Hilbert maps: Scalable continuous occupancy mapping with stochastic gradient descent

  title={Hilbert maps: Scalable continuous occupancy mapping with stochastic gradient descent},
  author={Fabio Tozeto Ramos and Lionel Ott},
  journal={The International Journal of Robotics Research},
  pages={1717 - 1730}
  • F. Ramos, Lionel Ott
  • Published 13 July 2015
  • Computer Science
  • The International Journal of Robotics Research
The vast amount of data robots can capture today motivates the development of fast and scalable statistical tools to model the space the robot operates in. We devise a new technique for environment representation through continuous occupancy mapping that improves on the popular occupancy grip maps in two fundamental aspects: (1) it does not assume an a priori discrimination of the world into grid cells and therefore can provide maps at an arbitrary resolution; (2) it captures spatial… 

Figures and Tables from this paper

Gaussian processes autonomous mapping and exploration for range-sensing mobile robots

A Gaussian processes (GPs) occupancy mapping technique is developed that is computationally tractable for online map building due to its incremental formulation and provides a continuous model of uncertainty over the map spatial coordinates.

Gaussian processes for information-theoretic robotic mapping and exploration

A framework for autonomous robotic mapping, exploration, and planning that uses Gaussian Processes to model high-dimensional dense maps and solve the problem of infinite-horizon planning with imperfect state information is proposed.

Building Continuous Occupancy Maps With Moving Robots

This work provides a theoretical analysis to compare and contrast the two major branches of Bayesian continuous occupancy mapping techniques---Gaussian process occupancy maps and Bayesian Hilbert maps---considering the fact that both utilize kernel functions to operate in a rich high-dimensional implicit feature space and use variational inference to learn parameters.

Spatio-Temporal Hilbert Maps for Continuous Occupancy Representation in Dynamic Environments

This work proposes a method to propagate motion uncertainty into the kernel using a hierarchical model that can directly predict the occupancy state of the map in the future from past observations, being a valuable tool for robot trajectory planning under uncertainty.

Autonomous Navigation in Unknown Environments with Sparse Bayesian Kernel-based Occupancy Mapping

This paper provides an online training algorithm, updating the sparse Bayesian map incrementally from streaming range data, and an efficient collision-checking method for general curves, representing potential robot trajectories, and the effectiveness of the mapping and collision checking algorithms is evaluated in tasks requiring autonomous robot navigation in unknown environments.

Information Filter Occupancy Mapping using Decomposable Radial Kernels

This paper proposes an information space formulation of the GP mapping problem and utilizes a Kronecker-product-of-Toeplitz-matrices structure to design an information filter occupancy mapping algorithm with linear time and memory complexity that still permits continuous space observations and predictions.

Dense 3-D Mapping with Spatial Correlation via Gaussian Filtering

This work proposes a new approach for occupancy mapping that models the binary nature of occupancy measurements precisely, via a Bernoulli distribution, and provides an efficient approximation of GP classification with complexity that does not scale with time.

Deep occupancy maps: a continuous mapping technique for dynamic environments

A “fully” convolutional neural network is proposed which can build global continuous occupancy maps by learning from raw local unorganized point cloud data, conveniently captured using a range sensor such as LIDAR.

Bayesian Hilbert Maps for Dynamic Continuous Occupancy Mapping

A variational Bayesian approach to Hilbert mapping, thus eliminating the regularization term typically adjusted heuristically and extended to learn long-term occupancy maps in dynamic environments in a sequential fashion, demonstrating the power of kernel methods to capture abstract nonlinear patterns and Bayesian learning to construct sophisticated models.

Learning Continuous Occupancy Maps with the Ising Process Model

A new method of learning a continuous occupancy field for use in robot navigation that explores a generalisation of the so-called Ising model as a suitable candidate for modelling an occupancy field and presents a unique kernel for use within the method that models range measurements.



Contextual occupancy maps using Gaussian processes

This model provides both a continuous representation of the robot's surroundings and an associated predictive variance by employing a Gaussian process as a non-parametric Bayesian learning technique to exploit the fact that real-world environments inherently possess structure.

Gaussian process occupancy maps*

The technique can handle noisy data, potentially from multiple sources, and fuse it into a robust common probabilistic representation of the robot’s surroundings, and provides inferences with associated variances into occluded regions and between sensor beams, even with relatively few observations.

Particle Filter Localization on Continuous Occupancy Maps

This paper devised a novel likelihood model based on the multivariate normal probability density function and adapted the particle filter localization method to work with GPOM to address a new localization method that provides higher accuracy compared to occupancy grid maps localization.

OctoMap: an efficient probabilistic 3D mapping framework based on octrees

An open-source framework to generate volumetric 3D environment models based on octrees and uses probabilistic occupancy estimation that represents not only occupied space, but also free and unknown areas and an octree map compression method that keeps the 3D models compact.

Efficient additive kernels via explicit feature maps

  • A. VedaldiAndrew Zisserman
  • Computer Science, Mathematics
    2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
It is shown that the χ2 kernel, which has been found to yield the best performance in most applications, also has the most compact feature representation, and is able to obtain a significant performance improvement over current state of the art results based on the intersection kernel.

A Gaussian process-based RRT planner for the exploration of an unknown and cluttered environment with a UAV

Simulation results show that GP map combined with RRT planner can achieve the 3D navigation and exploration task successfully in unknown and complex environments.

Sonar-Based Real-World Mapping and Navigation

A sonar-based mapping and navigation system developed for an autonomous mobile robot operating in unknown and unstructured environments is described. The system uses sonar range data to build a

A Sparse Covariance Function for Exact Gaussian Process Inference in Large Datasets

A new stationary covariance function (Mercer kernel) is constructed that naturally provides a sparse covariance matrix that enables exact GP inference and performs comparatively to the squared-exponential one, at a lower computational cost.

Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent

  • W. Xu
  • Computer Science
  • 2011
A finite sample analysis for the method of Polyak and Juditsky (1992) shows that it indeed usually takes a huge number of samples for ASGD to reach its asymptotic region for improperly chosen learning rate, and a simple way to properly set learning rate is proposed.

Practical Bayesian Optimization of Machine Learning Algorithms

This work describes new algorithms that take into account the variable cost of learning algorithm experiments and that can leverage the presence of multiple cores for parallel experimentation and shows that these proposed algorithms improve on previous automatic procedures and can reach or surpass human expert-level optimization for many algorithms.