Abstract
Successful manipulation of unknown objects requires an understanding of their physical properties. Infrared thermography has the potential to provide real-time, contactless material characterization for unknown objects. In this paper, we propose an approach that utilizes active thermography and custom multi-channel neural networks to perform classification between samples and regression towards the density property. With the help of an off-the-shelf technology to estimate the volume of the object, the proposed approach is capable of estimating the weight of the unknown object. We show the efficacy of the infrared thermography approach to a set of ten commonly used materials to achieve a 99.1% R 2 -fit for predicted versus actual density values. The system can be used with tele-operated or autonomous robots to optimize grasping techniques for unknown objects without touching them.
Highlights
As robots make their way into real-world applications such as in construction, manufacturing, human interaction, and other civilian and military applications in the marina, aerial or space arena, there is an increasing demand for physical interaction with unknown environments [1]
We present an approach to estimate the weight of an unknown object by estimating the density of the object using active thermography and estimating its the volume
We aim to extend this approach for classification and regression in order to estimate the density of the material based on thermal signature and an off-the-shelf volume estimation technique to estimate the weight of an unknown object using convolutional neural networks
Summary
As robots make their way into real-world applications such as in construction, manufacturing, human interaction, and other civilian and military applications in the marina, aerial or space arena, there is an increasing demand for physical interaction with unknown environments [1]. In a typical manipulation task, the robot is required to develop a gripping technique based on the physical properties of the object. Suitable grasping forces have to be determined preferably before making any physical contact with the object. One of the standing problems endured in grasping unknown objects is the lack of real-time information about the weight of unknown objects without touching or lifting them. Inspired by the fact that humans use rough weight guesses from vision as initial estimation, followed by tactile afferent control that improves the grasping precision, a common technique for estimating object weight is the execution of prevision grips [2]. Weight estimation involves five steps: initial positioning of the robotic arm around the object, (2) grasping and lifting the object,
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
