Autonomous Learning – Max Planck Institute for Intelligent Systems

Autonomous Learning Appointment 01-08-2024 Huanbo Sun becomes Assistant Professor in Peking University Test Abstract

Autonomous Learning Award 01-08-2023 Got grant InsightCobot from Baden-Württemberg Stiftung on manipulation with cobots using haptic sensors

Autonomous Learning News 20-04-2023 Albane Ruaud selected to join the 72nd Lindau Nobel Laureate Meeting The postdoctoral researcher from the Autonomous Learning Group at the Max Planck Institute for Intelligent Systems in Tübingen is one of 635 young scientists from across the world who are given the opportunity to participate in a week of scientific exchange with some of the world’s greatest minds. Albane Ruaud

Autonomous Learning Appointment 01-04-2023 Georg Martius is appointed W3 professor at the University of Tübingen

Autonomous Learning News 26-07-2022 Georg Martius receives ERC Consolidator Grant Autonomous Learning research group at the MPI-IS in Tübingen is awarded € 2 million for a period of 5 years. Georg Martius

Autonomous Learning Award 21-07-2022 ERC Consolidator Grant for the project REAL-RL = Model-based Reinforcement Learning for Versatile Robots in the Real World.

Autonomous Learning Haptic Intelligence News 24-02-2022 Fingertip sensitivity for robots Striving to improve touch sensing in robotics, scientists developed a thumb-shaped sensor with a camera hidden inside and trained a deep neural network to infer its haptic contact information. When something touches the finger, the system constructs a three-dimensional force map from the visible deformations of its flexible outer shell. This research invention significantly improves a robot finger’s haptic perception, coming ever closer to the sense of touch of human skin. Huanbo Sun Georg Martius Katherine J. Kuchenbecker

Autonomous Learning News 05-05-2021 Machine learning dynamics of quantum systems Researchers at the University of Tübingen and MPI-IS have applied machine learning methods to understand the quantum dynamics in physical models. Georg Martius Dominik Zietlow

Autonomous Learning News 15-01-2021 Two Publications Accepted at ICLR 2021 Our papers "Extracting Strong Policies for Robotics Tasks from Zero-order Trajectory Optimizers" and "Self-supervised Visual Reinforcement Learning with Object-centric Representations" got acceped to ICLR 2021. Cristina Pinneri Shambhuraj Sawant Sebastian Blaes Andrii Zadaianchuk Maximilian Seitzer Georg Martius

Autonomous Learning News 15-06-2020 CVPR Oral Now Online We just uploaded our presentations for our CVPR paper "Optimizing Rank-based Metrics with Blackbox Differentiation" to YouTube. Michal Rolinek Anselm Paulus Marin Vlastelica Pogancic Georg Martius

Autonomous Vision Autonomous Learning Dynamic Locomotion Intelligent Control Systems News 29-04-2020 MPI for Intelligent Systems continues video series Video No 4 is now available Short films present scientists' research projects in an understandable way Alejandro Posada Andreas Geiger Alexander Badri-Spröwitz Georg Martius Sebastian Trimpe

Autonomous Learning News 01-02-2020 Accepted Paper at CVPR Our paper on optimizing rank-based metrics with blackbox differentiation received flawless reviews and got accepted at CVPR 2020 Michal Rolinek Anselm Paulus Marin Vlastelica Pogancic Georg Martius

Autonomous Learning News 20-12-2019 Perfect Review-Scores for our ICLR Submission Our paper "Differentiation of Blackbox Combinatorial Solvers" received perfect review-scores for ICLR 2020! Marin Vlastelica Pogancic Anselm Paulus Georg Martius Michal Rolinek

Autonomous Learning News 12-12-2019 Two posters at NeurIPS We presented two posters at NeurIPS: "Control What You Can" and "Differentiation of Blackbox Combinatorial Solvers" Sebastian Blaes Marin Vlastelica Pogancic Michal Rolinek Georg Martius

Autonomous Learning News 10-07-2019 Article published in Frontiers in Neurorobotics Huanbo's paper 'Machine Learning for Haptics: Inferring Multi-Contact Stimulation From Sparse Sensor Configuration' was successfully published! Huanbo Sun Georg Martius

Autonomous Learning News 12-03-2019 CVPR 2019 Paper Accepted Our paper 'Variational Autoencoders Recover PCA Directions (by Accident)' got accepted at CVPR 2019! We are looking forward to present it as a poster in June at Long Beach! The paper elaborates on the close connection between Variational Autoencoders and the well known PCA algorithm in terms of their alignment of the latent space. Michal Rolinek Dominik Zietlow Georg Martius

Autonomous Learning News 11-02-2019 Winners of the final RL Course Competition Congratulations to Team SSP for winning the final Reinforcement Learning course competition with their SAC (Soft Actor Critic) agent. Sebastian Blaes Jia-Jie Zhu Georg Martius

Autonomous Learning News 04-12-2018 Poster @ NeurIPS 2018 presentation of our L4 Paper We had a busy 2h poster presentation with many interested visitors

Autonomous Learning News 13-07-2018 First machine learning method capable of accurate extrapolation Scientists develop new machine learning method that can make robots safer - New method provides simpler and more intuitive models of physical situations Understanding how a robot will react under different conditions is essential to guaranteeing its safe operation. But how do you know what will break a robot without actually damaging it? A new method developed by scientists at the Institute of Science and Technology Austria and the Max Planck Institute for Intelligent Systems is the first machine learning method that can use observations made under safe conditions to make accurate predictions for all possible conditions governed by the same physical dynamics. Especially designed for real-life situations, their method provides simple, interpretable descriptions of the underlying physics. The researchers will present their findings tomorrow at this year’s prestigious International Conference for Machine Learning (ICML). Georg Martius

Autonomous Learning News 27-06-2018 Jia-Jie Zhu receives the Marie Curie Individual Fellowship A prestigious junior scientist fellowship is awarded to the MPI-IS researcher Jia-Jie Zhu Georg Martius

Autonomous Learning Award 25-06-2018 coming

Autonomous Learning News 21-06-2018 ICML 2018 paper accepted Our Paper "Learning Equations for Extrapolation and Control" got excepted at ICML 2018! We are looking forward to present and discuss in Stockholm in July 10-15, 2018. Georg Martius

Autonomous Learning Award 19-06-2018 Michal Rolinek is awarded with a CVPR Honorable Mention for the paper 'Efficient Optimization for Rank-based Loss Functions'

Autonomous Learning News 19-06-2018 CVPR Honorable Mention The paper 'Efficient Optimization for Rank-based Loss Functions', on which Michal Rolinek was contributing to, received the CVPR Honorable Mention award. Michal Rolinek

Autonomous Learning News 01-05-2018 ALIFE 2018 paper accepted Our paper 'Systematic self-exploration of behaviors for robots in a dynamical systems framework' was accepted for ALIFE 2018 and will be presented in Tokyo, July 2018. Cristina Pinneri Georg Martius