Jianxiang Feng / 冯健祥
Hi there! I am a final-year PhD student at Technical University of Munich (TUM) and the Institute of Robotic and Mechtronic (RM), German Aerospace Center (DLR).
I am advised by Prof. Rudolph Triebel (DLR&KIT) and affiliated with Munich School of Data Science, where I worked with Prof. Stephan Günnemann.
Recently, I have been working on applying my previous research to grasping and LLMs for Robotics as a senior research scientist at Agile Robots SE.
In general, my research interests reside in the intersection of robotics and machine learning. A primary focus is on the trustworthy and adaptable learning ability of a robot in an open-world environment. Aiming to equip an autonomous agent with introspective capabilities i.e., uncertainty quantification/awareness of system internal states, I am passionate about investigating probabilistic machine learning on how to properly model/quantify it and leverage such information for learning-enabled robotics. I believe that this can lead to more explainable and ultimately safer autonomous robot systems.
P.S. The pronunciation of my first name "Jianxiang" is quite close to "Jensen" (yep, the well-known "Jensen inequality" often used in the Evidence Lower Bound (ELBO) derivation) but with a different ending :P.
Jianxiang Feng received his bachelor degree from Beijing University of Posts and Telecommunication (BUPT) in 2015 and his master degree from Technical University of Munich (TUM) in 2019. Since August 2019, he pursued his PhD at TUM and the Institute of Robotics and Mechatronics (RM), the German Aerospace Center (DLR). His research interests reside in the intersection of robotics and machine learning.
Short Bio
CV
Github
G. Scholar
LinkedIn
jianxiang.feng at tum dot de
|
|
News
10.2024 Congratulations to my former colleagues in DLR EDAN team for winning in the discipline of Assistance Robot Race at Cybathlon 2024!
01.2024 Our ICRA 2024 Workshop titled "Back to the Future: Robot Learning Going Probabilistic" got accepted, thrilled to co-organize it! Stay tuned!
08.2023 A paper on Normalizing Flows for Out-of-Distribution Detection got accepted for CoRL 2023!
07.2023 A paper on Graph Neural Networks and Assembly Sequence Planning got accepted for IROS 2023.
|
Selected Publications
(*: equal contribution.)
|
|
Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning
Jianxiang Feng,
Jongseok Lee,
Simon Geisler,
Stephan Günnemann,
Rudolph Triebel,
7th Conference on Robot Learning (CoRL) 2023.
code
/
webiste
/
poster
/
spotlight presentation
/
bibtex
A novel way to equip NFs with efficient but flexible base distributions to overcome the topological constraint for OOD detection in robot learning.
|
|
Density-based Feasibility Learning with
Normalizing Flows for Introspective Robotic
Assembly
Jianxiang Feng,
Matan Atad ,
Ismael Rodríguez,
Maximilian Durner,
Stephan Günnemann,
Rudolph Triebel,
Workshop on Robotics and AI: The Future of Industrial Assembly Tasks,
Robotics: Science and Systems (RSS-WS) 2023.
code
/
website
/
arxiv
/
presentation video
/
slides
/
bibtex
A density-based method with normalizing flows for feasibility learning in Robotic Assembly based on only feasible examples.
|
|
Efficient and Feasible Robotic Assembly Sequence Planning via Graph Representation Learning
Matan Atad *,
Jianxiang Feng*,
Ismael Rodríguez,
Maximilian Durner,
Rudolph Triebel,
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023.
code
/
website
/
arXiv
/
bibtex
A holistic graphical approach including a graph representation for product assemblies and a policy architecture, Graph Assembly Processing Network, dubbed GRACE to predict assembly sequences in a step-by-step manner.
|
|
Bayesian Active Learning for Sim-to-Real Robotic Perception
Jianxiang Feng,
Jongseok Lee,
Maximilian Durner,
Rudolph Triebel,
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022.
code
/
website
/
arXiv
/
poster
/
slides
/
presentation video
/
demo video
/
bibtex
An active learning pipeline to reduce annotation efforts of real data within a Sim-to-Real scenario based on deep Bayesian Neural Networks.
|
|
Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes
Jongseok Lee,
Jianxiang Feng,
Matthias Humt,
Marcus G. Muller,
Rudolph Triebel,
5th Conference on Robot Learning (CoRL) 2021.
code
/
video
/
bibtex
A probabilistic framework to obtain both reliable and fast uncertainty estimates for predictions with Deep Neural Networks (DNNs) based on Sparse Gaussian Processes.
|
|
Introspective Robot Perception using Smoothed Predictions from Bayesian Neural Networks
Jianxiang Feng,
Maximilian Durner,
Zoltán-Csaba Márton,
Ferenc Bálint-Benczédi,
Rudolph Triebel,
The International Symposium of Robotics Research (ISRR) 2019.
website
/
arXiv
/
bibtex
A method for adaptive image classification based on fusing uncertainty estimates from Bayesian Neural Networks as unary potentials within a Conditional Random Field (CRF).
|
|
DexGANGrasp: Dexterous Generative Adversarial Grasping Synthesis for Task-Oriented Manipulation
Qian Feng*,
David S. Martinez Lema*,
Mohammadhossein Malmir,
Hang Li,
Jianxiang Feng,
Zhaopeng Chen,
Alois Knoll,
IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2024
arxiv /
video
DexGanGrasp comprises a Conditional Generative Adversarial Networks (cGANs)-based DexGenerator to generate dexterous grasps and a discriminator-like DexEvalautor to assess the stability of these grasps.
|
|
Multi-fingered Dynamic Grasping for Unknown Objects
Yannick Burkhardt,
Qian Feng,
Jianxiang Feng,
Karan Sharma,
Zhaopeng Chen,
Alois Knoll,
IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2024
arxiv /
video
A dynamic grasping framework for unknown objects in this work, which uses a five-fingered hand with visual servo control and can compensate for external disturbances.
|
|
Generalizable Robotic Manipulation: Object-Centric Diffusion Policy with Language Guidance
Hang Li,
Qian Feng,
Zhi Zheng,
Jianxiang Feng,
Alois Knoll,
Workshop on Semantics for Robotics: From Environment Understanding and Reasoning to Safe Interaction of Robotics,
Robotics: Science and Systems (RSS-WS) 2024.
arxiv /
video
A language-guided object-centric diffusion policy that takes a 3d representation of task-relevant objects as conditional input and can be guided by cost function for collision avoidance at inference time.
|
|
Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners
Zhi Zheng*,
Qian Feng,
Hang Li,
Alois Knoll,
Jianxiang Feng*,
Workshop on Back to the Future: Robot Learning Going Probabilistic, IEEE International Conference on Robotics and Automation (ICRA) 2024.
webiste
/
poster
/
arxiv
/
bibtex
An investigation of three different ways for uncertainty quantification of a VLM failure detector for closed-loop LLM planners.
|
|
A Survey of Uncertainty in Deep Neural Networks
Jakob Gawlikowski,
Cedrique Rovile Njieutcheu Tassi,
Mohsin Ali,
Jongseok Lee,
Matthias Humt,
Jianxiang Feng,
Anna Kruspe,
Rudolph Triebel,
Peter Jung,
Ribana Roscher,
Muhammad Shahzad,
Wen Yang,
Richard Bamler,
Xiaoxiang Zhu
Artificial Intelligence Review (2023): 1-77
arXiv
/
bibtex
A comprehensive overview of uncertainty estimation in neural networks, reviewing recent advances in the field, highlighting current challenges, and identifying potential research opportunities.
|
|
Virtual Reality via Object Pose Estimation and Active Learning: Realizing Telepresence Robots with Aerial Manipulation Capabilities
Jongseok Lee, Ribin Radhakrishna Balachandran , Konstantin Kondak, Andre Coelho, Marco De Stefano, Matthias Humt, Jianxiang Feng, Tamim Asfour, Rudolph Triebel,
Field Robotics, 2023
video
/
bibtex
A novel teleoperation system for advancing aerial manipulation in dynamic and unstructured environments based on pose estimation pipelines for the industrial objects of
both known and unknown geometries and an active learning pipeline.
|
|
Estimating Model Uncertainty of Neural Networks in Sparse Information Form
Jongseok Lee,
Matthias Humt,
Jianxiang Feng,
Rudolph Triebel,
International Conference on Machine Learning (ICML) 2020.
code
/
bibtex
A sparse representation of model uncertainty for Deep Neural Networks (DNNs) where the parameter posterior is approximated with an inverse formulation of the Multivariate Normal Distribution (MND), also known as the information form.
|
Conference/Journal Reviewer:
- International Conference on Learning Representations (ICLR) 2025
- Conference on Robot Learning (CoRL) 2022-2024
- IEEE International Conference on Robotics and Automation (ICRA) 2020&2022&2025
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020&2022
- European Conference on Artificial Intelligence (ECAI) 2020
- IEEE-RAS International Conference on Humanoid Robots 2024
- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
Workshop Organizer:
|
06.2022 Team player, EDAN demo at Automatica Exhibition 2022 ( press).
|
08.2023 Master Thesis Supervision at TUM: "Improving Sample Selection in Active Learning Using Graph Neural Networks" by Zhoumin Zhao, co-supervision with Simon Geisler.
06.2023 Research Internship at DLR: "Automating Scene Graph Data Generation for Task and Motion Planning via Blenderproc" by Juan Diego Plaza Gomez, co-supervision with Samuel Bustamante and Dominik Winkelbauer.
|
Link to the template. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.
|
|