Predicting and attending to damaging collisions for placing everyday objects in photo-realistic simulations

Predicting and attending to damaging collisions for placing everyday objects in photo-realistic simulations
复制标题

预测并处理破坏性碰撞,将日常物体置于逼真的模拟中

DOI:
10.1080/01691864.2021.1913446
复制
发表时间:
2021
期刊:
影响因子:
2
通讯作者:
Kawai Hisashi
Kawai Hisashi
中科院分区:
计算机科学4区
文献类型:
--
作者:
Magassouba Aly;Sugiura Komei;Nakayama Angelica;Hirakawa Tsubasa;Yamashita Takayoshi;Fujiyoshi Hironobu;Kawai Hisashi

文献摘要

参考文献

相似文献

放置物体是家用服务机器人的一项基本任务。因此,在放置动作之前推断碰撞风险对于实现所要求的任务是至关重要的。这个问题特别具有挑战性,因为有必要预测如果一个物体被放置在一个杂乱的指定区域会发生什么。我们表明,使用平面检测来检测自由区域的基于规则的方法执行得很差。为了解决这个问题,我们开发了Ponnet,它具有多通道注意分支和自我注意机制,可以基于RGBD图像预测破坏性碰撞。我们的方法可以可视化破坏性碰撞的风险,这是方便的,因为它使用户能够了解风险。为此,我们构建并发布了一个原始数据集,其中包含12,000张照片级的特定放置区域的图像,以及家庭环境中的日常生活对象。实验结果表明,与基线方法相比,该方法提高了准确率。
Placing objects is a fundamental task for domestic service robots (DSRs). Thus, inferring the collision-risk before a placing motion is crucial for achieving the requested task. This problem is particularly challenging because it is necessary to predict what happens if an object is placed in a cluttered designated area. We show that a rule-based approach that uses plane detection, to detect free areas, performs poorly. To address this, we develop PonNet, which has multimodal attention branches and a self-attention mechanism to predict damaging collisions, based on RGBD images. Our method can visualize the risk of damaging collisions, which is convenient because it enables the user to understand the risk. For this purpose, we build and publish an original dataset that contains 12,000 photo-realistic images of specific placing areas, with daily life objects, in home environments. The experimental results show that our approach improves accuracy compared with the baseline methods.
如果...会发生什么
DOI: --
发表时间: 2011
期刊:
影响因子: --
作者:
Louise Brazil;J. Curtis;Rachel Grayer;R. Henry
通讯作者: R. Henry
俯仰轴和偏航轴之间的简单无干扰机构,用于机器人辅助腹腔镜手术中采用的腕机构
DOI: --
发表时间: 2019
期刊: ROBOMECH Journal
影响因子: 1.4
作者:
M. Jinno
通讯作者: M. Jinno
DOI: 10.1080/01691864.2019.1698462
发表时间: 2019
期刊: Advanced Robotics
影响因子: 2
作者:
Mizuchi Y.;Inamura T.
通讯作者: Inamura T.
无需几何对象模型即可拾取和放置
DOI: 10.1109/icra.2018.8460553
发表时间: 2018
期刊: Proceedings of 2018 IEEE International Conference on Robotics and Automation (ICRA
影响因子: --
作者:
Gualtieri, Marcus;Pas, Andreas ten;Platt, Robert
通讯作者: Platt, Robert
基于多模态注意力分支网络的抓取命令语句生成
DOI: --
发表时间: 2020
期刊:
影响因子: --
作者:
小椋忠志;Magassouba Aly;杉浦孔明;平川翼;山下隆義;藤吉弘亘;河井恒
通讯作者: 河井恒