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

TL;DR

This paper introduces a novel sparse Bayesian kernel-based occupancy mapping method for autonomous robots, enabling efficient, probabilistic, and real-time environment representation and collision checking in large unknown spaces.

Contribution

It presents a new approach using Relevance Vector Machines for sparse, probabilistic occupancy mapping with online updates, improving efficiency and robustness over traditional voxel-based methods.

Findings

Efficient online mapping with sparse support vectors.

Robust probabilistic occupancy classification.

Effective collision checking for autonomous navigation.

Abstract

This paper focuses on online occupancy mapping and real-time collision checking onboard an autonomous robot navigating in a large unknown environment. Commonly used voxel and octree map representations can be easily maintained in a small environment but have increasing memory requirements as the environment grows. We propose a fundamentally different approach for occupancy mapping, in which the boundary between occupied and free space is viewed as the decision boundary of a machine learning classifier. This work generalizes a kernel perceptron model which maintains a very sparse set of support vectors to represent the environment boundaries efficiently. We develop a probabilistic formulation based on Relevance Vector Machines, allowing robustness to measurement noise and probabilistic occupancy classification, supporting autonomous navigation. We provide 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. The effectiveness of our mapping and collision checking algorithms is evaluated in tasks requiring autonomous robot navigation and active mapping in unknown environments.