arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1903.00412cs.RO
收藏

RoboCSE:机器人常识嵌入

RoboCSE: Robot Common Sense Embedding

Georgia Institute of Technology(佐治亚理工学院);Institute for Robotics and Intelligent Machines(机器人与智能机器研究所)

Angel Daruna, Weiyu Liu, Zsolt Kira, Sonia Chernova

摘要:

自主服务机器人需要计算框架,使它们能够以一种建模不确定性的方式将知识推广到新的情况,同时扩展到现实世界的问题规模。机器人常识嵌入(RoboCSE)展示了一类计算框架,多关系嵌入,这些框架尚未在机器人技术中用于建模语义知识。我们在一个现实的家庭环境模拟器(AI2Thor)上验证RoboCSE,以衡量它如何概括有关对象启示,位置和材料的知识。我们的实验表明,RoboCSE可以比使用预先训练的嵌入(如Word2Vec)的基线更好地执行预测,在使用比我们的贝叶斯逻辑网络基线少几个数量级的内存的同时,实现了统计学上的显著改进。此外,我们表明,RoboCSE所做的预测是强大的,可用于训练的数据以及域转移到MatterPort3D的显着减少,实现统计上的显着改善,记忆训练数据的基线。

英文摘要:

Autonomous service robots require computational frameworks that allow them to generalize knowledge to new situations in a manner that models uncertainty while scaling to real-world problem sizes. The Robot Common Sense Embedding (RoboCSE) showcases a class of computational frameworks, multi-relational embeddings, that have not been leveraged in robotics to model semantic knowledge. We validate RoboCSE on a realistic home environment simulator (AI2Thor) to measure how well it generalizes learned knowledge about object affordances, locations, and materials. Our experiments show that RoboCSE can perform prediction better than a baseline that uses pre-trained embeddings, such as Word2Vec, achieving statistically significant improvements while using orders of magnitude less memory than our Bayesian Logic Network baseline. In addition, we show that predictions made by RoboCSE are robust to significant reductions in data available for training as well as domain transfer to MatterPort3D, achieving statistically significant improvements over a baseline that memorizes training data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑