Probabilistic Loss and its Online Characterization for Simplified Decision Making Under Uncertainty

Zhitnikov, Andrey; Indelman, Vadim

doi:10.48550/arxiv.2105.05789

Cited by 2 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[6], [16], [22], or without ML assumption, e.g. [24], [27], all consider the likelihood terms η and η s to be equal, to the best of our knowledge, we are the first to consider impact of simplification on the normalization term in the myopic case.…”

Section: Simulating Future Observations Z K+1mentioning

confidence: 99%

D2A-BSP: Distilled Data Association Belief Space Planning with Performance Guarantees Under Budget Constraints

Shienman¹,

Indelman²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Unresolved data association in ambiguous and perceptually aliased environments leads to multi-modal hypotheses on both the robot's and the environment state. To avoid catastrophic results, when operating in such ambiguous environments, it is crucial to reason about data association within Belief Space Planning (BSP). However, explicitly considering all possible data associations, the number of hypotheses grows exponentially with the planning horizon and determining the optimal action sequence quickly becomes intractable. Moreover, with hard budget constraints where some non-negligible hypotheses must be pruned, achieving performance guarantees is crucial. In this work we present a computationally efficient novel approach that utilizes only a distilled subset of hypotheses to solve BSP problems while reasoning about data association. Furthermore, to provide performance guarantees, we derive error bounds with respect to the optimal solution. We then demonstrate our approach in an extremely aliased environment, where we manage to significantly reduce computation time without compromising on the quality of the solution.

show abstract

Section: Simulating Future Observations Z K+1mentioning

confidence: 99%

D2A-BSP: Distilled Data Association Belief Space Planning with Performance Guarantees Under Budget Constraints

Shienman¹,

Indelman²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Typically, approximation based planners show asymptotical guarantees, e.g., the convergence of the algorithms. Recently, the novel paradigm of simplification has appeared in literature [15,13,4]. The simplification is concerned with carefully replacing the nonessential elements of the decision making problem and quantifying the impact of this relaxation.…”

Section: Related Workmentioning

confidence: 99%

Simplified Belief-Dependent Reward MCTS Planning with Guaranteed Tree Consistency

Sztyglic,

Zhitnikov,

Indelman

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Partially Observable Markov Decision Processes (POMDPs) are notoriously hard to solve. Most advanced state-of-the-art online solvers leverage ideas of Monte Carlo Tree Search (MCTS). These solvers rapidly converge to the most promising branches of the belief tree, avoiding the suboptimal sections. Most of these algorithms are designed to utilize straightforward access to the state reward and assume the belief-dependent reward is nothing but expectation over the state reward. Thus, they are inapplicable to a more general and essential setting of belief-dependent rewards. One example of such reward is differential entropy approximated using a set of weighted particles of the belief. Such an information-theoretic reward introduces a significant computational burden. In this paper, we embed the paradigm of simplification into the MCTS algorithm. In particular, we present Simplified Information-Theoretic Particle Filter Tree (SITH-PFT), a novel variant to the MCTS algorithm that considers information-theoretic rewards but avoids the need to calculate them completely. We replace the costly calculation of informationtheoretic rewards with adaptive upper and lower bounds. These bounds are easy to calculate and tightened only by the demand of our algorithm. Crucially, we guarantee precisely the same belief tree and solution that would be obtained by MCTS, which explicitly calculates the original information-theoretic rewards. Our approach is general; namely, any converging to the reward bounds can be easily plugged-in to achieve substantial speedup without any loss in performance.Preprint. Under review.

show abstract

Probabilistic Loss and its Online Characterization for Simplified Decision Making Under Uncertainty

Cited by 2 publications

References 19 publications

D2A-BSP: Distilled Data Association Belief Space Planning with Performance Guarantees Under Budget Constraints

D2A-BSP: Distilled Data Association Belief Space Planning with Performance Guarantees Under Budget Constraints

Simplified Belief-Dependent Reward MCTS Planning with Guaranteed Tree Consistency

Contact Info

Product

Resources

About