Xperience project, European Union Seventh Framework Programme FP7/2007-2013

[Airicist]

Website - xperience.org (https://www.xperience.org)

youtube.com/@xperienceproject3842 (https://www.youtube.com/@xperienceproject3842)

[Airicist]

https://youtu.be/jN5YkXkoeF8

Interaction learning for dynamic movement primitives used in cooperative robotic tasks

Published on May 26, 2014


Since several years dynamic movement primitives (DMPs) are more and more getting into the center of interest for flexible movement control in robotics. In this study we introduce sensory feedback together with a predictive learning mechanism which allows tightly coupled dual-agent systems to learn an adaptive,
sensor-driven interaction based on DMPs. The coupled conventional (no-sensors, no learning) DMP system automatically equilibrates and can still be solved analytically allowing us to derive conditions for stability. When adding adaptive sensor control we can show that both agents learn to cooperate.Interestingly, all these mechanisms are entirely based on low level interactions without any planning or cognitive component. In videos we show two interaction demos (human-robot and robot-robot) where agents learn to interact and cooperate in order to help each other to ovoid obstacles on a way.

[Airicist]

https://youtu.be/ZMa3NckVoE8

Robots bootstrapped through learning from experience

Published on Jan 20, 2017


This video shows an integrated demonstration of central results of the Xperience project. In the example task of preparing a salad
and setting a table together with a human, the robot ARMAR-III uses its knowledge gained from previous experience to plan and execute
the necessary actions towards its goal. The demonstration highlights the aspects of the realization of integrated complete robot systems,
and emphasizes the concept of structural bootstrapping on the levels of human-robot communication and physical interaction, sensorimotor
learning, learning of object affordances, and planning in robotics.

The scenario integrates several scientific methods developed in the project:
- Execution of complex manipulation tasks and plans based on the developed architecture and its implementation
- Automatic generation of domain descriptions for planning based on the robots experience
- Replanning on the fly in case of missing objects
- Replacing missing objects by employing different bootstrapping (replacement) strategies
- Replacing actions by adapting previously learnt actions to new context
- Human-robot communication in natural language including the robot's understanding of spoken commands, world descriptions, and feedback as well as the robot's ability to ask the human for help and information
- Handing over objects between the robot and the human