The fusion filtering problem is investigated for a class of time-varying nonlinear singular systems with packet disorders (PDs). The key idea is to transfer the original singular systems with multiple sensors to full-order augmented nonsingular systems by utilizing the matrix transformation method. The phenomenon of PDs accompanied with random transmission delays (RTDs) is considered, which exists in the channel from sensor to filter. A set of independent and identically distributed random variables obeying known probability distribution are introduced to model the RTDs. A centralized fusion filter is designed, which employs the rounding function of the mathematical expectation of the RTDs. Furthermore, the nonlinear function is linearized by utilizing the method of Taylor series expansion. Then, the desired upper bounds of the estimation error covariance are guaranteed and then locally minimized through appropriately designing the corresponding filter gains. Finally, a numerical example with comparisons is carried out to verify the feasibility of the proposed fusion filtering method.

Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large shape variations within a category and the discrepancies between the target object and the shape prior. To address these challenges, we introduce a novel architecture for category-level object pose refinement. Our approach integrates an HS-layer and learnable affine transformations, which aims to enhance the extraction and alignment of geometric information. Additionally, we introduce a cross-cloud transformation mechanism that efficiently merges diverse data sources. Finally, we push the limits of our model by incorporating the shape prior information for translation and size error prediction. We conducted extensive experiments to demonstrate the effectiveness of the proposed framework. Through extensive quantitative experiments, we demonstrate significant improvement over the baseline method by a large margin across all metrics.

This paper is concerned with the fusion filtering problem for time-varying singular systems with random transmission delays (RTDs) and packet dropout (PD) compensations. Here, the phenomena of RTDs and PDs are both characterized by Bernoulli distributed random variables with different probabilities. Generally, the current sensor measurement and one-step delayed sensor measurement can be received by filter. When the sensor measurement is lost, based on the strategy of PD compensations, the one-step predictor of current sensor measurement is used as compensator. Then, the new augmented systems with stochastic parameter matrices and correlated noises are introduced based on the measurement compensation model. Utilizing the innovation analysis approach, the local filters (LFs) dependent on probabilities and corresponding estimation error covariance matrices are derived for augmented systems. Moreover, the matrix-weighted distributed fusion filter (DFF) is designed for original singular systems on the basis of the state transformation. Compared with the LFs, it is not difficult to see that the presented DFF has better precision. In the end, some comparison simulation experiments are carried out to verify the effectiveness of the proposed fusion filtering algorithm.

In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation. 3D graph convolution (3D-GC) based methods have been widely used to extract local geometric features, but they have limitations for complex shaped objects and are sensitive to noise. Moreover, the scale and translation invariant properties of 3D-GC restrict the perception of an object's size and translation information. In this paper, we propose a simple network structure, the HS-layer, which extends 3D-GC to extract hybrid scope latent features from point cloud data for category-level object pose estimation tasks. The proposed HS-layer: 1) is able to perceive local-global geometric structure and global information, 2) is robust to noise, and 3) can encode size and translation information. Our experiments show that the simple replacement of the 3D-GC layer with the proposed HS-layer on the baseline method (GPV-Pose) achieves a significant improvement, with the performance increased by 14.5% on 5°2cm metric and 10.3% on IoU 75 . Our method outperforms the state-of-the-art methods by a large margin (8.3% on 5°2cm, 6.9% on IoU 75 ) on REAL275 dataset and runs in real-time (50 FPS) 1 1 Codeisavailable: https://github.com/Lynne-Zheng-Linfang/HS-Pose.

We study six-dimensional (6D) perceptive peg-in-hole problem for practical connector insertion task in this paper. To enable the manipulator system to handle different types of pegs in complex environment, we develop a perceptive robotic assembly system that utilizes an in-hand RGB-D camera for peg-in-hole with multiple types of pegs. The proposed framework addresses the critical hole detection and pose estimation problem through combining the learning-based detection with model-based pose estimation strategies. By exploiting the structure of the peg-in-hole task, we consider a rectangle-shape based characterization for modeling the candidate socket. Such a characterization allows us to design simple learning-based methods to detect and estimate the 6D pose of the target socket that balances between processing speed and accuracy. To validate our method, we test the performance of the proposed perceptive peg-in-hole solution using a KUKA iiwa7 robotic arm to accomplish the socket insertion task with two types of practical sockets (RJ45/HDMI). Without the need of additional search, our method achieves an acceptable success rate in the connector insertion tasks. The results confirm the reliability of our method and show that our method is suitable for real world application.

In robotic insertion tasks where the uncertainty exceeds the allowable tolerance, a good search strategy is essential for successful insertion and significantly influences efficiency. The commonly used blind search method is time-consuming and does not exploit the rich contact information. In this paper, we propose a novel search strategy that actively utilizes the information contained in the contact configuration and shows high efficiency. In particular, we formulate this problem as a Partially Observable Markov Decision Process (POMDP) with carefully designed primitives based on an in-depth analysis of the contact configuration's static stability. From the formulated POMDP, we can derive a novel search strategy. Thanks to its simplicity, this search strategy can be incorporated into a Finite-State-Machine (FSM) controller. The behaviors of the FSM controller are realized through a low-level Cartesian Impedance Controller. Our method is based purely on the robot's proprioceptive sensing and does not need visual or tactile sensors. To evaluate the effectiveness of our proposed strategy and control framework, we conduct extensive comparison experiments in simulation, where we compare our method with the baseline approach. The results demonstrate that our proposed method achieves a higher success rate with a shorter search time and search trajectory length compared to the baseline method. Additionally, we show that our method is robust to various initial displacement errors.

In this paper, the problem of optimized distributed fusion filtering is considered for a class of multi-sensor singular systems in the presence of fading measurements and stochastic nonlinearity. By utilizing the standard singular value decomposition, the multi-sensor stochastic singular systems are simplified to two reduced-order nonsingular subsystems (RONSs). The local filters (LFs) with corresponding error covariance matrices are proposed for RONSs via the innovation analysis approach. Then, on the basis of the matrix-weighted fusion estimation algorithm, the distributed fusion filters (DFFs) are designed for RONSs with multiple sensors in the linear minimum variance sense. Moreover, the DFFs are obtained by utilizing the state transformation for original singular systems. It can be observed that the DFFs have better accuracy in contrast with the LFs. Finally, an illustrate example is put forward to verify the feasibility of the proposed fusion filtering scheme.

This paper studies a novel encirclement guaranteed cooperative pursuit problem involving $N$ pursuers and a single evader in an unbounded two-dimensional game domain. Throughout the game, the pursuers are required to maintain encirclement of the evader, i.e., the evader should always stay inside the convex hull generated by all the pursuers, in addition to achieving the classical capture condition. To tackle this challenging cooperative pursuit problem, a robust model predictive control (RMPC) based formulation framework is first introduced, which simultaneously accounts for the encirclement and capture requirements under the assumption that the evader's action is unavailable to all pursuers. Despite the reformulation, the resulting RMPC problem involves a bilinear constraint due to the encirclement requirement. To further handle such a bilinear constraint, a novel encirclement guaranteed partitioning scheme is devised that simplifies the original bilinear RMPC problem to a number of linear tube MPC (TMPC) problems solvable in a decentralized manner. Simulation experiments demonstrate the effectiveness of the proposed solution framework. Furthermore, comparisons with existing approaches show that the explicit consideration of the encirclement condition significantly improves the chance of successful capture of the evader in various scenarios.