Robotics and Biology Laboratory

The Physical Exploration Challenge

Robots Learning to Discover, Actuate and Explore Degrees of Freedom in the World

Contact Persons

Project Leaders:

Researchers: 

Researchers - Alumni: 

  • Johannes Kulick (Stuttgart)
  • Sebastian Höfer (Berlin)
  • Roberto Martin Martin (Berlin)

Administration:

  • Elizabeth Ball (Berlin)
  • Carola Stahl (Stuttgart)

Associates:

  • Shlomo Zilberstein (Massachusetts)

Summary

This project addresses a fundamental challenge in the intersection of machine learning and robotics. The machine learning community has developed formal methods to generate behaviour for agents that learn from their own actions. However, several fundamental questions are raised when trying to realize such behaviour on real-world robotics systems that shall learn to perceive, actuate and explore degrees of freedom (DoF) in the world.
These questions pertain to basic theoretical aspects as well as the tight dependencies between exploration strategies and the perception and motor skills used to realize them. The goal of this project is to equip real-world robotic systems with one of the most  interesting aspects of intelligence: an internal drive to learn, i.e., the ability to organize their behavior so as to maximize learning progress towards an objective.
If successful, we believe that this will make a transitional change in the way such systems behave, in their autonomy of learning, in the way they ground acquired knowledge, and eventually also in the way they will interact with humans and play their part in application in industry and in the private sector. To examine the interplay between these building blocks, we built a mechanical device we call lock-box. This device features multiple mechanical joints that can lock each other. It is a rich testbed to research how motor and perceptual skills can be used for exploration of a complex physical environment.
The robot has to cope with a very high degree of uncertainty in this domain. If it tried to move an object and that object did not move, then there can be multiple explanations for this: the object can be rigidly attached to the environment, the object can be part of a mechanism that only temporarily locked, or the robot could have moved the mechanism but did not perform the right action. We want to find out how a robot can resolve this issue.
We already have some answers to the questions that surfaced on the way to our goal. Interactive Perception can be used to detect joints between movable objects.  Coupled Learning of Action Parameters and Forward Models for Manipulation,  can give the robot the ability to learn models for its own actions and the kinematic structure of its environment simultaneously.

Funding


The project is funded by DFG's Priority Programme 1527 Autonomous Learning

Publications

2022

Baum, Manuel; Schattenhofer, Lukas; R"ossler, Theresa; Osuna-Mascaró, Antonio; Auersperg, Alice; Kacelnik, Alex; Brock, Oliver
Yoking-Based Identification of Learning Behavior in Artificial and Biological Agents
Proceedings of the International Conference on the Simulation of Adaptive Behavior 2022 -From Animals to Animats 16, Seite 67–78
Herausgeber: Springer International Publishing, Cham
2022
ISBN
978-3-031-16770-6
Baum, Manuel; Brock, Oliver
"The World Is Its Own Best Model": Robust Real-World Manipulation Through Online Behavior Selection
Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)
2022

2021

Baum, Manuel; Brock, Oliver
Achieving Robustness in a Drawer Manipulation Task by using High-level Feedback instead of Planning
Proceedings of the DGR Days, Seite 29-29
DGR Days
2021

2019

Martín-Martín, Roberto; Brock, Oliver
Coupled recursive estimation for online interactive perception of articulated objects
The International Journal of Robotics Research, OnlineFirst :1-33
Mai 2019
Martín-Martín, Roberto; Eppner, Clemens; Brock, Oliver
The RBO dataset of articulated objects and interactions
The International Journal of Robotics Research, 39 (9) :1013-1019
April 2019

2018

Eppner, Clemens; Höfer, Sebastian; Jonschkowski, Rico; Martín-Martín, Roberto; Sieverling, Arne; Wall, Vincent; Brock, Oliver
Four aspects of building robotic systems: lessons from the Amazon Picking Challenge 2015
Autonomous Robots, 42 (7) :1459–1475
Oktober 2018
Herausgeber: Springer US
Höfer, Sebastian; Raisch, Jörg; Toussaint, Marc; Brock, Oliver
No Free Lunch in Ball Catching: A Comparison of Cartesian and Angular Representations for Control
PLoS ONE, 13 (6)
2018
Eppner, Clemens; Martín-Martín, Roberto Roberto; Brock, Oliver
Physics-Based Selection of Informative Actions for Interactive Perception
Proceedings of the IEEE International Conference on Robotics and Automation, Seite 7427-7432
2018

2017

Baum, Manuel; Bernstein, Matthew; Martín-Martín, Roberto; Höfer, Sebastian; Kulick, Johannes; Toussaint, Marc; Kacelnik, Alex; Brock, Oliver
Opening a Lockbox through Physical Exploration
Proceedings of the IEEE International Conference on Humanoid Robots (Humanoids)
2017
Eppner, Clemens; Martín-Martín, Roberto; Brock, Oliver
Physics-Based Selection of Actions That Maximize Motion for Interactive Perception
RSS workshop: Revisiting Contact - Turning a problem into a solution
2017
Martín-Martín, Roberto; Brock, Oliver
Cross-Modal Interpretation of Multi-Modal Sensor Streams in Interactive Perception Based on Coupled Recursion
In IEEE, Editor, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Seite 3289-3295
IEEE
In IEEE, Editor
2017
Höfer, Sebastian
On decomposability in robot reinforcement learning
Technische Universität Berlin, Berlin, Germany
2017
Martín-Martín, Roberto; Brock, Oliver
Building Kinematic and Dynamic Models of Articulated Objects with Multi-Modal Interactive Perception
In AAAI, Editor, AAAI Symposium on Interactive Multi-Sensory Object Perception for Embodied Agents
In AAAI, Editor
2017
Baum, Manuel; Brock, Oliver
Achieving Robustness by Optimizing Failure Behavior
Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Seite 5806-5811
2017

2016

Höfer, Sebastian; Raffin, Antonin; Jonschkowski, Rico; Brock, Oliver; Stulp, Freek
Unsupervised Learning of State Representations for Multiple Tasks
Workshop on Deep Learning for Action and Interaction at NIPS,
Dezember 2016
Höfer, Sebastian; Brock, Oliver
Coupled Learning of Action Parameters and Forward Models for Manipulation
In IEEE, Editor, IEEE/RSJ International Conference on Intelligent Robots and Systems, Seite 3893-3899
In IEEE, Editor
Oktober 2016
Jonschkowski, Rico; Eppner, Clemens; Höfer, Sebastian; Martín-Martín, Roberto; Brock, Oliver
Probabilistic Multi-Class Segmentation for the Amazon Picking Challenge
IEEE/RSJ International Conference on Intelligent Robots and Systems, Seite 1-7
Oktober 2016
Martín-Martín, Roberto; Sieverling, Arne; Brock, Oliver
Estimating the Relation of Perception and Action During Interaction
International Workshop on Robotics in the 21st century: Challenges and Promises,
September 2016
Eppner, Clemens; Höfer, Sebastian; Jonschkowski, Rico; Martín-Martín, Roberto; Sieverling, Arne; Wall, Vincent; Brock, Oliver
Lessons from the Amazon Picking Challenge: Four Aspects of Building Robotic Systems
Proceedings of Robotics: Science and Systems
Herausgeber: AnnArbor, Michigan
Juni 2016
Martín-Martín, Roberto; Höfer, Sebastian; Brock, Oliver
An Integrated Approach to Visual Perception of Articulated Objects
Proceedings of the IEEE International Conference on Robotics and Automation, Seite 5091 - 5097
Mai 2016
Jonschkowski, Rico; Höfer, Sebastian; Brock, Oliver
Patterns for Learning with Side Information
Februar 2016

2015

Buckmann, Marcus; Gaschler, Robert; Höfer, Sebastian; Loeben, Dennis; Frensch, Peter A.; Brock, Oliver
Learning to Explore the Structure of Kinematic Objects in a Virtual Environment
Frontiers in Psychology, 6 (374)
April 2015
Baum, Manuel; Meier, Martin; Schilling, Malte
Population based Mean of Multiple Computations networks: A building block for kinematic models
2015 International Joint Conference on Neural Networks (IJCNN), Seite 1–8
IEEE
2015

2014

Martín-Martín, Roberto; Brock, Oliver
Deterioration of Depth Measurements due to Interference of Multiple RGB-D Sensors
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Seite 4205-4212
2014
Höfer, Sebastian; Lang, Tobias; Brock, Oliver
Extracting Kinematic Background Knowledge from Interactions Using Task-Sensitive Relational Learning
Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Seite 4342-4347
2014

Seite 1 von 2