3D pose transfer over unorganized point clouds is a challenging generation task,which transfers a source’s pose to a target shape and keeps the target’s *** deep models have learned deformations and used the target...
详细信息
3D pose transfer over unorganized point clouds is a challenging generation task,which transfers a source’s pose to a target shape and keeps the target’s *** deep models have learned deformations and used the target’s identity as a style to modulate the combined features of two shapes or the aligned vertices of the source ***,all operations in these models are point-wise and independent and ignore the geometric information on the surface and structure of the input *** disadvantage severely limits the generation and generalization *** this study,we propose a geometry-aware method based on a novel transformer autoencoder to solve this *** efficient self-attention mechanism,that is,cross-covariance attention,was utilized across our framework to perceive the correlations between points at different ***,the transformer encoder extracts the target shape’s local geometry details for identity attributes and the source shape’s global geometry structure for pose *** transformer decoder efficiently learns deformations and recovers identity properties by fusing and decoding the extracted features in a geometry attentional manner,which does not require corresponding information or modulation *** experiments demonstrated that the geometry-aware method achieved state-of-the-art performance in a 3D pose transfer *** implementation code and data are available at https://***/SEULSH/Geometry-Aware-3D-Pose-Transfer-Using-Transfor mer-Autoencoder.
This article studies the effective traffic signal control problem of multiple intersections in a city-level traffic system.A novel regional multi-agent cooperative reinforcement learning algorithm called RegionSTLight...
详细信息
This article studies the effective traffic signal control problem of multiple intersections in a city-level traffic system.A novel regional multi-agent cooperative reinforcement learning algorithm called RegionSTLight is proposed to improve the traffic *** a regional multi-agent Q-learning framework is proposed,which can equivalently decompose the global Q value of the traffic system into the local values of several regions Based on the framework and the idea of human-machine cooperation,a dynamic zoning method is designed to divide the traffic network into several strong-coupled regions according to realtime traffic flow *** order to achieve better cooperation inside each region,a lightweight spatio-temporal fusion feature extraction network is *** experiments in synthetic real-world and city-level scenarios show that the proposed RegionS TLight converges more quickly,is more stable,and obtains better asymptotic performance compared to state-of-theart models.
Video-based person re-identification (Re-ID) aims at associating the video sequences of the identical person across multiple cameras. The ubiquitous appearance misalignment poses a major obstacle for video person Re-I...
详细信息
Leighton Chajnantor Telescope(LCT), i.e., the former Caltech Submillimeter Observatory telescope, will be refurbished at the new site in Chajnantor Plateau, Chile in 2023. The environment of LCT will change significan...
详细信息
Leighton Chajnantor Telescope(LCT), i.e., the former Caltech Submillimeter Observatory telescope, will be refurbished at the new site in Chajnantor Plateau, Chile in 2023. The environment of LCT will change significantly after its relocation, and the telescope will be exposed to large wind disturbances directly because its enclosure will be completely open during observation. The wind disturbance is expected to be a challenge for LCT's pointing control since the existing control method cannot reject this disturbance very well. Therefore, it is very necessary to develop a new pointing control method with good capability of disturbance rejection. In this research, a disturbance observer—based composite position controller(DOB-CPC) is designed, in which an H∞feedback controller is employed to compress the disturbance, and a feedforward linear quadratic regulator is employed to compensate the disturbance precisely based on the estimated disturbance signal. Moreover, a controller switching policy is adopted, which applies the proportional controller to the transient process to achieve a quick response and applies the DOB-CPC to the steady state to achieve a small position error. Numerical experiments are conducted to verify the good performance of the proposed pointing controller(i.e., DOB-CPC) for rejecting the disturbance acting on LCT.
In Off-Policy reinforcement learning (RL), the experience imbalance problem can affect learning performance. The experience imbalance problem refers to the phenomenon that the experiences obtained by the agent during ...
详细信息
This paper investigates the problem of traffic signal control in large-scale road networks. A deep reinforcement learning model based on graph meta-learning using local subgraphs is proposed to control the traffic sig...
This paper investigates the problem of traffic signal control in large-scale road networks. A deep reinforcement learning model based on graph meta-learning using local subgraphs is proposed to control the traffic signal. The entire traffic network is represented as a graph by defining traffic lights as nodes and treating connections between intersections as edges. A graph neural network is used to enhance cooperation and communications between agents since information about neighbors is aggregated. To overcome the challenges in large-scale road networks, the proposed model employs a graph neural network on local subgraphs to reduce the difficulty of training in large-scale road networks. The model trained in small-scale traffic networks is transferred to a large-scale traffic network. Agent knowledge acquired from local subgraphs during the training of a small-scale road network confers advantages to the training of large-scale road networks under the resemblance between the structures of local subgraphs in small-and large-scale road networks. Furthermore, meta-learning is used to facilitate the model's rapid adaptability to unseen large-scale road networks. The advantage of the double Q-learning network is taken to reduce overestimation. In experiments, real-world road networks and synthetic road networks comprising more than 1000 intersections are given to evaluate the effectiveness of the proposed model.
This paper discusses the data-driven design of linear quadratic regulators,i.e.,to obtain the regulators directly from experimental data without using the models of *** particular,we aim to improve an existing design ...
详细信息
This paper discusses the data-driven design of linear quadratic regulators,i.e.,to obtain the regulators directly from experimental data without using the models of *** particular,we aim to improve an existing design method by reducing the amount of the required experimental *** the data amount leads to the cost reduction of experiments and computation for the data-driven *** present a simplified version of the existing method,where parameters yielding the gain of the regulator are estimated from only part of the data required in the existing *** then show that the data amount required in the presented method is less than half of that in the existing method under certain *** addition,assuming the presence of measurement noise,we analyze the relations between the expectations and variances of the estimated parameters and the *** a result,it is shown that using a larger amount of the experimental data might mitigate the effects of the noise on the estimated *** results are verified by numerical examples.
Rail surface defect inspection is an essential task for the railway system. However, due to the similarity of the background and defect foreground pixels, uneven textures, irregular shapes and multiple scales of the e...
详细信息
Joint face super-resolution and frontalization of non-frontal low-resolution faces is of significant importance for many face analysis applications. However, at the same time, it is a challenging task. In this paper, ...
详细信息
Dear Editor,This letter is concerned with prescribed-time Nash equilibrium(PTNE)seeking problem in a pursuit-evasion game(PEG)involving agents with second-order *** order to achieve the prior-given and user-defined co...
详细信息
Dear Editor,This letter is concerned with prescribed-time Nash equilibrium(PTNE)seeking problem in a pursuit-evasion game(PEG)involving agents with second-order *** order to achieve the prior-given and user-defined convergence time for the PEG,a PTNE seeking algorithm has been developed to facilitate collaboration among multiple pursuers for capturing the evader without the need for any global ***,it is theoretically proved that the prescribedtime convergence of the designed algorithm for achieving Nash equilibrium of ***,the effectiveness of the PTNE method was validated by numerical simulation results.A PEG consists of two groups of agents:evaders and *** pursuers aim to capture the evaders through cooperative efforts,while the evaders strive to evade *** is a classic noncooperative *** has attracted plenty of attention due to its wide application scenarios,such as smart grids[1],formation control[2],[3],and spacecraft rendezvous[4].It is noteworthy that most previous research on seeking the Nash equilibrium of the game,where no agent has an incentive to change its actions,has focused on asymptotic and exponential convergence[5]-[7].
暂无评论