Mengmeng Fu

Mengmeng Fu

Auto-generated profile, based on publicly available information

Mengmeng Fu

Department of Neurosurgery, Shenzhen University General Hospital, Shenzhen, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 August 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
DYDongyu Yan
Dongyu Yan
JLJianheng Liu
Jianheng Liu
FQFengyu Quan
Fengyu Quan
HCHaoyao Chen
Haoyao Chen
MFMengmeng Fu
Mengmeng Fu
Actively planning sensor views during object reconstruction is crucial for autonomous mobile robots. An effective method should be able to strike a balance between accuracy and efficiency. In this paper, we propose a seamless integration of the emerging implicit representation with the active reconstruction task. We build an implicit occupancy field as our geometry proxy. While training, the prior object bounding box is utilized as auxiliary information to generate clean and detailed reconstructions. To evaluate view uncertainty, we employ a sampling-based approach that directly extracts entropy from the reconstructed occupancy probability field as our measure of view information gain. This eliminates the need for additional uncertainty maps or learning. Unlike previous methods that compare view uncertainty within a finite set of candidates, we aim to find the next-best-view (NBV) on a continuous manifold. Leveraging the differentiability of the implicit representation, the NBV can be optimized directly by maximizing the view uncertainty using gradient descent. It significantly enhances the method's adaptability to different scenarios. Simulation and real-world experiments demonstrate that our approach effectively improves reconstruction accuracy and efficiency of view planning in active reconstruction tasks. The proposed system is open-sourced at https://github.com/HITSZ-NRSL/ActiveImplicitRecon.git .

26 April 2024 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
RHRui He
Rui He
HCHaoyao Chen
Haoyao Chen
MFMengmeng Fu
Mengmeng Fu
Six-DoF grasp detection has attracted increasing attention due to its high flexibility in manipulation tasks. Recent learning-based methods typically use point sampling or filtering to extract a small subset of scene points for grasp pose computation. However, the sampling method disregards the fact that each scene point contributes differently to the grasp, while the filtering method nearly destroys the geometrical structure of the scene. Concurrently, indirectly learning point features by inputting point coordinates to the network is insufficient for detecting grasp poses since this task heavily depends on the geometrical structure of the local point clouds. In order to solve the above-mentioned problems, we design a novel interest point selection algorithm in the grasp scene, and a novel explicit geometrical feature extraction algorithm for local point clouds in the six-DoF grasp pose detection task. We include the basic grasp points, nearby object points and background points as interest points in calculating the grasp poses. Moreover, we add a module that predicts grasp collision within the network to eliminate the time-consuming collision detection in postprocessing. The proposed network is trained and evaluated on the GraspNet1Billion dataset, and achieves state-of-the-art performance. We also conduct an ablation study to validate the proposed algorithms and the network. Furthermore, we successfully implement our network on a UR5e robotic arm to demonstrate its practical applicability in both single-object and multiobject grasp scenarios.

3 January 2026
Verified
Preprint
Open access
MFMengmeng Fu
Mengmeng Fu
JXJing Xia
Jing Xia
XZXingxing Zhang
Xingxing Zhang
BSBaoxiang Shang
Baoxiang Shang
LWLan Wang
Lan Wang
YZYuhu Zhang
Yuhu Zhang
Cross-modal cognitive control mechanisms, particularly how top-down attention modulates modality-specific processing, remain insufficiently investigated. This study aimed to address this gap by investigating the neural and behavioral correlates of cross-modal conflict resolution. A 2×2×2 hybird-desigen cross-modal flanker paradigm using fMRI was conducted on 39 healthy adults. Participants attended to visual (Attend_Visual) or auditory (Attend_Auditory) modalities while responding to congruent/incongruent visual (V) and audio (A) stimuli. Behavioral data showed significant conflict effects: longer reaction times and lower accuracy for incongruent versus congruent conditions, with distinct interaction patterns across attentional modalities. Neuroimaging results revealed that Attend_Visual engaged the anterior cingulate cortex, insula, precentral/postcentral gyri, and occipitotemporal areas, while Attend_Auditory recruited focal lateral prefrontal regions. PPI analysis demonstrated enhanced connectivity between the left middle frontal gyrus and visual cortices (precuneus, cuneus) during AV conflict. These findings confirm a dual mechanism (supramodal conflict monitoring and modality-specific control) and highlight that top-down attention flexibly shapes cross-modal cognitive control, advancing understanding of multisensory interference resolution.