arXiv subjects

Zhenzhong Cao

Publications and source records attributed to Zhenzhong Cao.

7 recordsLinked to original sources

arXiv2025

HF-DGF: Hybrid Feedback Guided Directed Grey-box Fuzzing

Directed Grey-box Fuzzing (DGF) has emerged as a widely adopted technique for crash reproduction and patch testing, leveraging its capability to precisely navigate toward target locations and exploit vulnerabilities. However, current DGF tools are constrained by insufficient runtime feedback, limiting their efficiency in reaching targets and exploring state spaces. This study presents HF-DGF, a novel directed grey-box fuzzing framework. Its seed scheduling is guided by a hybrid feedback mechanism integrating control-flow distance, value-flow influence score, and slice coverage. To enable precise control-flow distance feedback, we propose a backward-stepping algorithm to calculate basic block-level seed distances on a virtual inter-procedural control-flow graph (ICFG). For effective state space exploration, we introduce value-flow influence and a corresponding metric, the value-flow influence score. Additionally, to mitigate runtime overhead from hybrid feedback, we adopt a novel selective instrumentation strategy. Evaluations on 41 real-world vulnerabilities show HF-DGF outperforms existing tools: it achieves crash reproduction 5.05 times faster than AFL, 5.79 times faster than AFLGo, 73.75 times faster than WindRanger, 2.56 times faster than DAFL, and 8.45 times faster than Beacon on average. Notably, when all fuzzers triggered crashes, HF-DGF exhibited the lowest code coverage, demonstrating superior directionality and efficiency. It also surpasses AFLGo, WindRanger, DAFL, and Beacon in static analysis efficiency.

cs.SE↗

arXiv2024

Scene Modeling of Autonomous Vehicles Avoiding Stationary and Moving Vehicles on Narrow Roads

Navigating narrow roads with oncoming vehicles is a significant challenge that has garnered considerable public interest. These scenarios often involve sections that cannot accommodate two moving vehicles simultaneously due to the presence of stationary vehicles or limited road width. Autonomous vehicles must therefore profoundly comprehend their surroundings to identify passable areas and execute sophisticated maneuvers. To address this issue, this paper presents a comprehensive model for such an intricate scenario. The primary contribution is the principle of road width occupancy minimization, which models the narrow road problem and identifies candidate meeting gaps. Additionally, the concept of homology classes is introduced to help initialize and optimize candidate trajectories, while evaluation strategies are developed to select the optimal gap and most efficient trajectory. Qualitative and quantitative simulations demonstrate that the proposed approach, SM-NR, achieves high scene pass rates, efficient movement, and robust decisions. Experiments conducted in tiny gap scenarios and conflict scenarios reveal that the autonomous vehicle can robustly select meeting gaps and trajectories, compromising flexibly for safety while advancing bravely for efficiency.

cs.RO↗

arXiv2024

RGBDS-SLAM: A RGB-D Semantic Dense SLAM Based on 3D Multi Level Pyramid Gaussian Splatting

High-quality reconstruction is crucial for dense SLAM. Recent popular approaches utilize 3D Gaussian Splatting (3D GS) techniques for RGB, depth, and semantic reconstruction of scenes. However, these methods often overlook issues of detail and consistency in different parts of the scene. To address this, we propose RGBDS-SLAM, a RGB-D semantic dense SLAM system based on 3D multi-level pyramid gaussian splatting, which enables high-quality dense reconstruction of scene RGB, depth, and semantics.In this system, we introduce a 3D multi-level pyramid gaussian splatting method that restores scene details by extracting multi-level image pyramids for gaussian splatting training, ensuring consistency in RGB, depth, and semantic reconstructions. Additionally, we design a tightly-coupled multi-features reconstruction optimization mechanism, allowing the reconstruction accuracy of RGB, depth, and semantic maps to mutually enhance each other during the rendering optimization process. Extensive quantitative, qualitative, and ablation experiments on the Replica and ScanNet public datasets demonstrate that our proposed method outperforms current state-of-the-art methods. The open-source code will be available at: https://github.com/zhenzhongcao/RGBDS-SLAM.

cs.CV↗

arXiv2023

SemanticTopoLoop: Semantic Loop Closure With 3D Topological Graph Based on Quadric-Level Object Map

Loop closure, as one of the crucial components in SLAM, plays an essential role in correcting the accumulated errors. Traditional appearance-based methods, such as bag-of-words models, are often limited by local 2D features and the volume of training data, making them less versatile and robust in real-world scenarios, leading to missed detections or false positives detections in loop closure. To address these issues, we first propose a object-level data association method based on multi-level verification, which can associate 2D semantic features of current frame with 3D objects landmarks of map. Next, taking advantage of these association relations, we introduce a semantic loop closure method based on quadric-level object map topology, which represents scenes through the topological graph of objects and achieves accurate loop closure at a wide field of view by comparing differences in the topological graphs. Finally, we integrate these two methods into a complete object-aware SLAM system. Qualitative experiments and ablation studies demonstrate the effectiveness and robustness of the proposed object-level data association algorithm. Quantitative experiments show that our semantic loop closure method outperforms existing state-of-the-art methods in terms of precision, recall and localization accuracy metrics.

cs.CV↗

arXiv2022

CFP-SLAM: A Real-time Visual SLAM Based on Coarse-to-Fine Probability in Dynamic Environments

The dynamic factors in the environment will lead to the decline of camera localization accuracy due to the violation of the static environment assumption of SLAM algorithm. Recently, some related works generally use the combination of semantic constraints and geometric constraints to deal with dynamic objects, but problems can still be raised, such as poor real-time performance, easy to treat people as rigid bodies, and poor performance in low dynamic scenes. In this paper, a dynamic scene-oriented visual SLAM algorithm based on object detection and coarse-to-fine static probability named CFP-SLAM is proposed. The algorithm combines semantic constraints and geometric constraints to calculate the static probability of objects, keypoints and map points, and takes them as weights to participate in camera pose estimation. Extensive evaluations show that our approach can achieve almost the best results in high dynamic and low dynamic scenarios compared to the state-of-the-art dynamic SLAM methods, and shows quite high real-time ability.

cs.RO↗

arXiv2021

Accurate and Robust Object-oriented SLAM with 3D Quadric Landmark Construction in Outdoor Environment

Object-oriented SLAM is a popular technology in autonomous driving and robotics. In this paper, we propose a stereo visual SLAM with a robust quadric landmark representation method. The system consists of four components, including deep learning detection, object-oriented data association, dual quadric landmark initialization and object-based pose optimization. State-of-the-art quadric-based SLAM algorithms always face observation related problems and are sensitive to observation noise, which limits their application in outdoor scenes. To solve this problem, we propose a quadric initialization method based on the decoupling of the quadric parameters method, which improves the robustness to observation noise. The sufficient object data association algorithm and object-oriented optimization with multiple cues enables a highly accurate object pose estimation that is robust to local observations. Experimental results show that the proposed system is more robust to observation noise and significantly outperforms current state-of-the-art methods in outdoor environments. In addition, the proposed system demonstrates real-time performance.

cs.RO↗

arXiv2020

Deep learning for magnitude prediction in earthquake early warning

Fast and accurate magnitude prediction is the key to the success of earthquake early warning. We have proposed a new approach based on deep learning for P-wave magnitude prediction (EEWNet), which takes time series data as input instead of feature parameters. The architecture of EEWNet is adaptively adjusted according to the length of the input, thus eliminates the need of complicated tuning of hyperparameters for deep learning. Only the unfiltered accelerograms of vertical components are used. EEWNet is trained on a moderate number of data set (10,000s of records), but it achieves excellent results in magnitude prediction compared with approaches using parameters τlog, τc and Pd.

physics.geo-ph↗