A Service Robot Instruction Parsing Method for Action Sequence Generation in Intelligent Space

被引：0
|
作者：
Cui Y. [1 ]
Tian G. [1 ]
Zhou Z. [1 ]
Jiang Z. [1 ]
机构：
[1] School of Control Science and Engineering, Shandong University, Jinan
来源：
Jiqiren/Robot | 2024年 / 46卷 / 01期
关键词：
action sequence generation; instruction parsing; intelligent space; intention understanding; service robot; simulation system;
D O I：
10.13973/j.cnki.robot.230074
中图分类号：
学科分类号：
摘要：
Service robots face challenges in difficult task analysis, poor environmental adaptability, and unfriendly human-machine interaction when performing household tasks. In order to accurately understand user intent and plan service steps suitable for the current environment, an intelligent parsing methods for service robot instructions in intelligent spaces is studied, to enhance the cognitive abilities of robots for service tasks in a home environment. Firstly, starting from the keywords in instructions, an intent recognition model based on a gating mechanism is proposed to enhance the robot's cognitive ability towards user instructions. Secondly, a sequence text generation mechanism is proposed, using service strategies as intermediate states, to assist to generate action sequences for the robot. Additionally, a strategy correction mechanism based on intelligent space ontology interaction is employed by integrating multimodal perception between the robot and the environment, to generate service strategies that are most suitable for the current environment. Finally, a task planning module based on domain and problem descriptions is integrated to generate executable action sequences for the robot, thereby improving the quality of service task execution. Experimental results demonstrate that the proposed method maintains a friendly interaction while accurately understanding complex user instructions, and ultimately generates reliable action sequences that the robot can execute. © 2024 Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：1 / 15
页数：14
相关论文
共 30 条
  • [1] NIITSUMA M, HASHIMOTO H, HASHIMOTO H., Spatial memory as an aid system for human activity in intelligent space, IEEE Transactions on Industrial Electronics, 54, 2, pp. 1122-1131, (2007)
  • [2] ZHANG Y, TIAN G H, ZHANG S Y, Et al., Multi-domain knowledge sharing and reuse in home intelligent space, Robot, 41, 4, pp. 507-518, (2019)
  • [3] LI C C, TIAN G H, ZHANG M Y, Et al., Ontology-based humanoid cognition and reasoning of object attributes, Journal of Zhejiang University (Engineering Science), 52, 7, pp. 1231-1238, (2018)
  • [4] ZHANG Y, TIAN G H, CHEN H Z., Exploring the cognitive process for service task in smart home: A robot service mechanism, Future Generation Computer Systems, 102, C, pp. 588-602, (2020)
  • [5] RAFFERTY J, NUGENT C D, LIU J, Et al., From activity recognition to intention recognition for assisted living within smart homes, IEEE Transactions on Human-Machine Systems, 47, 3, pp. 368-379, (2017)
  • [6] ZHANG M Y, TIAN G H, ZHANG Y., A home service-oriented question answering system with high accuracy and stability, IEEE Access, 7, pp. 22988-22999, (2019)
  • [7] GOMEZ L V, MIURA J., Ontology-based knowledge management with verbal interaction for command interpretation and execution by home service robots, Robotics and Autonomous Systems, (2021)
  • [8] YANG P, JI D, AI C M, Et al., AISE: Attending to intent and slots explicitly for better spoken language understanding, Knowledge-Based Systems, (2021)
  • [9] HE T, XU X H, WU Y T, Et al., Multitask learning with knowledge base for joint intent detection and slot filling, Applied Sciences, 11, 11, (2021)
  • [10] ABRO W A, QI G, AAMIR M, Et al., Joint intent detection and slot filling using weighted finite state transducer and BERT, Applied Intelligence, 52, 15, pp. 17356-17370, (2022)
123