Variable resolution decomposition for robotic navigation under a POMDP framework

Kaplow, Robert; Atrash, Amin; Pineau, Joëlle

doi:10.1109/robot.2010.5509188

Cited by 10 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The answers to questions yield an update to the relational map. We support two question types: polar questions 22 ("Is this a kitchen?") and open questions ("What room is this?").…”

Section: Dialoguementioning

confidence: 77%

“…The main challenge of decision-theoretic planning in partially observable environments is intractability. Kaplow et al [22] employed a variable resolution map to achieve scaling with a robotic wheelchair. All three of these approaches concerned path planning in a continuous space.…”

Section: Discussion Of Related Workmentioning

confidence: 99%

“…These are captured semi-automatically for quantities such as object type-room type relations. A set 22 By "polar question" we simply mean a question that can be answered with one of two options, e.g. yes or no.…”

Section: Acquiring Probabilistic Knowledgementioning

confidence: 99%

See 2 more Smart Citations

Robot task planning and explanation in open and uncertain worlds

Hanheide¹,

Gbelbecker²,

Horn³

et al. 2017

Artificial Intelligence

133

View full text Add to dashboard Cite

A long-standing goal of AI is to enable robots to plan in the face of uncertain and incomplete information, and to handle task failure intelligently. This paper shows how to achieve this. There are two central ideas. The first idea is to organize the robot's knowledge into three layers: instance knowledge at the bottom, commonsense knowledge above that, and diagnostic knowledge on top. Knowledge in a layer above can be used to modify knowledge in the layer(s) below. The second idea is that the robot should represent not just how its actions change the world, but also what it knows or believes. There are two types of knowledge effects the robot's actions can have: epistemic effects (I believe X because I saw it) and assumptions (I'll assume X to be true). By combining the knowledge layers with the models of knowledge effects, we can simultaneously solve several problems in robotics: (i) task planning and execution under uncertainty; (ii) task planning and execution in open worlds; (iii) explaining task failure; (iv) verifying those explanations. The paper describes how the ideas are implemented in a three-layer architecture on a mobile robot platform. The robot implementation was evaluated in five different experiments on object search, mapping, and room categorization.

show abstract

“…The answers to questions yield an update to the relational map. We support two question types: polar questions 22 ("Is this a kitchen?") and open questions ("What room is this?").…”

Section: Dialoguementioning

confidence: 77%

Section: Discussion Of Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Robot task planning and explanation in open and uncertain worlds

Hanheide¹,

Gbelbecker²,

Horn³

et al. 2017

Artificial Intelligence

133

View full text Add to dashboard Cite

show abstract

“…Finally, we note several recent methods to improve POMDP solution times by decreasing the size of the state space [24]- [26] and action space [27] through variable resolution decompositions. Although these decompositions are relevant to our goal of decreased computation time without sacrificing total accumulated reward, the decomposition we propose in this paper is across both the state space and time as opposed to the state space alone or the action space.…”

Section: Related Workmentioning

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

“…Probably the closest idea to AMA is found in [22], which builds a decomposition of the state space with varying resolution depending on the environment features. However, AMA uses knowledge from an approximate solution to the specific problem instance, rather than only the environment specification.…”

Section: Introductionmentioning

confidence: 99%

Automated model approximation for robotic navigation with POMDPs

Grady

Moll

Kavraki

2013

2013 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-Partially-Observable Markov Decision Processes (POMDPs) are a problem class with significant applicability to robotics when considering the uncertainty present in the real world, however, they quickly become intractable for large state and action spaces. A method to create a less complex but accurate action model approximation is proposed and evaluated using a state-of-the-art POMDP solver. We apply this general and powerful formulation to a robotic navigation task under state and sensing uncertainty. Results show that this method can provide a useful action model that yields a policy with similar overall expected reward compared to the true action model, often with significant computational savings. In some cases, our reduced complexity model can solve problems where the true model is too complex to find a policy that accomplishes the task. We conclude that this technique of building problem-dependent approximations can provide significant computational advantages and can help expand the complexity of problems that can be considered using current POMDP techniques.

show abstract

Variable resolution decomposition for robotic navigation under a POMDP framework

Cited by 10 publications

References 22 publications

Robot task planning and explanation in open and uncertain worlds

Robot task planning and explanation in open and uncertain worlds

Extending the Applicability of POMDP Solutions to Robotic Tasks

Automated model approximation for robotic navigation with POMDPs

Contact Info

Product

Resources

About