Lin Liao

IJCAI Conference 2007 Conference Paper

• Lin Liao
• Tanzeem Choudhury
• Dieter Fox
• Henry Kautz

While conditional random fields (CRFs) have been applied successfully in a variety of domains, their training remains a challenging task. In this paper, we introduce a novel training method for CRFs, called virtual evidence boosting, which simultaneously performs feature selection and parameter estimation. To achieve this, we extend standard boosting to handle virtual evidence, where an observation can be specified as a distribution rather than a single number. This extension allows us to develop a unified framework for learning both local and compatibility features in CRFs. In experiments on synthetic data as well as real activity classification problems, our new training algorithm outperforms other training approaches including maximum likelihood, maximum pseudo-likelihood, and the most recent boosted random fields.

ICRA Conference 2007 Conference Paper

CRF-Filters: Discriminative Particle Filters for Sequential State Estimation

• Benson Limketkai
• Dieter Fox
• Lin Liao

Particle filters have been applied with great success to various state estimation problems in robotics. However, particle filters often require extensive parameter tweaking in order to work well in practice. This is based on two observations. First, particle filters typically rely on independence assumptions such as "the beams in a laser scan are independent given the robot's location in a map". Second, even when the noise parameters of the dynamical system are perfectly known, the sample-based approximation can result in poor filter performance. In this paper we introduce CRF-filters, a novel variant of particle filtering for sequential state estimation. CRF-filters are based on conditional random fields, which are discriminative models that can handle arbitrary dependencies between observations. We show how to learn the parameters of CRF-filters based on labeled training data. Experiments using a robot equipped with a laser range-finder demonstrate that our technique is able to learn parameters of the robot's motion and sensor models that result in good localization performance, without the need of additional parameter tweaking.

AIJ Journal 2007 Journal Article

Learning and inferring transportation routines

• Lin Liao
• Donald J. Patterson
• Dieter Fox
• Henry Kautz

This paper introduces a hierarchical Markov model that can learn and infer a user's daily movements through an urban community. The model uses multiple levels of abstraction in order to bridge the gap between raw GPS sensor measurements and high level information such as a user's destination and mode of transportation. To achieve efficient inference, we apply Rao–Blackwellized particle filters at multiple levels of the model hierarchy. Locations such as bus stops and parking lots, where the user frequently changes mode of transportation, are learned from GPS data logs without manual labeling of training data. We experimentally demonstrate how to accurately detect novel behavior or user errors (e. g. taking a wrong bus) by explicitly modeling activities in the context of the user's historical data. Finally, we discuss an application called “Opportunity Knocks” that employs our techniques to help cognitively-impaired people use public transportation safely.

NeurIPS Conference 2005 Conference Paper

Location-based activity recognition

• Lin Liao
• Dieter Fox
• Henry Kautz

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 highlevel 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.

IJCAI Conference 2005 Conference Paper

Location-Based Activity Recognition using Relational Markov Networks

• Lin Liao
• Dieter Fox
• Henry

In this paper we define a general framework for activity recognition by building upon and extending Relational Markov Networks. Using the example of activity recognition from location data, we show that our model can represent a variety of features including temporal information such as time of day, spatial information extracted from geographic databases, and global constraints such as the number of homes or workplaces of a person. We develop an efficient inference and learning technique based on MCMC. Using GPS location data collected by multiple people we show that the technique can accurately label a person’s activity locations. Furthermore, we show that it is possible to learn good models from less data by using priors extracted from other people’s data.

UAI Conference 2005 Conference Paper

Prediction, Expectation, and Surprise: Methods, Designs, and Study of a Deployed Traffic Forecasting Service

• Eric Horvitz
• Johnson Apacible
• Raman Sarin
• Lin Liao

We present research on developing models that forecast traffic flow and congestion in the Greater Seattle area. The research has led to the deployment of a service named JamBayes, that is being actively used by over 2,500 users via smartphones and desktop versions of the system. We review the modeling effort and describe experiments probing the predictive accuracy of the models. Finally, we present research on building models that can identify current and future surprises, via efforts on modeling and forecasting unexpected situations.

IJCAI Conference 2005 Conference Paper

Relational Object Maps for Mobile Robots

• Benson Limketkai
• Lin Liao
• Dieter

Mobile robot map building is the task of generating a model of an environment from sensor data. Most existing approaches to mobile robot mapping either build topological representations or generate accurate, metric maps of an environment. In this paper we introduce relational object maps, a novel approach to building metric maps that represent individual objects such as doors or walls. We show how to extend relational Markov networks in order to reason about a hierarchy of objects and the spatial relationships between them. Markov chain Monte Carlo is used for efficient inference and to learn the parameters of the model. We show that the spatial constraints modeled by our mapping technique yield drastic improvements for labeling line segments extracted from laser range-finders.

AAAI Conference 2004 Conference Paper

Learning and Inferring Transportation Routines

• Lin Liao

This paper introduces a hierarchical Markov model that can learn and infer a user’s daily movements through the community. The model uses multiple levels of abstraction in order to bridge the gap between raw GPS sensor measurements and high level information such as a user’s mode of transportation or her goal. We apply Rao-Blackwellised particle filters for efficient inference both at the low level and at the higher levels of the hierarchy. Significant locations such as goals or locations where the user frequently changes mode of transportation are learned from GPS data logs without requiring any manual labeling. We show how to detect abnormal behaviors (e. g. taking a wrong bus) by concurrently tracking his activities with a trained and a prior model. Experiments show that our model is able to accurately predict the goals of a person and to recognize situations in which the user performs unknown activities.

IROS Conference 2003 Conference Paper

Voronoi tracking: location estimation using sparse and noisy sensor data

• Lin Liao
• Dieter Fox
• Jeffrey Hightower
• Henry A. Kautz
• Dirk Schulz 0001

Tracking the activity of people in indoor environments has gained considerable attention in the robotics community over the last years. Most of the existing approaches are based on sensors, which allow to accurately determining the locations of people but do not provide means to distinguish between different persons. In this paper we propose a novel approach to tracking moving objects and their identity using noisy, sparse information collected by id-sensors such as infrared and ultrasound badge systems. The key idea of our approach is to use particle filters to estimate the locations of people on the Voronoi graph of the environment. By restricting particles to a graph, we make use of the inherent structure of indoor environments. The approach has two key advantages. First, it is by far more efficient and robust than unconstrained particle filters. Second, the Voronoi graph provides a natural discretization of human motion, which allows us to apply unsupervised learning techniques to derive typical motion patterns of the people in the environment. Experiments using a robot to collect ground-truth data indicate the superior performance of Voronoi tracking. Furthermore, we demonstrate that EM-based learning of behavior patterns increases the tracking performance and provides valuable information for high-level behavior recognition.