Learning and Reasoning for Robot Dialog and Navigation Tasks

被引:0
|
作者
Lu, Keting [1 ]
Zhang, Shiqi [2 ]
Stone, Peter [3 ]
Chen, Xiaoping [1 ]
机构
[1] USTC, Hefei, Peoples R China
[2] SUNY Binghamton, Binghamton, NY USA
[3] UT Austin, Austin, TX USA
基金
美国国家科学基金会; 中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Reinforcement learning and probabilistic reasoning algorithms aim at learning from interaction experiences and reasoning with probabilistic contextual knowledge respectively. In this research, we develop algorithms for robot task completions, while looking into the complementary strengths of reinforcement learning and probabilistic reasoning techniques. The robots learn from trial-and-error experiences to augment their declarative knowledge base, and the augmented knowledge can be used for speeding up the learning process in potentially different tasks. We have implemented and evaluated the developed algorithms using mobile robots conducting dialog and navigation tasks. From the results, we see that our robot's performance can be improved by both reasoning with human knowledge and learning from task-completion experience. More interestingly, the robot was able to learn from navigation tasks to improve its dialog strategies.
引用
收藏
页码:107 / 117
页数:11
相关论文
共 50 条
  • [1] Quantum Deep Reinforcement Learning for Robot Navigation Tasks
    Hohenfeld, Hans
    Heimann, Dirk
    Wiebe, Felix
    Kirchner, Frank
    [J]. IEEE ACCESS, 2024, 12 : 87217 - 87236
  • [2] Using dialog and human observations to dictate tasks to a learning robot assistant
    Paul E. Rybski
    Jeremy Stolarz
    Kevin Yoon
    Manuela Veloso
    [J]. Intelligent Service Robotics, 2008, 1 : 159 - 167
  • [3] Using dialog and human observations to dictate tasks to a learning robot assistant
    Rybski, Paul E.
    Stolarz, Jeremy
    Yoon, Kevin
    Veloso, Manuela
    [J]. INTELLIGENT SERVICE ROBOTICS, 2008, 1 (02) : 159 - 167
  • [4] Learning Joint Policies for Human-Robot Dialog and Co-Navigation
    Hayamizu, Yohei
    Yu, Zhou
    Zhang, Shiqi
    [J]. 2023 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2023, : 7893 - 7898
  • [5] Generalization and transfer learning in noise-affected robot navigation tasks
    Frommberger, Lutz
    [J]. PROGRESS IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2007, 4874 : 508 - 519
  • [6] Exploring Auxiliary Reasoning Tasks for Task-oriented Dialog Systems with Meta Cooperative Learning
    Qin, Bowen
    Yang, Min
    Bing, Lidong
    Jiang, Qingshan
    Li, Chengming
    Xu, Ruifeng
    [J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 13701 - 13708
  • [7] Asynchronous Deep Reinforcement Learning for the Mobile Robot Navigation with Supervised Auxiliary Tasks
    Tongloy, T.
    Chuwongin, S.
    Jaksukam, K.
    Chousangsuntorn, C.
    Boonsang, S.
    [J]. 2017 2ND INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION ENGINEERING (ICRAE), 2017, : 68 - 72
  • [8] Learning Optimal Navigation Actions for Foresighted Robot Behavior During Assistance Tasks
    Bayoumi, AbdElMoniem
    Bennewitz, Maren
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2016, : 207 - 212
  • [9] ROBOT NAVIGATION WITH LEARNING
    ZELINSKY, A
    [J]. AUSTRALIAN COMPUTER JOURNAL, 1988, 20 (02): : 85 - 93
  • [10] Navigation for human-robot interaction tasks
    Althaus, P
    Ishiguro, H
    Kanda, T
    Miyashita, T
    Christensen, HI
    [J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1- 5, PROCEEDINGS, 2004, : 1894 - 1900