Comprehension of spoken natural language is an essential skill for robots to communicate with humans effectively. However, handling unconstrained spoken instructions is challenging due to (1) complex structures and the wide variety of expressions used in spoken language, and (2) inherent ambiguity of human instructions. In this paper, we propose the first comprehensive system for controlling robots with unconstrained spoken language, which is able to effectively resolve ambiguity in spoken instructions. Specifically, we integrate deep learning-based object detection together with natural language processing technologies to handle unconstrained spoken instructions, and propose a method for robots to resolve instruction ambiguity through dialogue. Through our experiments on both a simulated environment as well as a physical industrial robot arm, we demonstrate the ability of our system to understand natural instructions from human operators effectively, and show how higher success rates of the object picking task can be achieved through an interactive clarification process. 1
Bacteroides-Prevotella group is one of the most promising targets for detecting fecal contamination in water environments, principally due to its host-specific distributions and high concentrations in feces of warm-blooded animals. We developed real-time PCR assays for quantifying chicken/duck-, chicken-, and duck-associated Bacteroides-Prevotella 16S rRNA genetic markers (Chicken/Duck-Bac, Chicken-Bac, and Duck-Bac). A reference collection of DNA extracts from 143 individual fecal samples and wastewater treatment plant influent was tested by the newly established markers. The quantification limits of Chicken/Duck-Bac, Chicken-Bac, and Duck-Bac markers in environmental water were 54, 57, and 12 copies/reaction, respectively. It was possible to detect possible fecal contaminations from wild ducks in environmental water with the constructed genetic marker assays, even though the density of total coliforms in the identical water samples was below the detection limit. Chicken/Duck-Bac marker was amplified from feces of wild duck and chicken with the positive ratio of 96 and 61 %, respectively, and no cross-reaction was observed for the other animal feces. Chicken-Bac marker was detected from 70 % of chicken feces, while detected from 39 % of cow feces, 8.3 % of pig feces, and 12 % of swan feces. Duck-Bac marker was detected from 85 % of wild duck feces and cross-reacted with 31 % of cow feces. These levels of detection specificity are common in avian-associated genetic markers previously proposed, which implies that there is a practical limitation in the independent application of avian-associated Bacteroides-Prevotella 16S rRNA genetic markers and a combination with other fecal contamination markers is preferable for detecting fecal contamination in water environments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.