Ning Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ning Wang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Martin J. Pearson
University of the West of England
2 shared publications Ziheng Xue
Bristol Robotics Laboratory, University of Bristol, University of the West of England, Bristol, United Kingdom
2 shared publicationsArturs Elksnis
Bristol Robotics Laboratory, University of Bristol, University of the West of England, Bristol, United Kingdom
1 shared publication- Arturs Elksnis
Bristol Robotics Laboratory, University of the West of England and University of Bristol, Bristol, UK
1 shared publication - Chenguang Yang
Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China
1 shared publication - Cunjia Liu
Loughborough University
1 shared publication
Latest Publications
- Open Access
- 4 September 2025
- Published by Frontiers Media SA in Frontiers in Robotics and AI
- Vol. 12, 1627937
Integrating large language models for intuitive robot navigation
Home assistance robots face challenges in natural language interaction, object detection, and navigation, mainly when operating in resource-constrained home environments, which limits their practical deployment. In this study, we propose an AI agent framework based on Large Language Models (LLMs), which includes EnvNet, RoutePlanner, and AIBrain, to explore solutions for these issues. Utilizing quantized LLMs allows the system to operate on resource-limited devices while maintaining robust interaction capabilities. Our proposed method shows promising results in improving natural language understanding and navigation accuracy in home environments, also providing a valuable exploration for deploying home assistance robots.
- 4 September 2025
- Published by Frontiers Media SA in Frontiers in Robotics and AI
- Vol. 12, 1627937
Open AccessIntegrating large language models for intuitive robot navigation
Home assistance robots face challenges in natural language interaction, object detection, and navigation, mainly when operating in resource-constrained home environments, which limits their practical deployment. In this study, we propose an AI agent framework based on Large Language Models (LLMs), which includes EnvNet, RoutePlanner, and AIBrain, to explore solutions for these issues. Utilizing quantized LLMs allows the system to operate on resource-limited devices while maintaining robust interaction capabilities. Our proposed method shows promising results in improving natural language understanding and navigation accuracy in home environments, also providing a valuable exploration for deploying home assistance robots.
- 9 July 2025
- Published by ELS Publishing Co. Limited in Robot Learning
- Vol. 2 (1) , 1-31
Utility of low-parameter count, quantized large language models and visual language models in semantic navigation
The use of Large Language Models (LLMs) in Semantic Navigation (SN) is a novel approach and has so far centered around high-parameter count cloud-hosted LLMs. In this study we explore the capabilities...
- 9 July 2025
- Published by ELS Publishing Co. Limited in Robot Learning
- Vol. 2 (1) , 1-31
Utility of low-parameter count, quantized large language models and visual language models in semantic navigation
The use of Large Language Models (LLMs) in Semantic Navigation (SN) is a novel approach and has so far centered around high-parameter count cloud-hosted LLMs. In this study we explore the capabilities...
- Open Access
- 28 February 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (5) , 2615
A Vision-Guided Deep Learning Framework for Dexterous Robotic Grasping Using Gaussian Processes and Transformers
Robotic manipulation of objects with diverse shapes, sizes, and properties, especially deformable ones, remains a significant challenge in automation, necessitating human-like dexterity through the integration of perception, learning, and control. This study enhances a previous framework combining YOLOv8 for object detection and LSTM networks for adaptive grasping by introducing Gaussian Processes (GPs) for robust grasp predictions and Transformer models for efficient multi-modal sensory data integration. A Random Forest classifier also selects optimal grasp configurations based on object-specific features like geometry and stability. The proposed grasping framework achieved a 95.6% grasp success rate using Transformer-based force modulation, surpassing LSTM (91.3%) and GP (91.3%) models. Evaluation of a diverse dataset showed significant improvements in grasp force modulation, adaptability, and robustness for two- and three-finger grasps. However, limitations were observed in five-finger grasps for certain objects, and some classification failures occurred in the vision system. Overall, this combination of vision-based detection and advanced learning techniques offers a scalable solution for flexible robotic manipulation.
- 28 February 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (5) , 2615
Open AccessA Vision-Guided Deep Learning Framework for Dexterous Robotic Grasping Using Gaussian Processes and Transformers
Robotic manipulation of objects with diverse shapes, sizes, and properties, especially deformable ones, remains a significant challenge in automation, necessitating human-like dexterity through the integration of perception, learning, and control. This study enhances a previous framework combining YOLOv8 for object detection and LSTM networks for adaptive grasping by introducing Gaussian Processes (GPs) for robust grasp predictions and Transformer models for efficient multi-modal sensory data integration. A Random Forest classifier also selects optimal grasp configurations based on object-specific features like geometry and stability. The proposed grasping framework achieved a 95.6% grasp success rate using Transformer-based force modulation, surpassing LSTM (91.3%) and GP (91.3%) models. Evaluation of a diverse dataset showed significant improvements in grasp force modulation, adaptability, and robustness for two- and three-finger grasps. However, limitations were observed in five-finger grasps for certain objects, and some classification failures occurred in the vision system. Overall, this combination of vision-based detection and advanced learning techniques offers a scalable solution for flexible robotic manipulation.