Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. We show how to extract and label a person’s activities and significant places from traces of GPS data. In contrast to existing techniques, our approach simultaneously detects and classifies the significant locations of a person and takes the high-level context into account. Our system uses relational Markov networks to represent the hierarchical activity model that encodes the complex relations among GPS readings, activities and significant places. We apply FFT-based message passing to perform efficient summation over large numbers of nodes in the networks. We present experiments that show significant improvements over existing techniques. 1

Abstract — Indoor environments can typically be divided into places with different functionalities like corridors, kitchens, offices, or seminar rooms. The ability to learn such semantic categories from sensor data enables a mobile robot to extend the representation of the environment facilitating the interaction with humans. As an example, natural language terms like “corridor” or “room ” can be used to communicate the position of the robot in a map in a more intuitive way. In this work, we first propose an approach based on supervised learning to classify the pose of a mobile robot into semantic classes. Our method uses AdaBoost to boost simple features extracted from range data and vision into a strong classifier. We present two main applications of this approach. Firstly, we show how our approach can be utilized by a moving robot for an online classification of the poses traversed along its path using a hidden Markov model. Secondly, we introduce an approach to learn topological maps from geometric maps by applying our semantic classification procedure in combination with a probabilistic relaxation procedure. We finally show how to apply associative Markov networks (AMNs) together with AdaBoost for classifying complete geometric maps. Experimental results obtained in simulation and with real robots demonstrate the effectiveness of our approach in various indoor environments. I.

The ability to build maps of indoor environments is extremely important for autonomous mobile robots. In this paper we introduce Voronoi random fields (VRFs), a novel technique for mapping the topological structure of indoor environments. Our maps describe environments in terms of their spatial layout along with information about the different places and their connectivity. To build these maps, we extract a Voronoi graph from an occupancy grid map generated with a laser range-finder, and then represent each point on the Voronoi graph as a node of a conditional random field, which is a discriminatively trained graphical model. The resulting VRF estimates the label of each node, integrating features from both the map and the Voronoi topology. The labels provide a segmentation of an environment, with the different segments corresponding to rooms, hallways, or doorways. Experiments using different maps show that our technique is able to label unknown environments based on parameters learned from other environments. 1

Markov logic networks (MLNs) combine first-order logic and Markov networks, allowing us to handle the complexity and uncertainty of real-world problems in a single consistent framework. However, in MLNs all variables and features are discrete, while most real-world applications also contain continuous ones. In this paper we introduce hybrid MLNs, in which continuous properties (e.g., the distance between two objects) and functions over them can appear as features. Hybrid MLNs have all distributions in the exponential family as special cases (e.g., multivariate Gaussians), and allow much more compact modeling of non-i.i.d. data than propositional representations like hybrid Bayesian networks. We also introduce inference algorithms for hybrid MLNs, by extending the MaxWalkSAT and MC-SAT algorithms to continuous domains. Experiments in a mobile robot mapping domain—involving joint classification, clustering and regression—illustrate the power of hybrid MLNs as a modeling language, and the accuracy and efficiency of the inference algorithms.

In this paper, we present an algorithm to identify different types of objects from 2D and 3D laser range data. Our method is a combination of an instance-based feature extraction similar to the Nearest-Neighbor classifier (NN) and a collective classification method that utilizes associative Markov networks (AMNs). Compared to previous approaches, we transform the feature vectors so that they are better separable by linear hyperplanes, which are learned by the AMN classifier. We present results of extensive experiments in which we evaluate the performance of our algorithm on several recorded indoor scenes and compare it to the standard AMN approach as well as the NN classifier. The classification rate obtained with our algorithm substantially exceeds those of the AMN and the NN. 1

Relational Continuous Models (RCMs) represent joint probability densities over attributes of objects, when the attributes have continuous domains. With relational representations, they can model joint probability distributions over large numbers of variables compactly in a natural way. This paper presents a new exact lifted inference algorithm for RCMs, thus it scales up to large models of real world applications. The algorithm applies to Relational Pairwise Models which are (relational) products of potentials of arity 2. Our algorithm is unique in two ways. First, it substantially improves the efficiency of lifted inference with variables of continuous domains. When a relational model has Gaussian potentials, it takes only linear-time compared to cubic time of previous methods. Second, it is the first exact inference algorithm which handles RCMs in a lifted way. The algorithm is illustrated over an example from econometrics. Experimental results show that our algorithm outperforms both a groundlevel inference algorithm and an algorithm built with previously-known lifted methods. 1

Abstract. This paper presents a general probabilistic framework for multisensor multi-class object recognition based on Conditional Random Fields (CRFs) trained with virtual evidence boosting. The learnt representation models spatial and temporal relationships and is able to integrate arbitrary sensor information by automatically extracting features from data. We demonstrate the benefits of modelling spatial and temporal relationships for the problem of detecting seven classes of objects using laser and vision data in outdoor environments. Additionally, we show how this framework can be used with partially labeled data, thereby significantly reducing the burden of manual data annotation. 1

Abstract — This paper introduces a probabilistic, two-stage classification framework for the semantic annotation of urban maps as provided by a mobile robot. During the first stage, local scene properties are considered using a probabilistic bagof-words classifier. The second stage incorporates contextual information across a given scene via a Markov Random Field (MRF). Our approach is driven by data from an onboard camera and 3D laser scanner and uses a combination of appearancebased and geometric features. By framing the classification exercise probabilistically we are able to execute an informationtheoretic bail-out policy when evaluating appearance-based classconditional likelihoods. This efficiency, combined with low order MRFs resulting from our two-stage approach, allows us to generate scene labels at speeds suitable for online deployment and use. We demonstrate and analyze the performance of our technique on data gathered over almost 17 km of track through a city. I.

Meaningfully managing the relationship between representations and the entities they represent remains a challenge in robotics known as grounding. Useful insights can be found by approaching robotic systems development specifically with the grounding and symbol grounding problem in mind. In particular, Semantic Web technologies turn out to be not merely applicable to web-based software agents, but can also provide a powerful extension to existing proposals for grounded robotic systems development. Given the interoperability and openness of the Semantic Web, such technologies can increase the ability for a robot to introspect, communicate and be inspected- benefits that ultimately lead to more grounded systems with open-ended intelligent behaviour.

We address the problem of semantic mapping using mobile robots. We focus on the problem of mapping activity as a precursor to automatically classifying, modeling and ultimately understanding the usage of space in a typical urban outdoor environment. We propose and compare two methods for activity mapping- one based on hidden Markov models and the other based on support vector machines. Both approaches estimate high level properties of space based on low level sensor data using supervised learning to associate features to desired classification patterns. 1