Yong A
Research Subjects
Yong A has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Bin Fang
Beijing University of Posts and Telecommunications
2 shared publications - Jun Shi
Vision Computing Lab, Samsung R&D Institute China – Beijing (SRC-B), Beijing, China
2 shared publications - Peng Hao
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2 shared publications - Yixiang Jin
Vision Computing Lab, Samsung R&D Institute China – Beijing (SRC-B), Beijing, China
2 shared publications - Dingzhe Li
Samsung Research China Beijing (SRC-B), Beijing, China
1 shared publication - Dingzhe Li
Advanced Technology Team
1 shared publication
Latest Publications
- 20 November 2025
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 45 (7) , 1091-1142
What foundation models can bring for robot learning in manipulation: A survey
The realization of universal robots is an ultimate goal of researchers. However, a key hurdle in achieving this goal lies in the robots’ ability to manipulate objects in their unstructured environments according to different tasks. The learning-based approach is considered an effective way to address generalization. The impressive performance of foundation models in the fields of computer vision and natural language suggests the potential of embedding foundation models into manipulation tasks as a viable path toward achieving general manipulation capability. However, we believe achieving general manipulation capability requires an overarching framework akin to auto driving. This framework should encompass multiple functional modules, with different foundation models assuming distinct roles in facilitating general manipulation capability. This survey focuses on the contributions of foundation models to robot learning for manipulation. We propose a comprehensive framework and detail how foundation models can address challenges in each module of the framework. What’s more, we examine current approaches, outline challenges, suggest future research directions, and identify potential risks associated with integrating foundation models into this domain.
- 20 November 2025
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 45 (7) , 1091-1142
What foundation models can bring for robot learning in manipulation: A survey
The realization of universal robots is an ultimate goal of researchers. However, a key hurdle in achieving this goal lies in the robots’ ability to manipulate objects in their unstructured environments according to different tasks. The learning-based approach is considered an effective way to address generalization. The impressive performance of foundation models in the fields of computer vision and natural language suggests the potential of embedding foundation models into manipulation tasks as a viable path toward achieving general manipulation capability. However, we believe achieving general manipulation capability requires an overarching framework akin to auto driving. This framework should encompass multiple functional modules, with different foundation models assuming distinct roles in facilitating general manipulation capability. This survey focuses on the contributions of foundation models to robot learning for manipulation. We propose a comprehensive framework and detail how foundation models can address challenges in each module of the framework. What’s more, we examine current approaches, outline challenges, suggest future research directions, and identify potential risks associated with integrating foundation models into this domain.
- Top Cited Papers
- 23 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (3) , 2543-2550
RobotGPT: Robot Manipulation Learning From ChatGPT
We present RobotGPT, an innovative decision framework for robotic manipulation that prioritizes stability and safety. The execution code generated by ChatGPT cannot guarantee the stability and safety of the system. ChatGPT may provide different answers for the same task, leading to unpredictability. This instability prevents the direct integration of ChatGPT into the robot manipulation loop. Although setting the temperature to 0 can generate more consistent outputs, it may cause ChatGPT to lose diversity and creativity. Our objective is to leverage ChatGPT's problem-solving capabilities in robot manipulation and train a reliable agent. The framework includes an effective prompt structure and a robust learning model. Additionally, we introduce a metric for measuring task difficulty to evaluate ChatGPT's performance in robot manipulation. Furthermore, we evaluate RobotGPT in both simulation and real-world environments. Compared to directly using ChatGPT to generate code, our framework significantly improves task success rates, with an average increase from 38.5% to 91.5%. Therefore, training a RobotGPT by utilizing ChatGPT as an expert is a more stable approach compared to directly using ChatGPT as a task planner.
- 23 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (3) , 2543-2550
Top Cited PapersRobotGPT: Robot Manipulation Learning From ChatGPT
We present RobotGPT, an innovative decision framework for robotic manipulation that prioritizes stability and safety. The execution code generated by ChatGPT cannot guarantee the stability and safety of the system. ChatGPT may provide different answers for the same task, leading to unpredictability. This instability prevents the direct integration of ChatGPT into the robot manipulation loop. Although setting the temperature to 0 can generate more consistent outputs, it may cause ChatGPT to lose diversity and creativity. Our objective is to leverage ChatGPT's problem-solving capabilities in robot manipulation and train a reliable agent. The framework includes an effective prompt structure and a robust learning model. Additionally, we introduce a metric for measuring task difficulty to evaluate ChatGPT's performance in robot manipulation. Furthermore, we evaluate RobotGPT in both simulation and real-world environments. Compared to directly using ChatGPT to generate code, our framework significantly improves task success rates, with an average increase from 38.5% to 91.5%. Therefore, training a RobotGPT by utilizing ChatGPT as an expert is a more stable approach compared to directly using ChatGPT as a task planner.