vix.ing · top · new · best · stats · spec

Deep Neural Object Analysis by Interactive Auditory Exploration with a\n Humanoid Robot

2018/07/03 by Manfred Eppe, Matthias Kerzel, Eppe, Manfred +5
Computer Science · Engineering · #Advanced Chemical Sensor Technologies #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Human Pose and Action Recognition #Neural and Evolutionary Computing (cs.NE) #Robot Manipulation and Learning #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.1807.01035

openalex publication_date 2018/07/03 · openalex created_date 2021/08/16 · openalex updated_date 2026/07/28

Abstract

We present a novel approach for interactive auditory object analysis with a\nhumanoid robot. The robot elicits sensory information by physically shaking\nvisually indistinguishable plastic capsules. It gathers the resulting audio\nsignals from microphones that are embedded into the robotic ears. A neural\nnetwork architecture learns from these signals to analyze properties of the\ncontents of the containers. Specifically, we evaluate the material\nclassification and weight prediction accuracy and demonstrate that the\nframework is fairly robust to acoustic real-world noise.\n

Related