Filters








277 Hits in 6.3 sec

Learning Policy for Robot Anomaly Recovery Based on Robot Introspection [chapter]

Xuefeng Zhou, Hongmin Wu, Juan Rojas, Zhihao Xu, Shuai Li
2020 Nonparametric Bayesian Learning for Collaborative Robot Multimodal Introspection  
If and only if robot reverse many times (not less than twice) and still couldn't avoid or eliminate the anomaly, the human interaction is called.  ...  Zhou et al., Nonparametric Bayesian Learning for Collaborative Robot Multimodal Introspection, https://doi.  ...  Learning Policy for Robot Anomaly Recovery Based on Robot Introspection Learning Policy for Robot Anomaly Recovery Based on Robot Introspection Learning Policy for Robot Anomaly Recovery Based  ... 
doi:10.1007/978-981-15-6263-1_6 fatcat:v6cjejtmebdprayfwbjmgeoeku

Incremental Learning Introspective Movement Primitives from Multimodal Unstructured Demonstrations

Hongmin Wu, Zhihao Xu, Wu Yan, Qianxin Su, Shuai Li, Xuefeng Zhou
2019 IEEE Access  
INDEX TERMS Introspection, movement primitives, unstructured demonstration, Bayesian nonparametric learning, reverse execution, human interaction, kitting experiment.  ...  and adaptive exploration during robot manipulation task.  ...  Duan and D. Liu for their assistance on system development and Prof. J. Rojas for his revision on English writing throughout this project.  ... 
doi:10.1109/access.2019.2947529 fatcat:hwypvbiz55clrkfwcg5ojkjsyq

DARPA's Explainable Artificial Intelligence (XAI) Program

David Gunning, David Aha
2019 The AI Magazine  
decisions and actions to human users.  ...  The XAI developer teams are addressing the first two challenges by creating ML techniques and developing principles, strategies, and human-computer interaction techniques for generating effective explanations  ...  and Avi Pfeffer (CRA), Song-Chun Zhu (UCLA), Alan Fern (OSU), Mark Stefik (PARC), Zico Kolter (Carnegie Mellon), Mohamed Amer and Giedrius Burachas (SRI International), Bill Ferguson (Raytheon BBN), Vibhav  ... 
doi:10.1609/aimag.v40i2.2850 fatcat:2woifhwpdbcvbce5e6dm7xc4vm

Endowing Robots with Longer-term Autonomy by Recovering from External Disturbances in Manipulation through Grounded Anomaly Classification and Recovery Policies [article]

Hongmin Wu, Shuangqi Luo, Longxin Chen, Shuangda Duan, Sakmongkon Chumkamon, Dong Liu, Yisheng Guan, Juan Rojas
2018 arXiv   pre-print
Robot manipulation is increasingly poised to interact with humans in co-shared workspaces.  ...  A recovery critic stands atop of a tightly-integrated, graph-based online motion-generation and introspection system that resolves a wide range of anomalous situations.  ...  Vincent Duchaine and his team from the Department of Automated Manufacturing Engineering at Quebec University for his kind support in donating the multimodal tactile sensor used in this work (Maslyczyk  ... 
arXiv:1809.03979v1 fatcat:7xl6r3ltybgadgdlhm6jzjtbym

Nonparametric Bayesian Method for Robot Anomaly Diagnose [chapter]

Xuefeng Zhou, Hongmin Wu, Juan Rojas, Zhihao Xu, Shuai Li
2020 Nonparametric Bayesian Learning for Collaborative Robot Multimodal Introspection  
We evaluated the proposed methods with a multi-step human-robot collaboration objects kitting task on Baxter robot, the performance and results are presented of each method respectively. © The Author(s  ...  In this chapter, we introduce two novel anomaly diagnose methods using the Bayesian nonparametric hidden Markov models when anomaly triggered, including i)multi-class classifier based on nonparametric  ...  [50] carried out a diagnoses of the types of robot anomalies and their causes, and integrated this function into a human-robot interactive robot system for feeding disabled people.  ... 
doi:10.1007/978-981-15-6263-1_5 fatcat:gfvoox3mifhc3dutbcxastriu4

Efficient Automatic Perception System Parameter Tuning On Site without Expert Supervision

Humphrey Hu, George Kantor
2017 Conference on Robot Learning  
This incurs a large startup cost when deploying a robotic system by relying on human expertise and ground truth instrumentation.  ...  Our approach extends upon recent work on introspecting perception performance and uses Bayesian optimization to efficiently search the parameter configuration space.  ...  a model-based search.  ... 
dblp:conf/corl/HuK17 fatcat:tk53hjrszrbshl6jgnsjeul7qa

Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study

Ziyu Yao, Yu Su, Huan Sun, Wen-tau Yih
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
We then propose a simple yet remarkably effective instantiation of our framework, demonstrated on two text-to-SQL datasets (WikiSQL and Spider) with different state-of-the-art base semantic parsers.  ...  A key part of the agent is a world model: it takes a percept (either an initial question or subsequent feedback from the user) and transitions to a new state.  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Office or the  ... 
doi:10.18653/v1/d19-1547 dblp:conf/emnlp/YaoSSY19 fatcat:75gbwip5gjaj3mzrk7grgkq6cm

Endowing Robots with Longer-term Autonomy by Recovering from External Disturbances in Manipulation Through Grounded Anomaly Classification and Recovery Policies

Shuangqi Luo, Hongmin Wu, Shuangda Duan, Yijiong Lin, Juan Rojas
2021 Journal of Intelligent and Robotic Systems  
Our recovery critic stands atop of a tightly-integrated, graph-based online motion-generation and introspection system.  ...  Policies, skills, and introspection models are learned incrementally and contextually over time.  ...  Vincent Duchaine with the Department of Automated Manufacturing Engineering at Quebec University for his kind support in donating the multimodal tactile sensor used in this work [31] .  ... 
doi:10.1007/s10846-021-01312-6 fatcat:zyguj6hjrjbydmcv2d6qvncwom

"Dave...I can assure you ...that it's going to be all right ..." A Definition, Case for, and Survey of Algorithmic Assurances in Human-Autonomy Trust Relationships

Brett W. Israelsen, Nisar R. Ahmed
2019 ACM Computing Surveys  
Building on these definitions, a synthesis of research across communities such as machine learning, human-computer interaction, robotics, e-commerce, and others reveals that assurance algorithms naturally  ...  Algorithmic assurances are first formally defined and classified from the perspective of formally modeled human-artificially intelligent agent trust relationships.  ...  on introspective assurances that inform users of competency limits and boundaries of AIA capabilities without requiring user interaction, and that can generally be separated from core AIA functionality  ... 
doi:10.1145/3267338 fatcat:7wzpdawvwbdmvavttqfsu2fly4

A Latent State-Based Multimodal Execution Monitor with Anomaly Detection and Classification for Robot Introspection

Hongmin Wu, Yisheng Guan, Juan Rojas
2019 Applied Sciences  
observation based on trained models.  ...  We consider a humanrobot cooperation task to verify our work and measure the robustness and accuracy of each skill.  ...  Acknowledgments: We thank Shuangqi Luo and Shuangda Duan for their assistance throughout this project. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app9061072 fatcat:rcca4rjkgralbhmnbishzigo6y

What is an intelligent system? [article]

Martin Molina
2022 arXiv   pre-print
The goal of this paper is to give a general description of an intelligent system, which integrates previous approaches and takes into account recent advances in artificial intelligence.  ...  The concept of intelligent system has emerged in information technology as a type of system derived from successful applications of artificial intelligence.  ...  Besides these mechanisms, interaction with users can also be based on human language using algorithms on natural language processing. • Deliberative reasoning.  ... 
arXiv:2009.09083v2 fatcat:4xvajrzdpbdhjcc5hegpcxrumi

Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study [article]

Ziyu Yao, Yu Su, Huan Sun, Wen-tau Yih
2019 arXiv   pre-print
In this paper, we propose a new, unified formulation of the interactive semantic parsing problem, where the goal is to design a model-based intelligent agent.  ...  We then propose a simple yet remarkably effective instantiation of our framework, demonstrated on two text-to-SQL datasets (WikiSQL and Spider) with different state-of-the-art base semantic parsers.  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Office or the  ... 
arXiv:1910.05389v1 fatcat:ftshqnucp5anbnqbt7ixq4swe4

Understandable and trustworthy explainable robots: A sensemaking perspective

Guglielmo Papagni, Sabine Koeszegi
2020 Paladyn: Journal of Behavioral Robotics  
To this extent, we identify three main issues to solve: the approximate nature of explanations, their dependence on the interaction context and the intrinsic limitations of human understanding.  ...  AbstractThis article discusses the fundamental requirements for making explainable robots trustworthy and comprehensible for non-expert users.  ...  The former takes a more theoretical approach, while the latter is based on actual data collected from humanhuman and human-agent interactions.  ... 
doi:10.1515/pjbr-2021-0002 fatcat:hc5ltujes5ei3pgjyxwpdbkvsu

Intelligent Robotic Perception Systems [chapter]

Cristiano Premebida, Rares Ambrus, Zoltan-Csaba Marton
2018 Applications of Mobile Robots [Working Title]  
Robotic perception, in the scope of this chapter, encompasses the ML algorithms and techniques that empower robots to learn from sensory data and, based on learned models, to react and take decisions accordingly  ...  Recent advances in human-robot interaction, complex robotic tasks, intelligent reasoning, and decision-making are, at some extent, the results of the notorious evolution and success of ML algorithms.  ...  Thus, a high-level cognitive ability that is required for operating alongside humans is to continuously improve performance based on introspection.  ... 
doi:10.5772/intechopen.79742 fatcat:zrvsznb3frcthl3pfy7r54kire

Vision Systems with the Human in the Loop

Christian Bauckhage, Marc Hanheide, Sebastian Wrede, Thomas Käster, Michael Pfeiffer, Gerhard Sagerer
2005 EURASIP Journal on Advances in Signal Processing  
Experiences from psychologically evaluated human-machine interactions will be reported and the promising potential of psychologically-based usability experiments will be stressed.  ...  All three systems are designed to interact with human users.  ...  The authors would like to thank Silke Fischer for the valuable support and suggestions she provided for our usability experiments.  ... 
doi:10.1155/asp.2005.2375 fatcat:y7k2nij3nfdzlprcsox6hikjwe
« Previous Showing results 1 — 15 out of 277 results