Li Ren

Dr. Li Ren

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
17 February 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
LRLi Ren
Li Ren
YKYiming Kang
Yiming Kang
LYLongfan Yang
Longfan Yang
HJHaitao Jia
Haitao Jia
SWShaojiang Wang
Shaojiang Wang
With the rapid development of industrial automation, robotic arms are increasingly required to operate in dynamic and unstructured environments. Path planning for such systems has become a critical challenge, particularly in scenarios involving dynamic obstacles and complex environments. This paper addresses the challenge of obstacle avoidance path planning for robotic arms in dynamic and complex environments. It introduces a hybrid trajectory planning method that combines the strengths of the rapidly exploring random tree (RRT) and artificial potential field (APF) algorithms. The method divides the process into two phases: initial static path planning and dynamic path replanning. An adaptive angle guidance strategy is proposed to enhance the efficiency of RRT in static environments by improving target directionality and reducing redundant nodes, followed by Catmull–Rom spline interpolation for path smoothing. For dynamic environments, the algorithm dynamically adjusts the weight factors of RRT and APF, enabling rapid local path replanning to avoid both static and dynamic obstacles. Experimental results demonstrate that the proposed method achieves significant improvements in trajectory smoothness, path length, and computational efficiency compared to traditional approaches. This work offers a robust solution for real-time motion planning, contributing to the advancement of robotic arm control in industrial and unstructured settings.

22 January 2025 in Electronics
Verified
Journal Article
Open access
PDF file
LRLi Ren
Li Ren
YKYiming Kang
Yiming Kang
HJHaitao Jia
Haitao Jia
SWShaojiang Wang
Shaojiang Wang
RZRui Zhong
Rui Zhong
In complex environments with multi-object stacking, the spatial relationships between objects necessitate a sequential grasping strategy to ensure both the safety of the target objects and the efficiency of robotic arm operations. To address this challenge, this study introduces a Visual Manipulation Relationship Network (VMRN) to determine the optimal grasping sequence. Traditional VMRN frameworks typically rely on convolutional neural networks (CNNs) for feature extraction, which often struggle with high-frequency feature extraction, long-tail data distributions, and real-time computational demands in multi-object stacking scenarios. To overcome these limitations, we propose a lightweight, convolution-free Transformer-based feature extraction network integrated into the visual detection model. This model is specifically designed for visual reasoning, with a focus on lightweight optimization to enhance the extraction of features for stacked objects. The proposed network incorporates local window attention, global information aggregation and broadcasting, and a dual-dimensional attention-based feedforward network to improve feature representation. Additionally, a novel loss function is designed to address the performance degradation in detecting long-tail categories, effectively mitigating the over-suppression of rare objects in imbalanced datasets. Experimental results demonstrate that the proposed model significantly improves both detection accuracy and computational efficiency, making it particularly suitable for real-time robotic grasping tasks in complex environments due to its lightweight design.

5 January 2024 in Electronics
Verified
Journal Article
Open access
PDF file
HJHaitao Jia
Haitao Jia
JHJing Huang
Jing Huang
KZKang Zhao
Kang Zhao
有毛有思 毛
有思 毛
HZHuanlai Zhou
Huanlai Zhou
WXWenbo Xu
Wenbo Xu
Concepts empower cognitive intelligence. Extracting flat, nested, and discontinuous name entities and concept mentions from natural language texts is significant for downstream tasks such as concept knowledge graphs. Among the algorithms that uniformly detect these types of name entities and concepts, Li et al. proposed a novel architecture by modeling the unified mention recognition as the classification of word–word relations, named W2NER, achieved state-of-the-art (SOTA) results in 2022. However, there is still room for improvement. This paper presents three improvements based on W2NER. We enhanced the grid-tagging network by demonstration learning and tag attention feature extraction, so our modified model is named DTaE. Firstly, addressing the issue of insufficient semantic information in short texts and the lack of annotated data, and inspired by the demonstration learning from GPT-3, a demonstration is searched during the training phase according to a certain strategy to enhance the input features and improve the model’s ability for few-shot learning. Secondly, to tackle the problem of W2NER’s subpar recognition accuracy problem for discontinuous entities and concepts, a multi-head attention mechanism is employed to capture attention scores for different positions based on grid tagging. Then, the tagging attention features are embedded into the model. Finally, to retain information about the sequence position, rotary position embedding is introduced to ensure robustness. We selected an authoritative Chinese dictionary and adopted a five-person annotation method to annotate multiple types of entities and concepts in the definitions. To validate the effectiveness of our enhanced model, experiments were conducted on the public dataset CADEC and our annotated Chinese dictionary dataset: on the CADEC dataset, with a slight decrease in recall rate, precision is improved by 2.78%, and the comprehensive metric F1 is increased by 0.89%; on the Chinese dictionary dataset, the precision is improved by 2.97%, the recall rate is increased by 2.35%, and the comprehensive metric F1 is improved by 2.66%.

1 January 2017
Verified
Conference Paper
Open access
PDF file
LRLi Ren
Li Ren
YFYang Feng
Yang Feng
Currently tracking Track initiation in most core processes, how to achieve multiple objectives in a complex environment more accurate track initiation is still the key and difficult problems of target tracking. Waveform agile radar is currently the latest breakthroughs in the field of cognitive technology radar aspect, it is different from the conventional radar characteristics are mainly from the environment (including the target) in continuous learning to improve target detection capability. This paper introduces minimum gate volume to logic track initiation algorithm, which thesis proposes a track initiation agility algorithm by controlling gate volume to reduce amount of clutter, which improves success rate and accuracy of track.

1 January 2016
Verified
Conference Paper
Open access
PDF file
LRLi Ren
Li Ren
ZMZuzong Muo
Zuzong Muo
With the development of the sensor, the sensor can get more information of targets. Therefore, Scholars start to research new information of targets and a variety of methods are emerged in the process of exploring. It is meaningful for multiple targets tracking that if the sensors can distinguish target classes. In this paper, we study how to use the target classification information to support multiple targets tracking, and we make a further improvement on the JPDA algorithm. Comparison is made in simulation to compare different methods.