Robust Robotic Pouring using Audition and Haptics
RWTH Publications (RWTH Aachen)
Abstract
Robust and accurate estimation of liquid height lies as an essential part of pouring tasks for service robots. However, vision-based methods often fail in occluded conditions while audio-based methods cannot work well in a noisy environment. We instead propose a multimodal pouring network (MP-Net) that is able to robustly predict liquid height by conditioning on both audition and haptics input. MP-Net is trained on a self-collected multimodal pouring dataset. This dataset contains 300 robot pouring recordings with audio and force/torque measurements for three types of target containers. We also augment the audio data by inserting robot noise. We evaluated MP-Net on our collected dataset and a wide variety of robot experiments. Both network training results and robot experiments demonstrate that MP-Net is robust against noise and changes to the task and environment. Moreover, we further combine the predicted height and force data to estimate the shape of the target container.
Authors 9
-
Affiliation as printed
Group TAMS, Universität Hamburg
-
Universität Hamburg · RWTH Aachen University
Affiliation as printed
Group TAMS, Universität Hamburg
Institute of General Mechanics, RWTH Aachen University
-
Affiliation as printed
Group TAMS, Universität Hamburg
-
University of California, Los Angeles
Affiliation as printed
Group VCLA, University of California, Los Angeles
-
Affiliation as printed
Group TAMS, Universität Hamburg
-
Affiliation as printed
Signal Processing (SP), Universitat Hamburg
-
Affiliation as printed
Tsinghua University
-
Affiliation as printed
Institute of General Mechanics, RWTH Aachen University
-
Affiliation as printed
Group TAMS, Universität Hamburg
Cited by 16 stored of 16
16 results