Bodily aware soft robots: integration of proprioceptive and\n exteroceptive sensors

2017/10/15 by Gabor Soter, Soter, Gabor, Andrew T. Conn +5 · 2 citations
Computer Science · Engineering · #Advanced Sensor and Energy Harvesting Materials #FOS: Computer and information sciences #Human Pose and Action Recognition #Interactive and Immersive Displays #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.1710.05419

openalex publication_date 2017/10/15 · openalex created_date 2022/10/03 · openalex updated_date 2026/07/28

Abstract

Being aware of our body has great importance in our everyday life. This is\nthe reason why we know how to move in a dark room or to grasp a complex object.\nThese skills are important for robots as well, however, robotic bodily\nawareness is still an unsolved problem. In this paper we present a novel method\nto implement bodily awareness in soft robots by the integration of\nexteroceptive and proprioceptive sensors. We use a combination of a stacked\nconvolutional autoencoder and a recurrent neural network to map internal\nsensory signals to visual information. As a result, the simulated soft robot\ncan learn to \imagine its motion even when its visual sensor is not\navailable.\n

Cited by

• An Enhanced Proprioceptive Method for Soft Robots Integrating Bend Sensors and IMUs
• Pose Estimation of a Cable-Driven Serpentine Manipulator Utilizing Intrinsic Dynamics via Physical Reservoir Computing

Related

• Enabling the Sense of Self in a Dual-Arm Robot
• PneuGelSight: Soft Robotic Vision-Based Proprioception and Tactile Sensing
• Sensorimotor representation learning for an "active self" in robots: A\n model survey
• Real-time Soft Body 3D Proprioception via Deep Vision-based Sensing
• Proprioceptive and Exteroceptive Information Perception in a Fabric Soft Robotic Arm via Physical Reservoir Computing with minimal training data