Affordance-Based Grasping and Manipulation in Real World Applications скачать в хорошем качестве

Affordance-Based Grasping and Manipulation in Real World Applications

Christoph Pohl*, Kevin Hitzler*, Raphael Grimm, Antonio Zea, Uwe D. Hanebeck and Tamim Asfour Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany In real world applications, robotic solutions remain impractical due to the challenges that arise in unknown and unstructured environments. To perform complex manipulation tasks in complex and cluttered situations, robots need to be able to identify the interaction possibilities with the scene, i.e. the affordances of the objects encountered. In unstructured environments with noisy perception, insufficient scene understanding and limited prior knowledge, this is a challenging task. In this work, we present a robust approach for grasping unknown objects in cluttered scenes with a humanoid robot in the context of a nuclear decommissioning task. Our approach combines the convenience and reliability of autonomous robot control with the precision and adaptability of teleoperation in a semi-autonomous selection of grasp affordances. This allows exploiting the expert knowledge of an experienced teleoperator while keeping the cognitive load of the operator to a minimum. To evaluate our approach, we conducted 75 real world experiments with more than 660 grasp executions on the humanoid robot ARMAR-6. The results demonstrate that high-level decisions made by the teleoperator, supported by autonomous robot control, can contribute significantly to successful task execution. *The first two authors contributed equally to this work