Learning the behavior model of a robot

Infantes, Guillaume; Ghallab, Malik; Ingrand, Félix

doi:10.1007/s10514-010-9212-1

Cited by 17 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Numerous methods have been proposed for acquiring and improving action models at the skill and task levels. Approaches for acquiring and improving skill models are for example [78] with HMM, or [104] with Dynamic Bayes Nets (DBN) [56]. Skill selection can be addressed as acquiring an MDP policy, as illustrated in the Robel system [152].…”

Section: Acquiring Planning and Acting Modelsmentioning

confidence: 99%

Deliberation for autonomous robots: A survey

Ingrand

Ghallab

2017

Artificial Intelligence

Self Cite

241

151

View full text Add to dashboard Cite

International audienceAutonomous robots facing a diversity of open environments and performing a variety of tasks and interactions need explicit deliberation in order to fulfill their missions. Deliberation is meant to endow a robotic system with extended, more adaptable and robust functionalities, as well as reduce its deployment cost. The ambition of this survey is to present a global overview of deliberation functions in robotics and to discuss the state of the art in this area. The following five deliberation functions are identified and analyzed: planning, acting, monitoring, observing, and learning. The paper introduces a global perspective on these deliberation functions and discusses their main characteristics, design choices and constraints. The reviewed contributions are discussed with respect to this perspective. The survey focuses as much as possible on papers with a clear robotics content and with a concern on integrating several deliberation functions

show abstract

Section: Acquiring Planning and Acting Modelsmentioning

confidence: 99%

Deliberation for autonomous robots: A survey

Ingrand

Ghallab

2017

Artificial Intelligence

Self Cite

241

151

View full text Add to dashboard Cite

show abstract

“…In an AS, one can learn a skill for acting (e.g. using reinforcement learning [Kober et al, 2013] or DBN [Infantes et al, 2010]), an action model for planning, (e.g. using MDP), or a perception classifier (e.g.…”

Section: Learned Modelsmentioning

confidence: 99%

Recent Trends in Formal Validation and Verification of Autonomous Robots Software

Ingrand

2019

2019 Third IEEE International Conference on Robotic Computing (IRC)

View full text Add to dashboard Cite

The consequences of autonomous systems software failures can be potentially dramatic. There is no need to darken the picture, but still, it seems unlikely that people, insurance companies and certification agencies will let autonomous systems fly or drive around without requiring their makers and programmers to prove that the most critical parts of the software are robust and reliable. This is already the case for aeronautic, rail transportation, nuclear plants, medical devices, etc. were software must be certified, which possibly involve its formal validation and verification (V&V). Moreover, autonomous systems go further and embed onboard deliberation functions. This is what make them really autonomous, but open new challenges. We propose to consider the overall problem of V&V of autonomous systems software and examine the current situation with respect to the various type of software used. In particular, we point out that the availability of formal models is rather different depending on the type of component considered. We distinguish these different cases and stress the areas where we think we need to focus our efforts as to improve the overall robustness of autonomous systems.

show abstract

“…Infantes et al [19] Vazquez et al [22] presented a growing hidden Markov model (GHMM) which is used to recognize human and vehicle motions. The key feature of a GHMM is the ability of on-line and incremental learning of parameters and structure of a model.…”

Section: Hidden Markov Model (Hmm)mentioning

confidence: 99%

Simple and complex behavior learning using behavior hidden Markov model and CobART

2013

View full text Add to dashboard Cite

Date:I hereby declare that all information in this document has been obtained and presented in accordance with academic rules and ethical conduct. I also declare that, as required by these rules and conduct, I have fully cited and referenced all material and results that are not original to this work. In this thesis, behavior learning and generation models are proposed for simple and complex behaviors of robots using unsupervised learning methods. Simple behaviors are modeled by simple-behavior learning model (SBLM) and complex behaviors are modeled by complex-behavior learning model (CBLM) which uses previously learned simple or complex behaviors. Both models have common phases named behavior categorization, behavior modeling, and behavior generation. Sensory data are categorized using correlation based adaptive resonance theory network that generates motion primitives corresponding to robot's base abilities in the categorization phase. In the modeling phase, Behavior-HMM, a modified version of hidden Markov model, is used to model the relationships among the motion primitives in a finite state stochastic network. In addition, a motion generator which is an artificial neural network is trained for each motion primitive to learn essential robot motor commands. In the generation phase, desired task is presented as a target observation and the model generates corresponding motion primitive sequence. Then, these motion primitives are executed successively by the motion generators which are specifically trained for the corresponding motion primitives.The models are not proposed for one specific behavior, but are intended to be bases for all behaviors. CBLM enhances learning capabilities by integrating previously learned behaviors hierarchically. Hence, new behaviors can take advantage of already discovered behaviors. The proposed models are tested on a robot simulator and the experiments showed that simple and complex-behavior learning models can generate requested behaviors effectively. Bu tez kapsamında, basit ve karmaşık robot davranışlarını gözetmen ihtiyacı duymayan yöntemlerle ögrenen ve tekrarlayabilen davranış modelleri tasarlandı. Basit davranışlar basit-davranış ögrenme modeli (SBLM) ile karmaşık davranışlar ise daha önce ögrenilen basit ve karmaşık davranışları kullanabilen karmaşık-davranış ögrenme modeli (CBLM) ile modellendi. Her iki model de davranış sınıflan-dırma, davranış modelleme ve davranış üretme aşamalarından oluşmaktadır. Sınıflandırma aşamasında algılayıcılardan elde edilen veriler robotun temel yeteneklerine karşılık gelen temel hareketleri elde etmek amacıyla ilinti temelli uyarlanır rezonans kuramı kullanılarak sınıflandırılır. Modelleme aşama-sında, saklı Markov modelinin degiştirilmiş birşekli olan davranış-HMM kullanılarak temel hareketler arasındaki ilişki sonlu durumlu olasılıksal ag biçiminde modellenir. Davranış modeline ilaveten robot motor komutlarını ögrenmek amacıyla her bir temel davranış için yapay sinir aglarını kullanan bir hareket üretici egitilir. Davranış üretme aşamasın...

show abstract

Learning the behavior model of a robot

Cited by 17 publications

References 35 publications

Deliberation for autonomous robots: A survey

Deliberation for autonomous robots: A survey

Recent Trends in Formal Validation and Verification of Autonomous Robots Software

Simple and complex behavior learning using behavior hidden Markov model and CobART

Contact Info

Product

Resources

About