. Moreover, the data sets can be used repeatedly, which is computationally efficient. A mild condition on probing noise is established to ensure the converge of the proposed Q-Iearning algorithm. Simulation results demonstrate the effectiveness of the developed algorithm.
In this paper, we consider the plan recognition problem in the real-time strategy game. A probabilistic plan recognition algorithm is proposed to predict the future goals and identify the temporal logic tasks of the n...
详细信息
In this paper, we consider the plan recognition problem in the real-time strategy game. A probabilistic plan recognition algorithm is proposed to predict the future goals and identify the temporal logic tasks of the non-cooperative agent based on the observations. In order to model the temporal logic tasks, the plan library is composed of the Finite Transition System and Nondeterministic B ¨uchi Automation. Specially, we provide a unified framework to combine the plan recognition and the planning, and propose the probability calculation algorithm to calculate the posterior probability distribution of the goals and tasks. Finally, we verify the effectiveness of the proposed algorithm by the compared simulations.
In this paper, we propose a distributed adaptive approach for tracking problem without using leader's velocity information, where agents are modeled by Euler-Lagrange equations. It is assumed that only a small fra...
详细信息
In this paper, we propose a distributed adaptive approach for tracking problem without using leader's velocity information, where agents are modeled by Euler-Lagrange equations. It is assumed that only a small fraction of agents within the leader's communication range are informed about the position of the leader. Without using the leader's velocity information, a connectivity-preserving adaptive controller is proposed to achieve tracking control on Lagrangian systems with the leader of constant velocity. Moreover, position and velocity consensus can be achieved asymptotically with the proposed control strategy. Numerical simulations are further provided to illustrate the theoretical results.
This paper investigates the distributed tracking control problem for multiple Lagrangian systems under a general directed graph where only a portion of the agents have access to the desired time-varying trajectory. To...
详细信息
This paper investigates the distributed tracking control problem for multiple Lagrangian systems under a general directed graph where only a portion of the agents have access to the desired time-varying trajectory. To overcome the problem that only positions are measured, a observer is designed to estimate the velocity for each follower. By employing the estimated states, the distributed observer-based controller is proposed using only position measurements. Furthermore, the condition for the distributed tracking problem on the directed graph is derived, such that the tracking errors and observer errors semi-globally converge to zero. Finally, simulation examples are provided to show the effectiveness of the proposed control algorithms.
In this paper,the adaptive robust control（ARC） algorithm is proposed for tracking control of the electric cylinder *** to the analysis of the working principle of the electric cylinder servo system,the model of the ...
详细信息
In this paper,the adaptive robust control（ARC） algorithm is proposed for tracking control of the electric cylinder *** to the analysis of the working principle of the electric cylinder servo system,the model of the system is established on the modified Lugre friction model,and single observer is designed for calculating friction as *** the ARC controller and adaptive law are designed for on-line parameters estimation,frictional compensation and the suppression external *** the Lyapunov approach,the stability of this system can be obtained in this *** simulation result shows that ARC can suppresses external disturbances effectively and realize real-time online parameter estimation.
The virtual-to-real paradigm,i.e.,training models on virtual data and then applying them to solve real-world problems,has attracted more and more attention from various domains by successfully alleviating the data sho...
详细信息
The virtual-to-real paradigm,i.e.,training models on virtual data and then applying them to solve real-world problems,has attracted more and more attention from various domains by successfully alleviating the data shortage problem in machine *** summarize the advances in recent years,this survey comprehensively reviews the literature,from the viewport of parallel ***,an extended parallel learning framework is proposed to cover main domains including computer vision,natural language processing,robotics,and autonomous ***,a multi-dimensional taxonomy is designed to organize the literature in a hierarchical ***,the related virtual-toreal works are analyzed and compared according to the three principles of parallel learning known as description,prediction,and prescription,which cover the methods for constructing virtual worlds,generating labeled data,domain transferring,model training and testing,as well as optimizing the strategies to guide the task-oriented data generator for better learning *** issues remained in virtual-to-real are ***,the future research directions from the viewpoint of parallel learning are suggested.
Graph neural networks(GNNs) have shown great popularity and achieved promising performance on various graph-based tasks in the past years. However, there is little work that explores the information fusion mechanism, ...
详细信息
Graph neural networks(GNNs) have shown great popularity and achieved promising performance on various graph-based tasks in the past years. However, there is little work that explores the information fusion mechanism, which plays an import role in GNNs. Besides, datasets in the real world often have noises, which make the information fusion difficult. In this paper, we give an information-theoretic explanation. Specifically, we focus on how the information from topological structures and node features fuses and how different information contributes to the downstream task. Furthermore, we propose a general framework named M-GCN to express the fusion process in GNNs. Graph embeddings and feature graph are introduced to extract the information from topological structure and node features separately in M-GCN. Extensive experiments are conducted on several benchmark datasets and experimental results show that our proposed models are more robust and outperform state-of-the-art methods.
In the field of radar data processing, track interruption seriously affects target tracking, track fusion, and other *** existing track segment association algorithms have low correlation accuracy in dense distributed...
In the field of radar data processing, track interruption seriously affects target tracking, track fusion, and other *** existing track segment association algorithms have low correlation accuracy in dense distributed or long-time interruption situations. To this purpose, a dense multi-target track segment association(DMTTSA) algorithm is proposed. Firstly, two identical networks based on the multi-head probability sparse(ProbSparse) self-attention are used to capture the long-term dependencies of the tracks. Then, the bidirectional quadruplet hard sample loss(BiQuaHard loss) is constructed to make the tracks belonging to the same targets closer and the tracks belonging to the different targets farther. Finally, DMTTSA takes the closest track pairs in the feature space as the associated tracks and divides the unassociated tracks into the birth and dead tracks in chronological order. Some comparative experiments are carried out to show the anti-noise performance of the DMTTSA, as well as the effectiveness of solving the problem of dense multi-target track interruption.
暂无评论