Emily A. Doucette

Decentralized Rendezvous of Nonholonomic Robots With Sensing and Connectivity Constraints

A group of wheeled robots with nonholonomic constraints is considered to rendezvous at a common specified setpoint with a desired orientation while maintaining network connectivity and ensuring collision avoidance within the robots. Given communication and sensing constraints for each robot, only a subset of the robots are aware or informed of the global destination, and the remaining robots must move within the network connectivity constraint so that the informed robots can guide the group to the goal. The mobile robots are also required to avoid collisions with each other outside a neighborhood of the common rendezvous point. To achieve the rendezvous control objective, decentralized time-varying controllers are developed based on a navigation function framework to steer the robots to perform rendezvous while preserving network connectivity and ensuring collision avoidance. Only local sensing feedback, which includes position feedback from immediate neighbors and absolute orientation measurement, is used to navigate the robots and enables radio silence during navigation. Simulation results demonstrate the performance of the developed approach.

Human-Assisted RRT for Path Planning in Urban Environments

A human-RRT (Rapidly-exploring Random Tree) collaborative algorithm is presented for path planning in urban environments. The well-known RRT algorithm is modified for efficient planning in cluttered, yet structured urban environments. To engage the expert human knowledge in dynamic replanning of autonomous vehicles, a graphical user interface is developed that enables interaction with the automated RRT planner in real-time. The interface can be used to invoke standard planning attributes such as way areas, space constrains, and waypoints. In addition, the human can draw desired trajectories using the touch interface for the RRT planner to follow. Based on new information and evidence collected by human, state-dependent risk or penalty to grow paths based on an objective function can also be specified using the interface.

A touch interface for soft data modeling in Bayesian estimation

A novel approach for human-generated “soft information” modeling and Bayesian fusion using touch interface devices is presented. The human-generated soft information can be encoded using a combination of single, multiple, and overlapping strokes that represent arbitrary measurement likelihood functions which can be approximated using non-parametric density estimators. The proposed interface offers a flexible and natural medium to encode a large class of qualitatively distinct types of information for both positive and negative observations. The touch interface naturally provides robustness with respect to human variability in terms of psycho-physiological and environmental parameters without the need for offline training. An urban-target tracking example is provided to illustrate fusion of soft information (generated using the proposed soft sensor model) with measurements from traditional automated sensors.

Moving target acquisition through state uncertainty minimization

This work addresses the task of a mobile sensor platform searching for a moving target. We show that minimizing the entropy of the probability distribution of the target state estimate can result in a control input for the mobile sensor that acquires the target in less iterations than an exhaustive search. We also show that this approach can be used to track the target after it is acquired. We apply a particle filter framework to estimate the state of the target and propose an information-based cost function to optimize as part of a control law for the mobile sensor. We include simulation results to illustrate the performance of our approach.

Map merging of rotated, corrupted, and different scale maps using rectangular features

Integrating data from multiple cooperative robots can be important for expanding their individual capabilities. In an environmental mapping scenario, multiple ground robots map different local areas. Algorithm complexity on merging the maps to build a global map depends on the three factors: orientation, accuracy and scale of the maps. When the three factors are all unknown, the map merging becomes a challenging problem. In this paper, a new approach on merging of two maps with the three factors are unknown. The idea is to estimate the best shared-areas by means of rectangular features. The information of dimensions and connections of maximal empty rectangles allows the algorithms to match orientations and scales, also to find overlapping points. The advantage of this approach is that a map merging is accomplished without any location estimations between the robots. This paper explains the map-merging process with an example of a simple environment, and presents a result with a practical environment.

Urban target search and tracking using a UAV and unattended ground sensors

We present a framework to search for and track a target within an urban environment by fusing data from an Unmanned Aerial Vehicle and Unattended Ground Sensors. The target and UAV are restricted to a road network modeled as a directed graph with the ground sensors deployed along selected edges. The UAV is equipped with an onboard camera capable of detecting the target, and it is guided by an information-theoretic planner that uses a particle filter estimate of the target state as its input. We introduce a method to process out-of-sequence measurements that exploits the time-sparseness of the UGS readings to reduce the computational complexity. Finally, we present simulation results on real road networks that show the target tracking performance and the gains in computation time of our approach.

Curious partner: an autonomous system that proactively dialogues with human teammates

In this paper, a human-autonomy interaction approach is presented that enables autonomy to proactively dialogue with human teammates to maintain common understanding of the underlying processes. A class of human-autonomy systems where the role of the autonomy is to assist a human teammate in decision making tasks is considered. The autonomy maintains its knowledge of the processes and the environment in a Bayesian engine, and uses a Bayesian inference framework to provide decision support. Any discrepancy in the knowledge of the process between the autonomy and the human teammate may lead to inefficient decision support. The presented curious partner interaction framework uses a dialogue-based approach to resolve differences between the human and the autonomy. The dialog acts as a feedback mechanism to revise the Bayesian engine representation of the autonomy’s knowledge to establish common ground. An application to military operations is considered where a digital assistant uses the curious partner framework to provide decision support to a commander.

Passive switched system analysis of semi-autonomous systems

While autonomous capabilities have proliferated across a wide range of commercial and domestic applications, some tasks require intermittent aid from a human operator. Guaranteeing the safety of these intermittently-teleoperated systems requires stability guarantees that hold in the presence of switching. In this paper, we consider the problem of controlling a robotic vehicle using both a human controller and an autonomous controller. The strategy is to allow the human operator to switch between manual control and autonomous control as needed. The feedback loop is analyzed and shown to be stable using a notion of passivity from nonlinear system analysis. Finally, an example is provided to demonstrate the approach.

Degree of automation in command and control decision support systems

This paper investigates the effects of integrating automation into the various stages of information processing in a military command and control scenario. Command and control (C2) is an extreme decision-making paradigm characterized by high uncertainty, high risk, and severe time pressure. We introduce a principled approach to decision support system (DSS) design that specifically addresses these issues. Our approach establishes the principles of communicating confidence in sensor estimates and consequence of actions in an intuitive, timely manner. We hypothesize that automation designed to communicate confidence and/or consequence will improve task performance over systems that neglect these concepts. Toward this end, human-subjects experiments were conducted to compare the effects of displaying confidence/consequence information in a C2 target-tracking and interdiction scenario. Four variations of a decision support interface were designed, each with a distinct “degree of automation”: (i) an instantaneous sensor measurement visualization (baseline), (ii) a confidence-based visualization, (iii) a confidence- and consequence-based visualization, and (iv) a confidence- and consequence-based visualization with explicit decision recommendations. While increasing automation generally improved results, the inclusion of consequence information did not have a major effect, perhaps because the scenario was overly-simplified.

Optimal Placement for a Limited-Support Binary Sensor

We present an optimal strategy for placement of a binary sensor based on maximizing the mutual information between the distribution of possible target locations, the sensor footprint, and probability of sensor errors. The result replaces the direct computation of information gradients by a sensor coverage criterion, which can greatly reduce computation. Contributions include closed-form expressions for the optimal sensor placement and a proposed control algorithm for a mobile sensor. The approach is validated with multiple experiments using a quadrotor UAV conducting a search task.