Douglas L. Vail

Conditional random fields for activity recognition

Activity recognition is a key component for creating intelligent, multi-agent systems. Intrinsically, activity recognition is a temporal classification problem. In this paper, we compare two models for temporal classification: hidden Markov models (HMMs), which have long been applied to the activity recognition problem, and conditional random fields (CRFs). CRFs are discriminative models for labeling sequences. They condition on the entire observation sequence, which avoids the need for independence assumptions between observations. Conditioning on the observations vastly expands the set of features that can be incorporated into the model without violating its assumptions. Using data from a simulated robot tag domain, chosen because it is multi-agent and produces complex interactions between observations, we explore the differences in performance between the discriminatively trained CRF and the generative HMM. Additionally, we examine the effect of incorporating features which violate independence assumptions between observations; such features are typically necessary for high classification accuracy. We find that the discriminatively trained CRF performs as well as or better than an HMM even when the model features do not violate the independence assumptions of the HMM. In cases where features depend on observations from many time steps, we confirm that CRFs are robust against any degradation in performance.

Learning from accelerometer data on a legged robot

Abstract Robot calibration for an environment is a tedious task that usually involves extensive, if not total, human intervention. However, robots have sensing mechanisms, in particular accelerometers, which could in principle be used to detect specific environmental states. In this paper, we contribute several approaches for robots to detect their state using accelerometer data. In particular, we use accelerometer data from a four-legged AIBO robot. We present a surface detector that identifies the surface under the robot as it walks and the features used for this classification. Additionally, since AIBO robots can easily become entangled on obstacles or other robots in multi-robot environments, such as robot soccer, we contribute results that show effective detection of robot state, again based on accelerometer data. Finally, we examine a third, more challenging problem: predicting gait velocity from accelerometer data. We use a k-nearest neighbor approach with a library of labeled accelerometer data for velocity prediction. Our work, as reported in this paper, demonstrates the general use of robot accelerometer data for automatically detecting robot or environment state without tedious manual calibration.

Feature selection in conditional random fields for activity recognition

Temporal classification, such as activity recognition, is a key component for creating intelligent robot systems. In the case of robots, classification algorithms must robustly incorporate complex, non-independent features extracted from streams of sensor data. Conditional random fields are discriminatively trained temporal models that can easily incorporate such features. However, robots have few computational resources to spare for computing a large number of features from high bandwidth sensor data, which creates opportunities for feature selection. Creating models that contain only the most relevant features reduces the computational burden of temporal classification. In this paper, we show that lscr1 regularization is an effective technique for feature selection in conditional random fields. We present results from a multi-robot tag domain with data from both real and simulated robots that compare the classification accuracy of models trained with lscr1 regularization, which simultaneously smoothes the model and selects features; lscr2 regularization, which smoothes to avoid over-fitting, but performs no feature selection; and models trained with no smoothing.

A real-time world model for multi-robot teams with high-latency communication

In this paper, we present in detail our approach to constructing a world model in a multi-robot team. We introduce two separate world models, namely an individual world model that stores one robots state, and a shared world model that stores the state of the team. We present procedures to effectively merge information in these two world models in real-time. We overcome the problem of high communication latency by using shared information on an as-needed basis. The success of our world model approach is validated by experimentation in the robot soccer domain. The results show that a team using a world model that incorporates shared information is more successful at tracking a dynamic object in its environment than a team that does not use shared information.

CMRoboBits: Creating an Intelligent AIBO Robot

CMRoboBits is a course offered at Carnegie Mellon University that introduces students to all the concepts needed to create a complete intelligent robot. In particular, the course focuses on the areas of perception, cognition, and action by using the Sony AIBO robot as the focus for the programming assignments. This course shows how an AIBO and its software resources make it possible for students to investigate and work with an unusually broad variety of AI topics within a single semester. While material presented in this article describes using AIBOs as the primary platform, the concepts presented in the course are not unique to the AIBO and can be applied on different kinds of robotic hardware.