Max Mintz

Cooperative material handling by human and robotic agents: Module development and system synthesis

Abstract In this paper we present a collaborative effort to design and implement a cooperative material handling system by a small team of human and robotic agents in an unstructured indoor environment. Our approach makes fundamental use of the human agents expertise for aspects of task planning, task monitoring and error recovery. Our system is neither fully autonomous nor fully teleoperated. It is designed to make effective use of the humans abilities within the present state of the art of autonomous systems. Our robotic agents refer to systems which are each equipped with at least one sensing modality and which possess some capability for self-orientation and/or mobility. Our robotic agents are not required to be homogeneous with respect to either capabilities or function. Our research stresses both paradigms and testbed experimentation. Theory issues include the requisite coordination principles and techniques which are fundamental to a cooperative multi-agent systems basic functioning. We have constructed an experimental distributed multi-agent architecture testbed facility. The required modular components of this testbed are currently operational and have been tested individually. Our current research focuses on the agents integration in a scenario for cooperative material handling.

A stereo confidence metric using single view imagery with comparison to five alternative approaches

Although stereo vision research has progressed remarkably, stereo systems still need a fast, accurate way to estimate confidence in their output. In the current paper, we explore using stereo performance on two different images from a single view as a confidence measure for a binocular stereo system incorporating that single view. Although it seems counterintuitive to search for correspondence in two different images from the same view, such a search gives us precise quantitative performance data. Correspondences significantly far from the same location are erroneous because there is little to no motion between the two images. Using hand-generated ground truth, we quantitatively compare this new confidence metric with five commonly used confidence metrics. We explore the performance characteristics of each metric under a variety of conditions.

Modeling and analyzing biomolecular networks

The authors argue for the need to model and analyze biological networks at molecular and cellular levels. They propose a computational toolbox for biologists. Central to their approach is the paradigm of hybrid models in which discrete events are combined with continuous differential equations to capture switching behavior.

Task-directed multisensor fusion

The authors consider the problem of task-directed information gathering. They first develop a decision-theoretic model of task-directed sensing. In this framework, sensors are modeled as noise-contaminated, uncertain measurement systems. A sensor task is modelled as consisting of a function describing the type of information required by the task, a utility function describing sensitivity to error, and a cost function describing time or resource constraints on the system. From this description, the authors develop a computational method approximating a standard Bayesian decision-making model. This algorithm, which relies on a finite-element computation, is applicable to a wide variety of sensor fusion problems. The authors describe its derivation, analyze its error properties, and indicate how it can be made robust to errors in the description of sensors and discrepancies between geometric models and sensed objects. They also present the result of applying this fusion technique to several different information gathering tasks in simulated situations and in a distributed sensing system.<<ETX>>

Refined methods for creating realistic haptic virtual textures from tool-mediated contact acceleration data

Dragging a tool across a textured object creates rich high-frequency vibrations that distinctly convey the physical interaction between the tool tip and the object surface. Varying ones scanning speed and normal force alters these vibrations, but it does not change the perceived identity of the tool or the surface. Previous research developed a promising data-driven approach to embedding this natural complexity in a haptic virtual environment: the approach centers on recording and modeling the tool contact accelerations that occur during real texture interactions at a limited set of force-speed combinations. This paper aims to optimize these prior methods of texture modeling and rendering to improve system performance and enable potentially higher levels of haptic realism. The key elements of our approach are drawn from time series analysis, speech processing, and discrete-time control. We represent each recorded texture vibration with a low-order auto-regressive moving-average (ARMA) model, and we optimize this set of models for a specific tool-surface pairing (plastic stylus and textured ABS plastic) using metrics that depend on spectral match, final prediction error, and model order. For rendering, we stably resample the texture models at the desired output rate, and we derive a new texture model at each time step using bilinear interpolation on the line spectral frequencies of the resampled models adjacent to the users current force and speed. These refined processes enable our TexturePad system to generate a stable and spectrally accurate vibration waveform in real time, moving us closer to the goal of virtual textures that are indistinguishable from their real counterparts.

Stereo depth estimation: a confidence interval approach

We describe an estimation technique which, given a measurement of the depth of a target from a wide-field-of-view (WFOV) stereo camera pair, produces a minimax risk fixed-size confidence interval estimate for the target depth. This work constitutes the first application to the computer vision domain of optimal fixed-size confidence-interval decision theory. The approach is evaluated in terms of theoretical capture probability and empirical capture frequency during actual experiments with a target on an optical bench. The method is compared to several other procedures including the Kalman Filter. The minimax approach is found to dominate all the other methods in performance. In particular for the minimax approach, a very close agreement is achieved between theoretical capture probability and empirical capture frequency. This allows performance to be accurately predicted, greatly facilitating the system design, and delineating the tasks that may be performed with a given system.

Robust fusion of location information

A sensor fusion problem for location data using statistical decision theory (SDT) is studied. The contribution of this study is the application of SDT to obtain a robust test of the hypothesis that data from different sensors is consistent and a robust procedure for combining the date which pass this preliminary consistency test. Here, robustness refers to the statistical effectiveness of the decision rules when the probability distributions of the observation noise and the a priori position information associated with the individual sensors are uncertain. Location data refers to observations of the form Z= theta +V, where V represents additive sensor noise and theta denotes the sensed parameter of interest to the observer. The paper focuses on epsilon -contamination models, which allow one to account for heavy-tailed deviations from nominal sampling distributions.<<ETX>>

Minimax rules under zero–one loss for a restricted location parameter

In this paper, we obtain minimax and near-minimax nonrandomized decision rules under zero–one loss for a restricted location parameter of an absolutely continuous distribution. Two types of rules are addressed: monotone and nonmonotone. A complete-class theorem is proved for the monotone case. This theorem extends the previous work of Zeytinoglu and Mintz (1984) to the case of 2e-MLR sampling distributions. A class of continuous monotone nondecreasing rules is defined. This class contains the monotone minimax rules developed in this paper. It is shown that each rule in this class is Bayes with respect to nondenumerably many priors. A procedure for generating these priors is presented. Nonmonotone near-minimax almost-equalizer rules are derived for problems characterized by non-2e-MLR distributions. The derivation is based on the evaluation of a distribution-dependent function Qc. The methodological importance of this function is that it is used to unify the discrete- and continuous-parameter problems, and to obtain a lower bound on the minimax risk for the non-2e-MLR case.

Statistical decision theory for mobile robotics: theory and application

In this paper we pioneer a method which, given an input of mobile robot pose measurements by a sensor-based localization algorithm, produces a minimax risk fixed-size confidence set estimate for the pose of the agent. This work constitutes the first application to the mobile robotics domain of optimal fixed-size confidence-interval decision theory. The approach is evaluated in terms of theoretical capture probability and empirical capture frequency during actual experiments with the mobile agent. The method is compared to several other procedures including the Kalman filter (minimum mean squared error estimate) and the maximum likelihood estimator (MLE). The minimax approach is found to dominate all the other methods in performance. In particular, for the minimax approach, a very close agreement is achieved between theoretical capture probability and empirical capture frequency. This allows performance to be accurately predicted, greatly facilitating the design of mobile robotic systems, and delineating the tasks that may be performed with a given system.

A confidence set approach to mobile robot localization

In this paper we pioneer a method which, given an input of mobile robot pose measurements by a sensor-based localization algorithm, produces a minimax risk fixed-size confidence set estimate for the pose of the agent. This work constitutes the first application to the mobile robotics domain of optimal fixed-size confidence-interval decision theory. The approach is evaluated in terms of theoretical capture probability and empirical capture frequency during actual experiments with the mobile agent. The method is compared to several other procedures including the Kalman filter and the maximum likelihood estimator. The minimax approach is found to dominate all the other methods in performance. In particular, for the minimax approach, a very close agreement is achieved between theoretical capture probability and empirical capture frequency. This allows performance to be accurately predicted, greatly facilitating the design of mobile robotic systems, and delineating the tasks that may be performed with a given system.