Deep Neural Object Analysis by Interactive Auditory Exploration with a Humanoid Robot
This addresses the challenge of object analysis in robotics for scenarios where visual information is insufficient, though it is incremental in applying neural networks to auditory data.
The paper tackles the problem of analyzing object properties using auditory signals from a robot shaking capsules, achieving material classification and weight prediction with robustness to real-world noise.
We present a novel approach for interactive auditory object analysis with a humanoid robot. The robot elicits sensory information by physically shaking visually indistinguishable plastic capsules. It gathers the resulting audio signals from microphones that are embedded into the robotic ears. A neural network architecture learns from these signals to analyze properties of the contents of the containers. Specifically, we evaluate the material classification and weight prediction accuracy and demonstrate that the framework is fairly robust to acoustic real-world noise.