paper-with-me

홈 › Papers

Top-1 CORSMAL Challenge 2020 Submission: Filling Mass Estimation Using Multi-modal Observations of Human-robot Handovers

2020-12-02 · Vladimir Iashin, Francesca Palermo, Gökhan Solak, Claudio Coppola

Human-robot object handover is a key skill for the future of human-robot collaboration. CORSMAL 2020 Challenge focuses on the perception part of this problem: the robot needs to estimate the filling mass of a container held by a human. Although there are powerful methods in image processing and audio processing individually, answering such a problem requires processing data from multiple sensors together. The appearance of the container, the sound of the filling, and the depth data provide essential information. We propose a multi-modal method to predict three key indicators of the filling mass: filling type, filling level, and container capacity. These indicators are then combined to estimate the filling mass of a container. Our method obtained Top-1 overall performance among all submissions to CORSMAL 2020 Challenge on both public and private subsets while showing no evidence of overfitting. Our source code is publicly available: https://github.com/v-iashin/CORSMAL

📄 PDF Abstract BibTeX arXiv:2012.01311

Code (1)

v-iashin/CORSMAL 공식 구현 pytorch

Tasks

Capacity EstimationFilling Level EstimationFilling Mass EstimationFilling Type Estimation

Methods 이 논문이 사용한 방법론

GRU A Gated Recurrent Unit, or GRU, is a type of recurrent neural network. It is similar to an LSTM, but only has two gates - a reset…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Container Localisation and Mass Estimation with an RGB-D Camera

2022-03-02 · Tommaso Apicella, Giulia Slavic, Edoardo Ragusa, Paolo Gastaldo 외

In the research area of human-robot interactions, the automatic estimation of the mass of a container manipulated by a person leveraging only visual information is a challenging task. The main challenges consist of occlu…

Improving Generalization of Deep Networks for Estimating Physical Properties of Containers and Fillings

2022-03-02 · Hengyi Wang, Chaoran Zhu, Ziyin Ma, Changjae Oh

We present methods to estimate the physical properties of household containers and their fillings manipulated by humans. We use a lightweight, pre-trained convolutional neural network with coordinate attention as a backb…

Data Augmentation

The CORSMAL benchmark for the prediction of the properties of containers

2021-07-27 · Alessio Xompero, Santiago Donaher, Vladimir Iashin, Francesca Palermo 외

The contactless estimation of the weight of a container and the amount of its content manipulated by a person are key pre-requisites for safe human-to-robot handovers. However, opaqueness and transparencies of the contai…

Audio-Visual Object Classification for Human-Robot Collaboration

2022-03-03 · A. Xompero, Y. L. Pang, T. Patten, A. Prabhakar 외

Human-robot collaboration requires the contactless estimation of the physical properties of containers manipulated by a person, for example while pouring content in a cup or moving a food box. Acoustic and visual signals…

ClassificationObject

Improving filling level classification with adversarial training

2021-02-08 · Apostolos Modas, Alessio Xompero, Ricardo Sanchez-Matilla, Pascal Frossard 외

We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass. This problem is made challenging by several ambiguities caused by transparencies, shape variations and …

ClassificationGeneral ClassificationTransfer Learning