Publication record · 18.cifr/2006.durrantwhyte.slam-ekf

Simultaneous localization and mapping: part I

v1.0.0

H. Durrant-Whyte (University of Sydney), T. Bailey (University of Sydney)

RAI18.cifr/2006.durrantwhyte.slam-ekf

IEEE Robotics & Automation Magazine· 2006· doi:10.1109/MRA.2006.1638022

This article presents a tutorial on simultaneous localization and mapping (SLAM). The SLAM problem asks if it is possible for an autonomous vehicle to start in an unknown location in an unknown environment and then to incrementally build a consistent map of this environment while simultaneously determining its location within this map.

SLAMextended Kalman filterrobot localizationlandmark mappingmobile robotics

✦ Research context

What this agent contributes to the literature.

Problem solved

Mobile robots in unknown environments face a chicken-and-egg problem: localization requires a map and mapping requires localization. Before this work, no principled probabilistic framework unified odometry uncertainty, sensor noise, and the growing landmark correlations that drive convergence. This paper proves when and why SLAM is consistent.

Novelty

This paper provides the first comprehensive tutorial formulation of the SLAM problem as a probabilistic estimation problem, unifying landmark-based mapping and robot localization in a single recursive Bayesian filter. It formally proves that the joint landmark-robot covariance converges monotonically, establishing the theoretical foundation for all subsequent SLAM algorithms.

Related research

Computing related research...

Canvas contract1-in / 1-out · unpacked into map_params, motion_observations legacy ports

Sample data

Loading sample data...

Total calls

This month

Citations

Last called

—

Image digest

sha256:8783054d5ea1d74f3dce657c5714a91fd5cfb9498c221a8b5c6d8463426e93db

Invoke command

python main.py

Inputs

input:application/json

Outputs

output:application/json

Citation

Loading DOI…

Invoke

CPU compute only

How to get GPU access: Your university, lab, or company can become a CIFR institutional member. Members get GPU-accelerated runs for all their researchers. Contact us

Pre-filled with the paper's canonical scenario. Click Invoke agent to reproduce the original result, or edit the JSON below to run a counterfactual.

inputapplication/jsonoptional

Unified canvas input containing map_params and motion_observations

Leave empty to run the paper's canonical scenario.

Recent invocations(0)

No invocations yet — be the first to call this agent.