Daniel S. Levine

Learn More
This paper describes the system architecture and core algorithms for a quadrotor helicopter that uses vision data to navigate an unknown, indoor, GPS-denied environment. Without external sensing, an estimation system that relies only on integrating inertial data will have rapidly drifting position estimates. Micro aerial vehicles (MAVs) are stringently(More)
This paper presents vehicle models and test flight results for an autonomous fixed-wing aircraft with the capability to take off, hover, transition to and from level-flight, and perch on a vertical landing platform. These maneuvers are all demonstrated in the highly space constrained environment of the Real-time indoor Autonomous Vehicle test ENvironment(More)
This paper considers the decision-making problem for a human-driven vehicle crossing a road intersection in the presence of other, potentially errant, drivers. Our approach relies on a novel threat assessment module, which combines an intention predictor based on support vector machines with an efficient threat assessor using rapidly-exploring random trees.(More)
This thesis introduces the Information-rich Rapidly-exploring Random Tree (IRRT), an extension of the RRT algorithm that embeds information collection as predicted using Fisher information matrices. The primary contribution of this trajectory generation algorithm is target-based information maximization in general (possibly heavily constrained)(More)
We consider the sensor selection problem on multivariate Gaussian distributions where only a subset of latent variables is of inferential interest. For pairs of vertices connected by a unique path in the graph, we show that there exist decompositions of nonlocal mutual information into local information measures that can be computed efficiently from the(More)
This paper introduces the Information-rich Rapidly-exploring Random Tree (IRRT), an extension of the RRT algorithm that embeds information collection as predicted using Fisher Information Matrices. The primary contribution of this algorithm is target-based information maximization in general (possibly heavily constrained) environments, with complex vehicle(More)
This paper considers the path planning problem for an autonomous vehicle in an urban environment populated with static obstacles and moving vehicles with uncertain intents. We propose a novel threat assessment module, consisting of an intention predictor and a threat assessor, which augments the host vehicle's path planner with a real-time threat value(More)
This paper considers the problem of online informative motion planning for a network of heterogeneous mobile sensing agents, each subject to dynamic constraints, environmental constraints, and sensor limitations. Previouswork has not yielded algorithms that are amenable to such general constraint characterizations. In this paper, the information-rich(More)
We consider the problem of selecting informative observations in Gaussian graphical models containing both cycles and nuisances. More specifically, we consider the subproblem of quantifying conditional mutual information measures that are nonlocal on such graphs. The ability to efficiently quantify the information content of observations is crucial for(More)
This thesis introduces the Information-rich Rapidly-exploring Random Tree (IRRT), an extension of the RRT algorithm that embeds information collection as predicted using Fisher information matrices. The primary contribution of this trajectory generation algorithm is target-based information maximization in general (possibly heavily constrained)(More)