Coordinated guidance of autonomous uavs via nominal belief-state optimization

Miller, Scott; Harris, Zachary A.; Chong, Edwin K. P.

doi:10.1109/acc.2009.5159963

Cited by 34 publications

(28 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al. [4] and the work of Erez and Smart [5]. Both approaches plan in belief space using extended Kalman filter dynamics that incorporate an assumption that observations will be consistent with a maximum likelihood state.…”

Section: A Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Belief space planning assuming maximum likelihood observations

Platt¹,

Tedrake²,

Kaelbling³

et al. 2010

Robotics: Science and Systems VI

275

278

View full text Add to dashboard Cite

Abstract-We cast the partially observable control problem as a fully observable underactuated stochastic control problem in belief space and apply standard planning and control techniques. One of the difficulties of belief space planning is modeling the stochastic dynamics resulting from unknown future observations. The core of our proposal is to define deterministic beliefsystem dynamics based on an assumption that the maximum likelihood observation (calculated just prior to the observation) is always obtained. The stochastic effects of future observations are modeled as Gaussian noise. Given this model of the dynamics, two planning and control methods are applied. In the first, linear quadratic regulation (LQR) is applied to generate policies in the belief space. This approach is shown to be optimal for linearGaussian systems. In the second, a planner is used to find locally optimal plans in the belief space. We propose a replanning approach that is shown to converge to the belief space goal in a finite number of replanning steps. These approaches are characterized in the context of a simple nonlinear manipulation problem where a planar robot simultaneously locates and grasps an object.

show abstract

Section: A Related Workmentioning

confidence: 99%

“…In order to apply these tools, this paper defines nominal belief space dynamics based on an assumption that all future observations will obtain their maximum likelihood values (this assumption is also made in [4,5]). During execution, the system tracks the true belief based on the observations actually obtained.…”

Section: Introductionmentioning

confidence: 99%

Belief space planning assuming maximum likelihood observations

Platt¹,

Tedrake²,

Kaelbling³

et al. 2010

Robotics: Science and Systems VI

275

278

View full text Add to dashboard Cite

show abstract

“…Note that the dimensionality of Problem 1 is nklinear in the dimensionality of the underlying state space with a constant equal to the number of samples. This compares favorably with the approaches in [6], [7], [8] that must solve planning problems in n 2 -dimensional spaces (number of entries in the covariance matrix).…”

Section: A Creating Plansmentioning

confidence: 80%

“…Most of this work assumes that belief state can be accurately described by a Gaussian distribution. For example, in prior work, we and others have explored approaches to planning in belief space based on assuming that belief state can always be described accurately as a Gaussian distribution [6], [7], [8]. Another recent class of approaches avoids the complexity of belief space planning by evaluating a large number of candidate trajectories in This work was performed in the Computer Science and Artificial Intelligence Laboratory at MIT.…”

Section: Introductionmentioning

confidence: 99%

Non-Gaussian belief space planning: Correctness and complexity

Platt

Kaelbling

Lozano-Pérez

et al. 2012

2012 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-We consider the partially observable control problem where it is potentially necessary to perform complex information-gathering operations in order to localize state. One approach to solving these problems is to create plans in belief-space, the space of probability distributions over the underlying state of the system. The belief-space plan encodes a strategy for performing a task while gaining information as necessary. Unlike most approaches in the literature which rely upon representing belief state as a Gaussian distribution, we have recently proposed an approach to non-Gaussian belief space planning based on solving a non-linear optimization problem defined in terms of a set of state samples [1]. In this paper, we show that even though our approach makes optimistic assumptions about the content of future observations for planning purposes, all low-cost plans are guaranteed to gain information in a specific way under certain conditions. We show that eventually, the algorithm is guaranteed to localize the true state of the system and to reach a goal region with high probability. Although the computational complexity of the algorithm is dominated by the number of samples used to define the optimization problem, our convergence guarantee holds with as few as two samples. Moreover, we show empirically that it is unnecessary to use large numbers of samples in order to obtain good performance.

show abstract

“…He and Chong [13] solve a sensor management problem by applying a roll-out approach based on a particle filter. Miller et al [14] propose a POMDP approximation based on a Gaussian target representation and the use of nominal state trajectories in the planning. They are applying the method to a UAV guidance problem for multiple target tracking.…”

Section: Background and Literature Surveymentioning

confidence: 99%

Road Target Search and Tracking with Gimballed Vision Sensor on an Unmanned Aerial Vehicle

et al. 2012

View full text Add to dashboard Cite

This article considers a sensor management problem where a number of road bounded vehicles are monitored by an unmanned aerial vehicle (UAV) with a gimballed vision sensor. The problem is to keep track of all discovered targets and simultaneously search for new targets by controlling the pointing direction of the vision sensor and the motion of the UAV. A planner based on a state-machine is proposed with three different modes; target tracking, known target search, and new target search. A high-level decision maker chooses among these sub-tasks to obtain an overall situational awareness. A utility measure for evaluating the combined search and target tracking performance is also proposed. By using this measure it is possible to evaluate and compare the rewards of updating known targets versus searching for new targets in the same framework. The targets are assumed to be road bounded and the road network information is used both to improve the tracking and sensor management performance. The tracking and search are based on flexible target density representations provided by particle mixtures and deterministic grids.

show abstract

Coordinated guidance of autonomous uavs via nominal belief-state optimization

Cited by 34 publications

References 12 publications

Belief space planning assuming maximum likelihood observations

Belief space planning assuming maximum likelihood observations

Non-Gaussian belief space planning: Correctness and complexity

Road Target Search and Tracking with Gimballed Vision Sensor on an Unmanned Aerial Vehicle

Contact Info

Product

Resources

About