Active Visual Planning for Mobile Robot Teams Using Hierarchical POMDPs

Zhang, Shiqi; Sridharan, Mohan; Washington, Christian

doi:10.1109/tro.2013.2252252

Cited by 23 publications

(31 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each scene, the scene processing (SP)-POMDP plans the processing of regions of images of the scene using available algorithms. This hierarchical decomposition supports automatic belief propagation between the levels of the hierarchy and automatic model creation at each level [28], [29]. Thus, ASP-based inference operates at the (abstract) level of rooms, and POMDPs plan at the higher resolution of cells.…”

Section: B Planning Under Uncertainty With Partially Observable Markmentioning

confidence: 99%

“…This formulation can become computationally intractable for real-time operation because the number of grid cells can increase significantly in complex domains. Our previous work [28] addressed this challenge by enabling robots to learn a convolutional policy kernel from the policy for a small region, exploiting the rotation and shift invariance properties of visual search. This kernel is convolved with larger maps to efficiently generate appropriate policies.…”

Section: B Planning Under Uncertainty With Partially Observable Markmentioning

confidence: 99%

See 1 more Smart Citation

Mixed Logical Inference and Probabilistic Planning for Robots in Unreliable Worlds

2015

Self Cite

View full text Add to dashboard Cite

Deployment of robots in practical domains poses key knowledge representation and reasoning challenges. Robots need to represent and reason with incomplete domain knowledge, acquiring and using sensor inputs based on need and availability. This paper presents an architecture that exploits the complementary strengths of declarative programming and probabilistic graphical models as a step toward addressing these challenges. Answer Set Prolog (ASP), a declarative language, is used to represent, and perform inference with, incomplete domain knowledge, including default information that holds in all but a few exceptional situations. A hierarchy of partially observable Markov decision processes (POMDPs) probabilistically models the uncertainty in sensor input processing and navigation. Nonmonotonic logical inference in ASP is used to generate a multinomial prior for probabilistic state estimation with the hierarchy of POMDPs. It is also used with historical data to construct a beta (meta) density model of priors for metareasoning and early termination of trials when appropriate. Robots equipped with this architecture automatically tailor sensor input processing and navigation to tasks at hand, revising existing knowledge using information extracted from sensor inputs. The architecture is empirically evaluated in simulation and on a mobile robot visually localizing objects in indoor domains.

show abstract

Section: B Planning Under Uncertainty With Partially Observable Markmentioning

confidence: 99%

Section: B Planning Under Uncertainty With Partially Observable Markmentioning

confidence: 99%

Mixed Logical Inference and Probabilistic Planning for Robots in Unreliable Worlds

2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…POMDPs form a general and powerful mathematical basis for planning under uncertainty, and their use in mobile robotic applications has increased [13,14,55,57,62]. POMDPs provide a comprehensive approach for modeling the interaction of an active sensor with its environment.…”

Section: A Decision-theoretic Approachmentioning

confidence: 99%

“…Work on active sensing using POMDPs includes collaboration between mobile robots to detect static objects [62] and combining a POMDP approach with information-theoretic heuristics to reduce uncertainty on goal position and probability of collision in robot navigation [12]. Finally, Spaan and Lima [52] consider objectives such as maximizing coverage or improving localization uncertainty when dynamically selecting a subset of image streams to be processed simultaneously.…”

Section: Active Sensingmentioning

confidence: 99%

Decision-theoretic planning under uncertainty with information rewards for active cooperative perception

Spaan

Veiga

Lima

2014

Auton Agent Multi-Agent Syst

View full text Add to dashboard Cite

Partially observable Markov decision processes (POMDPs) provide a principled framework for modeling an agent's decision-making problem when the agent needs to consider noisy state estimates. POMDP policies take into account an action's influence on the environment as well as the potential information gain. This is a crucial feature for robotic agents which generally have to consider the effect of actions on sensing. However, building POMDP models which reward information gain directly is not straightforward, but is important in domains such as robot-assisted surveillance in which the value of information is hard to quantify. Common techniques for uncertainty reduction such as expected entropy minimization lead to non-standard POMDPs that are hard to solve. We present the POMDP with Information Rewards (POMDP-IR) modeling framework, which rewards an agent for reaching a certain level of belief regarding a state feature. By remaining in the standard POMDP setting we can exploit many known results as well as successful approximate algorithms. We demonstrate our ideas in a toy problem as well as in real robot-assisted surveillance, showcasing their use for active cooperative perception scenarios. Finally, our experiments show that the POMDP-IR framework compares favorably with a related approach on benchmark domains.

show abstract

“…The optimal action policy consists of the optimal action for any possible sequence of observations, such that the expected total reward is maximized under the POMDPs model of sensing and action uncertainty. POMDPs have been established as a tool to solve a variety of tasks in robot soccer [2], household robotics [3], coastal survey [4], and even nursing assistance [5].…”

mentioning

confidence: 99%

Extending the Applicability of POMDP Solutions to Robotic Tasks

2015

View full text Add to dashboard Cite

Abstract-Partially-Observable Markov Decision Processes (POMDPs) are used in many robotic task classes from soccer to household chores. Determining an approximately optimal action policy for POMDPs is PSPACE-complete, and the exponential growth of computation time prohibits solving large tasks. This paper describes two techniques to extend the range of robotic tasks that can be solved using a POMDP. Our first technique reduces the motion constraints of a robot, and then uses state-of-the-art robotic motion planning techniques to respect the true motion constraints at runtime. We then propose a novel task decomposition that can be applied to some indoor robotic tasks. This decomposition transforms a long time horizon task into a set of shorter tasks.We empirically demonstrate the performance gain provided by these two techniques through simulated execution in a variety of environments. Comparing a direct formulation of a POMDP to solving our proposed reductions, we conclude that the techniques proposed in this paper can provide significant enhancement to current POMDP solution techniques, extending the POMDP instances that can be solved to include large, continuous-state robotic tasks.

show abstract

Active Visual Planning for Mobile Robot Teams Using Hierarchical POMDPs

Cited by 23 publications

References 15 publications

Mixed Logical Inference and Probabilistic Planning for Robots in Unreliable Worlds

Mixed Logical Inference and Probabilistic Planning for Robots in Unreliable Worlds

Decision-theoretic planning under uncertainty with information rewards for active cooperative perception

Extending the Applicability of POMDP Solutions to Robotic Tasks

Contact Info

Product

Resources

About