no code implementations • 26 May 2024 • Moshe Shienman, Ohad Levy-Or, Michael Kaess, Vadim Indelman
We introduce an innovative method for incremental nonparametric probabilistic inference in high-dimensional state spaces.
1 code implementation • 13 Nov 2023 • Idan Lev-Yehudi, Moran Barenboim, Vadim Indelman
Solving partially observable Markov decision processes (POMDPs) with high dimensional and continuous observations, such as camera images, is required for many real life robotics and planning problems.
no code implementations • 16 Oct 2023 • Andrey Zhitnikov, Ori Sztyglic, Vadim Indelman
Using the general theoretical results, we present three algorithms to accelerate continuous POMDP online planning with belief-dependent rewards.
1 code implementation • 19 Sep 2023 • Tom Yotam, Vadim Indelman
In both cases we show a significant speed-up in planning with performance guarantees.
no code implementations • 3 Mar 2023 • Moran Barenboim, Idan Lev-Yehudi, Vadim Indelman
To overcome this challenge, we introduce a pruning-based approach for planning with ambiguous data associations.
no code implementations • 13 Feb 2023 • Andrey Zhitnikov, Vadim Indelman
Moreover, using our proposed framework, we contribute an adaptive method to find a maximal feasible return (e. g., information gain) in terms of Value at Risk for the candidate action sequence with substantial acceleration.
no code implementations • 14 Nov 2022 • Moran Barenboim, Moshe Shienman, Vadim Indelman
Real-world problems often require reasoning about hybrid beliefs, over both discrete and continuous random variables.
no code implementations • 23 Sep 2022 • Gilad Rotman, Vadim Indelman
Moreover, we apply the dimensionality reduction for cases in which the new states are augmented to the previous, yet again without sacrificing accuracy.
no code implementations • 6 Sep 2022 • Andrey Zhitnikov, Vadim Indelman
In addition, with an arbitrary confidence parameter, we did not find any analogs to our approach.
no code implementations • 17 Jul 2022 • Moshe Shienman, Vadim Indelman
We present a computationally efficient method to solve the nonmyopic Belief Space Planning problem while reasoning about data association.
no code implementations • 10 Feb 2022 • Moshe Shienman, Vadim Indelman
Unresolved data association in ambiguous and perceptually aliased environments leads to multi-modal hypotheses on both the robot's and the environment state.
no code implementations • 14 Jan 2022 • Moran Barenboim, Vadim Indelman
Reasoning about uncertainty is vital in many real-life autonomous systems.
no code implementations • 29 Dec 2021 • Khen Elimelech, Vadim Indelman
In this work, we examine the problem of online decision making under uncertainty, which we formulate as planning in the belief space.
no code implementations • 29 May 2021 • Ori Sztyglic, Andrey Zhitnikov, Vadim Indelman
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.
no code implementations • 12 May 2021 • Andrey Zhitnikov, Vadim Indelman
On top of this extension, our key contribution is a novel framework to simplify decision making while assessing and controlling online the simplification's impact.
no code implementations • 11 May 2021 • Ori Sztyglic, Vadim Indelman
Our key contribution is a novel algorithmic approach, Simplified Information Theoretic Belief Space Planning (SITH-BSP), which aims to speed-up POMDP planning considering belief-dependent rewards, without compromising on the solution's accuracy.
no code implementations • 18 Feb 2021 • Elad I. Farhi, Vadim Indelman
We demonstrate how iX-BSP could benefit existing approximations of the general problem, introducing iML-BSP, which re-uses calculations across planning sessions under the common Maximum Likelihood assumption.
no code implementations • 19 Oct 2019 • Dmitry Kopitkov, Vadim Indelman
In contrast, in this paper we empirically explore these properties along the optimization and show that in practical applications the NTK changes in a very dramatic and meaningful way, with its top eigenfunctions aligning toward the target function learned by NN.
no code implementations • 2 Sep 2019 • Khen Elimelech, Vadim Indelman
In this work, we introduce a new and efficient solution approach for the problem of decision making under uncertainty, which can be formulated as decision making in a belief space, over a possibly high-dimensional state space.
no code implementations • 6 Aug 2019 • Elad I. Farhi, Vadim Indelman
Inference and decision making under uncertainty are key processes in every autonomous system and numerous robotic problems.
no code implementations • 5 Jun 2019 • Dmitry Kopitkov, Vadim Indelman
Our approach, rAMDL-Tree, extends our previous BSP method rAMDL, by exploiting incremental covariance calculation and performing calculation re-use between common parts of non-myopic candidate actions, such that these parts are evaluated only once, in contrast to existing approaches.
no code implementations • 25 Mar 2019 • Dmitry Kopitkov, Vadim Indelman
In our experiments we demonstrate this technique to be superior over state-of-the-art baselines in density estimation task for multimodal 20D data.
no code implementations • 27 Jul 2018 • Dmitry Kopitkov, Vadim Indelman
For example, kernel density estimation (KDE) methods require meticulous parameter search and are extremely slow at querying new points.
no code implementations • 16 Jun 2016 • Shashank Pathak, Antony Thomas, Asaf Feniger, Vadim Indelman
We develop a belief space planning (BSP) approach that advances the state of the art by incorporating reasoning about data association (DA) within planning, while considering additional sources of uncertainty.