Autonomous Navigation in Unknown Environments using Sparse Kernel-based Occupancy Mapping

Thai Duong, Nikhil Das, Michael Yip, Nikolay Atanasov
2/5/2020
cs.ROcs.LGeess.SY

Official code: thaipduong/kernelbasedmap (8 stars, MIT, last commit 2020-10-28).

Abstract

This paper focuses on real-time occupancy mapping and collision checking onboard an autonomous robot navigating in an unknown environment. We propose a new map representation, in which occupied and free space are separated by the decision boundary of a kernel perceptron classifier. We develop an online training algorithm that maintains a very sparse set of support vectors to represent obstacle boundaries in configuration space. We also derive conditions that allow complete (without sampling) collision-checking for piecewise-linear and piecewise-polynomial robot trajectories. We demonstrate the effectiveness of our mapping and collision checking algorithms for autonomous navigation of an Ackermann-drive robot in unknown environments.

View on arXivView PDF

Code Implementations(1)

thaipduong/kernelbasedmapOfficial100%
MIT

Code for our ICRA paper "Autonomous Navigation in Unknown Environments with Sparse Kernel-based Occupancy Mapping"

81PythonSep 20, 20195 years agoMIT
collision-checkingkernel-perceptronoccupancy-mapping

Similar Papers

Memory-based Deep Reinforcement Learning for Obstacle Avoidance in UAV with Limited Environment Knowledge

83% match1 repo1132018

NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning

83% match1 repo1.0k2024

Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation

83% match1 repo1062017

Real-Time Model Checking for Closed-Loop Robot Reactive Planning

83% match1 repo12025

Multi-Robot Navigation in Social Mini-Games: Definitions, Taxonomy, and Algorithms

82% match2025

Bench2FreeAD: A Benchmark for Vision-based End-to-end Navigation in Unstructured Robotic Environments

82% match1 repo282025

Cite this paper

@article{duong2020autonomous,
  title  = {Autonomous Navigation in Unknown Environments using Sparse Kernel-based Occupancy Mapping},
  author = {Thai Duong and Nikhil Das and Michael Yip and Nikolay Atanasov},
  year   = {2020},
  eprint = {2002.01921},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2002.01921}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2002.01921.svg)](https://codeofpaper.com/paper/2002.01921)

Discussion