Internship: Training Diffusion policies with Reinforcement Learning for Robotic Mobile Manipulation
at
NAVER LABS Europe
Description
Diffusion models demonstrate state-of-the-art performance on a variety of learning from demonstrations tasks in the domain of robotic manipulation [1][2][3], because of high training stability and their ability to capture complex multi-modal action distributions. However, as expert demonstration data are often sub-optimal and exhibit a limited coverage of actual task space, diffusion policies trained through a supervised objective can be sub-optimal.
Globally, this Internship aims at overcoming this limitation and at using Reinforcement Learning (RL) as a way to fine-tune diffusion policies, pre-trained with large-scale datasets [4]. As demonstrated in [5], this appears as a natural pipeline to improve the performance of models beyond the limits of demonstration data [5].
More specifically, in our team, we designed a novel object-centric policy architecture for learning more efficiently and more effectively a repertoire of robot mobile manipulation skills. The objective of the internship will be to investigate how this novel object-centric policy architecture can be leveraged to improve the fine-tuning of diffusion models using RL and, eventually, their performances.
Required skills
- Last year MSc or PhD student in Machine Learning/Reinforcement Learning, preferably in the Robotics domain; existing publications in top conferences will provide a significant advantage in the application process.
- Solid background in deep learning
- Excellent coding skills, especially in PyTorch
- Familiarity with robotics and robotic simulators is a plus
References
[1] C. Chi, S. Feng, Y. Du, Z. Xu, E. Cousineau, B. Burchfiel, and S. Song, “Diffusion Policy: Visuomotor Policy Learning via Action Diffusion,” in RSS, 2023.
[2] H. Zhen, X. Qiu, P. Chen, J. Yang, X. Yan, Y. Du, Y. Hong, and C. Gan, “3D-VLA: A 3D VisionLanguage-Action Generative World Model,” in ICML, 2024.
[3] S.-F. Chen, H.-C. Wang, M.-H. Hsu, C.-M. Lai, and S.-H. Sun, “Diffusion Model-Augmented Behavioral Cloning,” in Proceedings of the 41st International Conference on Machine Learning, pp. 7486–7510, PMLR, July 2024.
Application instructions
Please note that applicants must be registered students at a university or other academic institution and that this establishment will need to sign an 'Internship Convention' with NAVER LABS Europe before the student is accepted.
You can apply for this position online. Don't forget to upload your CV and cover letter before you submit. Incomplete applications will not be accepted.
About NAVER LABS
NAVER is the #1 Internet portal in Korea with activities that span a wide range of businesses including search, commerce, content, financial and cloud platforms.
NAVER LABS, co-located in Korea and France, is the organization dedicated to preparing NAVER’s future. NAVER LABS Europe is located in a spectacular setting in Grenoble, in the heart of the French Alps. Scientists at NAVER LABS Europe are empowered to pursue long-term research problems that, if successful, can have significant impact and transform NAVER. We take our ideas as far as research can to create the best technology of its kind. Active participation in the academic community and collaborations with world-class public research groups are, among others, important tools to achieve these goals. Teamwork, focus and persistence are important values for us.
NAVER LABS Europe is an equal opportunity employer.
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
VISION
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.