Gaoming Chen

Gaoming Chen

Auto-generated profile, based on publicly available information

Gaoming Chen

School of Mechanical Engineering, State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
22 April 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
KSKun Song
Kun Song
WLWenhang Liu
Wenhang Liu
GCGaoming Chen
Gaoming Chen
XXXiang Xu
Xiang Xu
ZXZhenhua Xiong
Zhenhua Xiong
Topological maps are favorable for their small storage compared to geometric maps. However, they are limited in relocalization and path planning capabilities. To solve the problem, a feature-based hybrid topological map (FHT-Map) is proposed along with a real-time map construction algorithm based on robot exploration. Specifically, the FHT-Map utilizes both RGB cameras and LiDAR information and consists of two types of nodes: main node and support node. Main nodes store visual information compressed by convolutional neural network and local laser scan data to enhance subsequent relocalization capability. Support nodes retain a minimal amount of data to ensure storage efficiency while facilitating path planning. After map construction through robot exploration, the FHT-Map can be used by other robots for relocalization and path planning. Simulation results demonstrate that the proposed FHT-Map can effectively improve relocalization and path planning capability compared with other topological maps. Moreover, simulations of the hybrid architecture are implemented to show the necessity of two types of nodes.

13 September 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
KSKun Song
Kun Song
GCGaoming Chen
Gaoming Chen
WLWenhang Liu
Wenhang Liu
ZXZhenhua Xiong
Zhenhua Xiong
Rendezvous aims at gathering all robots at a specific location, which is an important collaborative behavior for multi-robot systems. However, in an unknown environment, it is challenging to achieve rendezvous. Previous researches mainly focus on special scenarios where communication is not allowed and each robot executes a random searching strategy, which is highly time-consuming, especially in large-scale environments. In this letter, we focus on rendezvous in unknown environments where communication is available. We divide this task into two steps: rendezvous based environment exploration with relative pose (RP) estimation and rendezvous point selection. A new strategy called partitioned and incomplete exploration for rendezvous (PIER) is proposed to efficiently explore the unknown environment, where lightweight topological maps are constructed and shared among robots for RP estimation with very few communications. Then, a rendezvous point selection algorithm based on the merged topological map is proposed for efficient rendezvous for multi-robot systems. The effectiveness of the proposed methods is validated in both simulations and real-world experiments.

28 May 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
GCGaoming Chen
Gaoming Chen
KSKun Song
Kun Song
XXXiang Xu
Xiang Xu
WLWenhang Liu
Wenhang Liu
ZXZhenhua Xiong
Zhenhua Xiong
Mutual localization serves as the foundation for collaborative perception in multi-robot systems. Effectively utilizing limited onboard sensors for mutual localization between marker-less robots is worthwhile. However, due to inadequate consideration of large scale variations of the robot and localization refinement, previous work has shown limited accuracy when robots are equipped only with RGB cameras. To enhance the precision of localization, this letter proposes a novel rendezvous-based hierarchical architecture for mutual localization (RHAML). Firstly, to learn multi-scale features, anisotropic convolutions are introduced into the network, yielding initial localization results. Then, the iterative refinement module is employed to adjust the poses. Finally, the pose graph is conducted to globally optimize localization results, which takes into account multi-frame observations. Therefore, a flexible architecture is provided that allows for the selection of appropriate modules based on requirements. Simulations demonstrate that RHAML effectively addresses the problem of multi-robot mutual localization, achieving translation errors below 2 cm and rotation errors below 0.5 degrees when robots exhibit 5 m of depth variation. Moreover, its practical utility is validated by applying it to map fusion when multi-robots explore unknown environments.

16 January 2026 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
GCGaoming Chen
Gaoming Chen
KSKun Song
Kun Song
WLWenhang Liu
Wenhang Liu
WMWenyao Ma
Wenyao Ma
ZXZhenhua Xiong
Zhenhua Xiong
Relative Localization (RelLoc) is crucial for consistent decision-making in multi-robot systems. To achieve efficient RelLoc, two key problems must be solved: how to evaluate the RelLoc accuracy, and how to coordinate the robot swarm to enhance it when it does not meets the stopping criterion. Existing research mainly focuses on passively optimizing relative poses, without explicitly evaluating the uncertainty in this process or efficiently improving RelLoc accuracy in an active manner. In this paper, we propose a novel Dynamic Localization Graph (DLG) to evaluate, monitor, and actively improve inter-robot RelLoc accuracy. To address the first problem, we propose the Metric of Relative Localization Accuracy (MRLA) based on the pose covariance without requiring prior knowledge of relative poses. Specifically, graduated non-convexity factor graph optimization and uncertainty propagation is applied to calculate the transformation and update the pose covariance between the initial frames, followed by outlier rejection through hypothesis testing. Then, the DLG is constructed by assigning the MRLA between robots as the edge weight, which illustrates the status of RelLoc in the multi-robot system. To address the second problem, we further introduce an active RelLoc enhancement strategy on top of the DLG that triggers additional inter-robot measurements when needed, enabling autonomous, accuracy-cost aware RelLoc enhancement. When the MRLA between all robot pairs exceeds the threshold, the stopping criterion for RelLoc is satisfied, ensuring high-accuracy RelLoc among robots. The DLG is sensor-independent, focusing on evaluating and enhancing RelLoc accuracy. It is instantiated on a place recognition RelLoc pipeline as a representative case study. Simulations demonstrate that when the MRLA in the DLG reaches 0.98, the Absolute Trajectory Error is less than 0.1 m, and the DLG is further verified in both indoor and outdoor experiments.

1 October 2019 in Journal of Thoracic Oncology
Verified
Journal Article
Closed access
LHL. Huang
L. Huang
YLY. Lv
Y. Lv
WCW. Cang
W. Cang
QLQ. Li
Q. Li
XLX. Liao
X. Liao
LQL. Qiu
L. Qiu