Chi Li

Chi Li

Auto-generated profile, based on publicly available information

Chi Li

College of Information Engineering, Dalian University,Dalian,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
12 April 2019 in IEEE Sensors Journal
Verified
Journal Article
Closed access
CLChi Li
Chi Li
SWSen Wang
Sen Wang
YZYan Zhuang
Yan Zhuang
FYFei Yan
Fei Yan
Multi-sensor fusion plays a key role in 2D laser based robot location and navigation. Although it has achieved great success, there are still some challenges, e.g., being fragile when having large angular rotation. In this paper, we present a deep learning based approach to localizing a mobile robot using a 2D laser and an Inertial Measurement Unit. A novel Recurrent Convolutional Neural Network (RCNN) based architecture is developed to fuse laser and inertial data for scan-to-scan pose estimation. A scan-to-submap optimization is also introduced to optimize the poses estimated by the RCNN for enhanced robustness and accuracy. Extensive experiments have been conducted in both simulation and practice with a real mobile robot, verifying the effectiveness of the proposed deep sensor fusion system.

2 August 2022 in Transactions of the Institute of Measurement and Control
Verified
Journal Article
Closed access
CLChi Li
Chi Li
FYFei Yan
Fei Yan
SWSen Wang
Sen Wang
YZYan Zhuang
Yan Zhuang
Light detection and ranging (LiDAR) odometry plays a crucial role in autonomous mobile robots and unmanned ground vehicles (UGVs). This paper presents a deep learning–based odometry system using two successive three-dimensional (3D) point clouds to estimate their scene flow and then predict their relative pose. The network consumes continuous 3D point clouds directly and outputs their scene flow and uncertain mask in a coarse-to-fine fashion. A pose estimation layer without trainable parameters is designed to compute the pose with the scene flow. We also introduce a scan-to-map optimization algorithm to enhance the robustness and accuracy of the system. Our experiments on the KITTI odometry data set and our campus data set demonstrate the effectiveness of the proposed deep learning–based point cloud odometry.

21 July 2022 in IET Cyber-Systems and Robotics
Verified
Journal Article
Open access
CLChi Li
Chi Li
FYFei Yan
Fei Yan
YZYan Zhuang
Yan Zhuang
Deep‐learning‐based 3D place recognition has received more attention since the data‐driven fashion is widely used for the 3D point cloud applications. Most of the existing deep‐learning‐based 3D place recognition methods only utilise a single scene for place recognition. However, a single scene may have measurement noise or observable dynamic object differences, which may lead to a reduction in recognition accuracy. To improve the performance of 3D place recognition, a sequence matching based rearrangement method is proposed. Our sequence matching method is based on an assignment algorithm and guides the candidate rearrangement in searching for a similar place. The global descriptor extraction adapts the effective sparse tensor representation and a simple pooling layer to obtain the global descriptor. A new loss function combination is employed to train the network. The proposed approach is evaluated on the popular 3D place recognition benchmarks, which proves the effectiveness of the proposed approach.

27 October 2023
Verified
Conference Paper
Closed access
JLJ. Li
J. Li
SWShixi Wen
Shixi Wen
YZYuan Zhao
Yuan Zhao
CLChi Li
Chi Li
To address the vehicle trajectory planning and tracking control problem in vehicular platoon control, we propose a two-layered hierarchical control framework based on deep deterministic policy gradient (DDPG) combined with incremental PID with switching function, considering the communication abnormal (packet-dropout, time delay, interruption) during the following process. Firstly, the vehicle dynamics model is constructed based on vehicle theory, secondly, the state space, action space, and multi-objective reward function are designed based on reinforcement learning theory for the decision-making of the RL-Agent, and finally, the effectiveness of the designed controller was validated through experimental simulations. The results show that: the controller designed in this paper, not only can realize the vehicle speed error, and vehicle space error quickly converge to zero, but also the communication time delay, the following vehicle can still smoothly follow the preceding vehicle, acceleration, and speed.

17 November 2023
Verified
Conference Paper
Closed access
ZYZhuang Yu
Zhuang Yu
SWShixi Wen
Shixi Wen
YZYuan Zhao
Yuan Zhao
CLChi Li
Chi Li
This paper explores the issue of multi-Automated Guided Vehicles formation control in special scenarios. The leader-following type of formation is adopted, take account of both the time delay in communication between AGVs and the disturbance caused by the acceleration of the leader AGV. In the first, a third-order kinematic model is established for the driving mode of the automated guided vehicles. Secondly, a composite controller consisting of an integral sliding mode controller and a feedback controller is designed. The feedback controller is used for the followers to track the leader AGV, the distinctive sliding surface of the sliding mode controller enables compensation for jerk. Thus, the effect of the acceleration disturbance from the leader is mitigated. Finally, the effectiveness of the proposed method is verified by Matlab/simulink simulation software.

1 January 2026 in IET Cyber-Systems and Robotics
Verified
Journal Article
Open access
FZFengkai Zhou
Fengkai Zhou
CLChi Li
Chi Li
YZYan Zhuang
Yan Zhuang
Real‐time dense three‐dimensional (3D) semantic mapping plays a crucial role in robotics. However, existing explicit and implicit representations often entail a trade‐off among geometric precision, semantic richness and computational efficiency. To address this challenge, we propose a hierarchical hybrid mapping framework that unifies geometry, appearance and dense semantics within a shared multiresolution hash grid, enabling end‐to‐end optimisation via differentiable rendering. By caching per‐keyframe semantic masks and reusing them during incremental refinement, our method eliminates redundant semantic segmentation and significantly accelerates runtime. Additionally, an adaptive keyframe pruning strategy further ensures bounded memory usage. Extensive experiments demonstrate that our framework achieves real‐time performance with superior geometric and semantic accuracy.