Detail publikace

SLAM++-A Highly Efficient and Temporally Scalable Incremental SLAM Framework

Originální název

SLAM++-A Highly Efficient and Temporally Scalable Incremental SLAM Framework

Anglický název

SLAM++-A Highly Efficient and Temporally Scalable Incremental SLAM Framework

Jazyk

en

Originální abstrakt

The most common way to deal with the uncertainty present in noisy sensorial perception and action is to model the problem with a probabilistic framework. Maximum likelihood estimation (MLE) is a well-known estimation method used in many robotic and computer vision applications. Under Gaussian assumption, the MLE converts to a nonlinear least squares (NLS) problem. Efficient solutions to NLS exist and they are based on iteratively solving sparse linear systems until convergence. In general, the existing solutions provide only an estimation of the mean state vector, the resulting covariance being computationally too expensive to recover. Nevertheless, in many simultaneous localisation and mapping (SLAM) applications, knowing only the mean vector is not enough. Data association, obtaining reduced state representations, active decisions and next best view are only a few of the applications that require fast state covariance recovery. Furthermore, computer vision and robotic applications are in general performed online. In this case, the state is updated and recomputed every step and its size is continuously growing, therefore, the estimation process may become highly computationally demanding. This paper introduces a general framework for incremental MLE called SLAM++, which fully benefits from the incremental nature of the online applications, and provides efficient estimation of both the mean and the covariance of the estimate. Based on that, we propose a strategy for maintaining a sparse and scalable state representation for large scale mapping. SLAM++ differs from existing implementations by performing all the matrix operations by blocks. This led to extremely fast matrix manipulation and arithmetic operations used in NLS. Even though this paper tests SLAM++ efficiency on SLAM problems, its applicability remains general.

Anglický abstrakt

The most common way to deal with the uncertainty present in noisy sensorial perception and action is to model the problem with a probabilistic framework. Maximum likelihood estimation (MLE) is a well-known estimation method used in many robotic and computer vision applications. Under Gaussian assumption, the MLE converts to a nonlinear least squares (NLS) problem. Efficient solutions to NLS exist and they are based on iteratively solving sparse linear systems until convergence. In general, the existing solutions provide only an estimation of the mean state vector, the resulting covariance being computationally too expensive to recover. Nevertheless, in many simultaneous localisation and mapping (SLAM) applications, knowing only the mean vector is not enough. Data association, obtaining reduced state representations, active decisions and next best view are only a few of the applications that require fast state covariance recovery. Furthermore, computer vision and robotic applications are in general performed online. In this case, the state is updated and recomputed every step and its size is continuously growing, therefore, the estimation process may become highly computationally demanding. This paper introduces a general framework for incremental MLE called SLAM++, which fully benefits from the incremental nature of the online applications, and provides efficient estimation of both the mean and the covariance of the estimate. Based on that, we propose a strategy for maintaining a sparse and scalable state representation for large scale mapping. SLAM++ differs from existing implementations by performing all the matrix operations by blocks. This led to extremely fast matrix manipulation and arithmetic operations used in NLS. Even though this paper tests SLAM++ efficiency on SLAM problems, its applicability remains general.

BibTex


@article{BUT130989,
  author="Viorela Simona {Ila} and Lukáš {Polok} and Marek {Šolony} and Pavel {Svoboda}",
  title="SLAM++-A Highly Efficient and Temporally Scalable Incremental SLAM Framework",
  annote="The most common way to deal with the uncertainty present in noisy sensorial
perception and action is to model the problem with a probabilistic framework.
Maximum likelihood estimation (MLE) is a well-known estimation method used in
many robotic and computer vision applications. Under Gaussian assumption, the MLE
converts to a nonlinear least squares (NLS) problem.

Efficient solutions to NLS exist and they are based on iteratively solving sparse
linear systems until convergence. In general, the existing solutions provide only
an estimation of the mean state vector, the resulting covariance being
computationally too expensive to recover. Nevertheless, in many simultaneous
localisation and mapping (SLAM) applications, knowing only the mean vector is not
enough. Data association, obtaining reduced state representations, active
decisions and next best view are only a few of the applications that require fast
state covariance recovery. Furthermore, computer vision and robotic applications
are in general performed online. In this case, the state is updated and
recomputed every step and its size is continuously growing, therefore, the
estimation process may become highly computationally demanding.

This paper introduces a general framework for incremental MLE called SLAM++,
which fully benefits from the incremental nature of the online applications, and
provides efficient estimation of both the mean and the covariance of the
estimate. Based on that, we propose a strategy for maintaining a sparse and
scalable state representation for large scale mapping. SLAM++ differs from
existing implementations by performing all the matrix operations by blocks. This
led to extremely fast matrix manipulation and arithmetic operations used in NLS.
Even though this paper tests SLAM++ efficiency on SLAM problems, its
applicability remains general.",
  address="NEUVEDEN",
  booktitle="Online First",
  chapter="130989",
  doi="10.1177/0278364917691110",
  edition="NEUVEDEN",
  howpublished="online",
  institution="NEUVEDEN",
  number="1",
  volume="2017",
  year="2017",
  month="february",
  pages="210--230",
  publisher="NEUVEDEN",
  type="journal article in Web of Science"
}