Zhiqiang Zheng

Neng Wang, Chenghao Shi, Ruibin Guo et al.

Identifying moving objects is a crucial capability for autonomous navigation, consistent map generation, and future trajectory prediction of objects. In this paper, we propose a novel network that addresses the challenge of segmenting moving objects in 3D LiDAR scans. Our approach not only predicts point-wise moving labels but also detects instance information of main traffic participants. Such a design helps determine which instances are actually moving and which ones are temporarily static in the current scene. Our method exploits a sequence of point clouds as input and quantifies them into 4D voxels. We use 4D sparse convolutions to extract motion features from the 4D voxels and inject them into the current scan. Then, we extract spatio-temporal features from the current scan for instance detection and feature fusion. Finally, we design an upsample fusion module to output point-wise labels by fusing the spatio-temporal features and predicted instance information. We evaluated our approach on the LiDAR-MOS benchmark based on SemanticKITTI and achieved better moving object segmentation performance compared to state-of-the-art methods, demonstrating the effectiveness of our approach in integrating instance information for moving object segmentation. Furthermore, our method shows superior performance on the Apollo dataset with a pre-trained model on SemanticKITTI, indicating that our method generalizes well in different scenes.The code and pre-trained models of our method will be released at https://github.com/nubot-nudt/InsMOS.

Wenbang Deng, Kaihong Huang, Qinghua Yu et al.

Open-world Instance Segmentation (OIS) is a challenging task that aims to accurately segment every object instance appearing in the current observation, regardless of whether these instances have been labeled in the training set. This is important for safety-critical applications such as robust autonomous navigation. In this paper, we present a flexible and effective OIS framework for LiDAR point cloud that can accurately segment both known and unknown instances (i.e., seen and unseen instance categories during training). It first identifies points belonging to known classes and removes the background by leveraging close-set panoptic segmentation networks. Then, we propose a novel ellipsoidal clustering method that is more adapted to the characteristic of LiDAR scans and allows precise segmentation of unknown instances. Furthermore, a diffuse searching method is proposed to handle the common over-segmentation problem presented in the known instances. With the combination of these techniques, we are able to achieve accurate segmentation for both known and unknown instances. We evaluated our method on the SemanticKITTI open-world LiDAR instance segmentation dataset. The experimental results suggest that it outperforms current state-of-the-art methods, especially with a 10.0% improvement in association quality. The source code of our method will be publicly available at https://github.com/nubot-nudt/ElC-OIS.

Zhiwen Zeng, Xiangke Wang, Zhiqiang Zheng

This study develops an original and innovative matrix representation with respect to the information flow for networked multi-agent system. To begin with, the general concepts of the edge Laplacian of digraph are proposed with its algebraic properties. Benefit from this novel graph-theoretic tool, we can build a bridge between the consensus problem and the edge agreement problem; we also show that the edge Laplacian sheds a new light on solving the leaderless consensus problem. Based on the edge agreement framework, the technical challenges caused by unknown but bounded disturbances and inherently nonlinear dynamics can be well handled. In particular, we design an integrated procedure for a new robust consensus protocol that is based on a blend of algebraic graph theory and the newly developed cyclic-small-gain theorem. Besides, to highlight the intricate relationship between the original graph and cyclic-small-gain theorem, the concept of edge-interconnection graph is introduced for the first time. Finally, simulation results are provided to verify the theoretical analysis.

Zhiwen Zeng, Xiangke Wang, Zhiqiang Zheng

This work explores the edge agreement problem of second-order nonlinear multi-agent system under quantized measurements. Under the edge agreement framework, we introduce an important concept about the \emph{essential edge Laplacian} and also obtain a reduced model of the edge agreement dynamics based on the spanning tree subgraph. The quantized edge agreement problem of second-order nonlinear multi-agent system is studied, in which both uniform and logarithmic quantizers are considered. We do not only guarantee the stability of the proposed quantized control law, but also reveal the explicit mathematical connection of the quantized interval and the convergence properties for both uniform and logarithmic quantizers, which has not been addressed before. Particularly, for uniform quantizers, we provide the upper bound of the radius of the agreement neighborhood and indicate that the radius increases with the quantization interval. While for logarithmic quantizers, the agents converge exponentially to the desired agreement equilibrium. In addition, we figure out the relationship of the quantization interval and the convergence speed and also provide the estimates of the convergence rate. Finally, simulation results are given to verify the theoretical analysis.

Michael Yang, Ruijiang Gao, Zhiqiang Zheng

The rapid expansion of Artificial Intelligence is hindered by a fundamental friction in data markets: the value-privacy dilemma, where buyers cannot verify a dataset's utility without inspection, yet inspection may expose the data (Arrow's Information Paradox). We resolve this challenge by introducing the Trustworthy Influence Protocol (TIP), a privacy-preserving framework that enables prospective buyers to quantify the utility of external data without ever decrypting the raw assets. By integrating Homomorphic Encryption with gradient-based influence functions, our approach allows for the precise, blinded scoring of data points against a buyer's specific AI model. To ensure scalability for Large Language Models (LLMs), we employ low-rank gradient projections that reduce computational overhead while maintaining near-perfect fidelity to plaintext baselines, as demonstrated across BERT and GPT-2 architectures. Empirical simulations in healthcare and generative AI domains validate the framework's economic potential: we show that encrypted valuation signals achieve a high correlation with realized clinical utility and reveal a heavy-tailed distribution of data value in pre-training corpora where a minority of texts drive capability while the majority degrades it. These findings challenge prevailing flat-rate compensation models and offer a scalable technical foundation for a meritocratic, secure data economy.

Neng Wang, Ruibin Guo, Chenghao Shi et al.

4D LiDAR semantic segmentation, also referred to as multi-scan semantic segmentation, plays a crucial role in enhancing the environmental understanding capabilities of autonomous vehicles or robots. It classifies the semantic category of each LiDAR measurement point and detects whether it is dynamic, a critical ability for tasks like obstacle avoidance and autonomous navigation. Existing approaches often rely on computationally heavy 4D convolutions or recursive networks, which result in poor real-time performance, making them unsuitable for online robotics and autonomous driving applications. In this paper, we introduce SegNet4D, a novel real-time 4D semantic segmentation network offering both efficiency and strong semantic understanding. SegNet4D addresses 4D segmentation as two tasks: single-scan semantic segmentation and moving object segmentation, each tackled by a separate network head. Both results are combined in a motion-semantic fusion module to achieve comprehensive 4D segmentation. Additionally, instance information is extracted from the current scan and exploited for instance-wise segmentation consistency. Our approach surpasses state-of-the-art in both multi-scan semantic segmentation and moving object segmentation while offering greater efficiency, enabling real-time operation. Besides, its effectiveness and efficiency have also been validated on a real-world unmanned ground platform. Our code will be released at https://github.com/nubot-nudt/SegNet4D.

Xiangke Wang, Xun Li, Yirui Cong et al.

In this paper, the recent developments on distributed coordination control, especially the consensus and formation control, are summarized with the graph theory playing a central role, in order to present a cohesive overview of the multi-agent distributed coordination control, together with brief reviews of some closely related issues including rendezvous/alignment, swarming/flocking and containment control.In terms of the consensus problem, the recent results on consensus for the agents with different dynamics from first-order, second-order to high-order linear and nonlinear dynamics, under different communication conditions, such as cases with/without switching communication topology and varying time-delays, are reviewed, in which the algebraic graph theory is very useful in the protocol designs, stability proofs and converging analysis. In terms of the formation control problem, after reviewing the results of the algebraic graph theory employed in the formation control, we mainly pay attention to the developments of the rigid and persistent graphs. With the notions of rigidity and persistence, the formation transformation, splitting and reconstruction can be completed, and consequently the range-based formation control laws are designed with the least required information in order to maintain a formation rigid/persistent. Afterwards, the recent results on rendezvous/alignment, swarming/flocking and containment control, which are very closely related to consensus and formation control, are briefly introduced, in order to present an integrated view of the graph theory used in the coordination control problem. Finally, towards the practical applications, some directions possibly deserving investigation in coordination control are raised as well.