• Corpus ID: 244477820

Analysis of Exploration vs. Exploitation in Adaptive Information Sampling

@article{Munir2021AnalysisOE,
  title={Analysis of Exploration vs. Exploitation in Adaptive Information Sampling},
  author={Aiman Munir and Ramviyas Parasuraman},
  journal={ArXiv},
  year={2021},
  volume={abs/2111.11384}
}
Adaptive information sampling approaches enable efficient selection of mobile robot’s waypoints through which accurate sensing and mapping of a physical process, such as the radiation or field intensity, can be obtained. This paper analyzes the role of exploration and exploitation in such informationtheoretic spatial sampling of the environmental processes. We use Gaussian processes to predict and estimate predictions with confidence bounds, thereby determining each point’s informativeness in… 
[PDF] Semantic Reader

Figures and Tables from this paper

References

SHOWING 1-10 OF 26 REFERENCES

Online information gathering using sampling-based planners and GPs: An information theoretic approach

This approach includes two intertwined steps: a Gaussian processes-based prediction that allows a robot to identify highly unexplored locations, and an RRT∗-based informative path planning that guides the robot towards those locations that allows an online realization of the algorithm, while eliminating the need of discretization.

Adaptive Sampling and Online Learning in Multi-Robot Sensor Coverage with Mixture of Gaussian Processes

  • Wenhao LuoK. Sycara
  • Computer Science
    2018 IEEE International Conference on Robotics and Automation (ICRA)
  • 2018
This work proposes a new approach with mixture of locally learned Gaussian Processes for collective model learning and an information-theoretic criterion for simultaneous adaptive sampling in multi-robot coverage that demonstrates a better generalization of the environment modeling and thus the improved performance of coverage without assuming the density function is known a priori.

Nonmyopic Adaptive Informative Path Planning for Multiple Robots

This paper presents a novel approach to adaptive informative path planning that plans ahead for possible observations that can be made in the future, and develops an algorithm that performs provably near-optimally in settings where the adaptivity gap is small.

Coordinating multi-robot systems through environment partitioning for adaptive informative sampling

An information rate adaptive sampling approach for tasking robots within an environment to gather sensor measurements is presented and shows efficiency gains through the use of adaptive information gain rate tasking above a naïve closest point approach.

Distributed Environmental Modeling and Adaptive Sampling for Multi-Robot Sensor Coverage

A distributed mixture of Gaussian Processes algorithm that enables robots to collaboratively learn the global density function by exchanging only model-related parameters is proposed.

Multi-robot coordination through dynamic Voronoi partitioning for informative adaptive sampling in communication-constrained environments

Simulation results show that the addition of the coordination with dynamic Voronoi partitioning results in obtaining higher quality models faster, thus creating a decentralized, multi-robot coordination approach for informative, adaptive sampling of unknown environments.

Adaptive Informative Sampling with Environment Partitioning for Heterogeneous Multi-Robot Systems

  • Yunfei ShiNing Wang K. Sycara
  • Computer Science
    2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2020
This paper proposes an environmental partitioning approach that leverages various robot capabilities by forming a uniformly defined heterogeneity cost space and combines with the mixture of Gaussian Processes model-learning framework to adaptively sample and model the environment in an efficient and scalable manner.

Online methods for radio signal mapping with mobile robots

An online model of the signal-strength map that can be used to provide the current maximum likelihood estimate of the source location is built and the Gaussian process model allows for prediction of received signal strength with confidence bounds in regions of the environment that have not been explored.

Smart radiation sensor management

This work developed and experimentally tested a robotic implementation of two Bayesian-based radiation mapping strategies in two dimensions, using a commercially available desktop mobile robot fitted with a CsI radiation sensor.

Fast radioactive hotspot localization using a UAV

A novel Hexagonal Tree (HexTree) based sampling algorithm is proposed to find an optimal tour path based on the appropriate measurement locations and gives faster convergence to the hotspot, an optimal exploration termination condition, and more informative locations while returning to the initial position than conventional random sampling based exploration and path smoothing algorithms.