Autonomous mobile robots are designed to behave appropriately in changing real-world environments without human intervention. In order to satisfy the requirements of autonomy, robots have to cope with unknown settings...
详细信息
Autonomous mobile robots are designed to behave appropriately in changing real-world environments without human intervention. In order to satisfy the requirements of autonomy, robots have to cope with unknown settings and several issues of uncertainties in dynamic, unstructured and complex environments. A first step is to provide a robot with cognitive capabilities and the ability of self-examination to detect behavioral abnormalities. Unfortunately, most existing anomaly detection systems are neither suitable for the domain of robotic behavior nor flexible enough or even well generalizable. In the following article, we introduce a novel anomaly detection framework based on spatial-temporal models for robotic behaviors which is generally applicable for e.g., plan execution monitoring. The introduced framework combines the methodology of Kohonen's Self-organizing Maps (SOMs) and probabilistic graphical models (PGM) exploiting all advantages of both concepts. The underlying methods of the framework are discussed briefly, whereas the data-driven training of the spatial-temporal model and the reasoning process are described in detail. Finally, the framework is evaluated with different scenarios to emphasize its potential and its high level of generalization and flexibility in robotic application.
We present a novel hierarchical model for human activity recognition. In contrast with approaches that successively recognize actions and activities, our approach jointly models actions and activities in a unified fra...
详细信息
We present a novel hierarchical model for human activity recognition. In contrast with approaches that successively recognize actions and activities, our approach jointly models actions and activities in a unified framework, and their labels are simultaneously predicted. The model is embedded with a latent layer that is able to capture a richer class of contextual information in both state-state and observation-state pairs. Although loops are present in the model, the model has an overall linear-chain structure, where the exact inference is tractable. Therefore, the model is very efficient in both inference and learning. The parameters of the graphical model are learned with a structured support vector machine. A data-driven approach is used to initialize the latent variables;therefore, no manual labeling for the latent states is required. The experimental results from using two benchmark datasets show that our model outperforms the state-of-the-art approach, and our model is computationally more efficient.
This paper presents a novel approach that exploits semantic knowledge to enhance the object recognition capability of autonomous robots. Semantic knowledge is a rich source of information, naturally gathered from huma...
详细信息
This paper presents a novel approach that exploits semantic knowledge to enhance the object recognition capability of autonomous robots. Semantic knowledge is a rich source of information, naturally gathered from humans (elicitation), which can encode both objects' geometrical/appearance properties and contextual relations. This kind of information can be exploited in a variety of robotics skills, especially for robots performing in human environments. In this paper we propose the use of semantic knowledge to eliminate the need of collecting large datasets for the training stages required in typical recognition approaches. Concretely, semantic knowledge encoded in an ontology is used to synthetically and effortless generate an arbitrary number of training samples for tuning probabilistic graphical models (PGMs). We then employ these PGMs to classify patches extracted from 3D point clouds gathered from office environments within the UMA-offices dataset, achieving a similar to 90% of recognition success, and from office and home scenes within the NYU2 dataset, yielding a success of similar to 81% and similar to 69.5% respectively. Additionally, a comparison with state-of-the-art recognition methods also based on graphicalmodels has been carried out, revealing that our semantic-based training approach can compete with, and even outperform, those trained with a considerable number of real samples. (C) 2015 Elsevier B.V. All rights reserved.
We consider the problem of multi-label classification where a feature vector may belong to one of more different classes or concepts at the same time. Many existing approaches are devoted for solving the difficult est...
详细信息
We consider the problem of multi-label classification where a feature vector may belong to one of more different classes or concepts at the same time. Many existing approaches are devoted for solving the difficult estimation task of uncovering the relationship between features and active concepts, solely from data without taking into account any sensible functional structure. In this paper, we propose a novel probabilistic generative model that aims to describe the core generative process of how multiple active concepts can contribute to feature generation. Within our model, each concept is associated with multiple representative base feature vectors, which shares the central idea of sparse feature modeling with the popular dictionary learning. However, by dealing with the weight coefficients as exclusive latent random variables encoding contribution levels, we effectively frame the coefficient learning task as probabilistic inference. We introduce two parameter learning algorithms for the proposed model: one based on standard maximum likelihood learning via the expectation-maximization algorithm, the other focusing on maximally separating the margin of the true concept configuration away from the class boundary. In the latter we suggest an efficient approximate optimization method where each iteration admits closed-form update with no line search. For several benchmark datasets mostly from the multi-label image classification, we demonstrate that our generative model with proposed estimators can often yield superior prediction performance to existing methods. (C) 2014 Elsevier Inc. All rights reserved.
Grasping and manipulating everyday objects in a goal-directed manner is an important ability of a service robot. The robot needs to reason about task requirements and ground these in the sensorimotor information. Gras...
详细信息
Grasping and manipulating everyday objects in a goal-directed manner is an important ability of a service robot. The robot needs to reason about task requirements and ground these in the sensorimotor information. Grasping and interaction with objects are challenging in real-world scenarios, where sensorimotor uncertainty is prevalent. This paper presents a probabilistic framework for the representation and modeling of robot-grasping tasks. The framework consists of Gaussian mixture models for generic data discretization, and discrete Bayesian networks for encoding the probabilistic relations among various task-relevant variables, including object and action features as well as task constraints. We evaluate the framework using a grasp database generated in a simulated environment including a human and two robot hand models. The generative modeling approach allows the prediction of grasping tasks given uncertain sensory data, as well as object and grasp selection in a task-oriented manner. Furthermore, the graphical model framework provides insights into dependencies between variables and features relevant for object grasping.
probabilistic graphical models are powerful mathematical formalisms for machine learning and reasoning under uncertainty that are widely used for cognitive computing. However, they cannot be employed efficiently for l...
详细信息
probabilistic graphical models are powerful mathematical formalisms for machine learning and reasoning under uncertainty that are widely used for cognitive computing. However, they cannot be employed efficiently for large problems (with variables in the order of 100K or larger) on conventional systems, due to inefficiencies resulting from layers of abstraction and separation of logic and memory in CMOS implementations. In this paper, we present a magnetoelectric probabilistic technology framework for implementing probabilistic reasoning functions. The technology leverages straintronic magneto-tunneling junction (S-MTJ) devices in a novel mixed-signal circuit framework for direct computations on probabilities while enabling in-memory computations with persistence. Initial evaluations of the Bayesian likelihood estimation operation occurring during Bayesian Network inference indicate up to 127 x lower area, 214 x lower active power, and 70 x lower latency compared to an equivalent 45-nm CMOS Boolean implementation.
The Libra Toolkit is a collection of algorithms for learning and inference with discrete probabilisticmodels, including Bayesian networks, Markov networks, dependency networks, and sum-product networks. Compared to o...
详细信息
The Libra Toolkit is a collection of algorithms for learning and inference with discrete probabilisticmodels, including Bayesian networks, Markov networks, dependency networks, and sum-product networks. Compared to other toolkits, Libra places a greater emphasis on learning the structure of tractable models in which exact inference is efficient. It also includes a variety of algorithms for learning graphicalmodels in which inference is potentially intractable, and for performing exact and approximate inference. Libra is released under a 2-clause BSD license to encourage broad use in academia and industry.
We present a new modelling framework for dialogue management based on the concept of probabilistic rules. probabilistic rules are defined as structured mappings between logical conditions and probabilistic effects. Th...
详细信息
We present a new modelling framework for dialogue management based on the concept of probabilistic rules. probabilistic rules are defined as structured mappings between logical conditions and probabilistic effects. They function as high-level templates for probabilistic graphical models and may include unknown parameters whose values are estimated from data using Bayesian inference. Thanks to their use of logical abstractions, probabilistic rules are able to encode the probability and utility models employed in dialogue management in a compact and human-readable form. As a consequence, they can reduce the amount of dialogue data required for parameter estimation and allow system designers to directly incorporate their expert domain knowledge into the dialogue models. Empirical results of a user evaluation in a human-robot interaction task with 37 participants show that a dialogue manager structured with probabilistic rules outperforms both purely hand-crafted and purely statistical methods on a range of subjective and objective quality metrics. The framework is implemented in a software toolkit called OpenDial, which can be used to develop various types of dialogue systems based on probabilistic rules. (C) 2015 Elsevier Ltd. All rights reserved.
In this paper we develop a formal dynamic version of Chain Event Graphs (CEGs), a particularly expressive family of discrete graphicalmodels. We demonstrate how this class links to semi-Markov models and provides a c...
详细信息
In this paper we develop a formal dynamic version of Chain Event Graphs (CEGs), a particularly expressive family of discrete graphicalmodels. We demonstrate how this class links to semi-Markov models and provides a convenient generalization of the Dynamic Bayesian Network (DBN). In particular we develop a repeating time-slice Dynamic CEG providing a useful and simpler model in this family. We demonstrate how the Dynamic CEG's graphical formulation exhibits asymmetric conditional independence statements and also how each model can be estimated in a closed form enabling fast model search over the class. The expressive power of this model class together with its estimation is illustrated throughout by a variety of examples that include the risk of childhood hospitalization and the efficacy of a flu vaccine.
暂无评论