TOPO-Bench: Benchmarking Topological Mapping under Perceptual Aliasing

TOPO-Bench: An Open-Source Topological Mapping Evaluation Framework with Quantifiable Perceptual Aliasing, Jiaming Wang★, Diwen Liu★, Jizhuo Chen★, and Harold Soh★, IEEE International Conference on Robotics and Automation (ICRA)
Links: Paper

Topological maps offer a compact, scalable representation for robot navigation, but evaluating them has been surprisingly hard—especially under perceptual aliasing, where distinct places look alike. TOPO-Bench tackles this with an open-source evaluation framework that makes two contributions: (1) it formalizes topological consistency and proposes localization accuracy as a practical surrogate metric, and (2) it introduces the first quantitative measure of dataset ambiguity.

We curate a benchmark dataset with calibrated ambiguity levels, implement both deep-learned and classical baselines, and release open-source tooling. The analysis yields concrete insights into how perceptual aliasing challenges current topological mapping approaches.

Resources

You can find our paper here.

Citation

Please consider citing our paper if you build upon our results and ideas.

Jiaming Wang★, Diwen Liu★, Jizhuo Chen★, and Harold Soh★, “TOPO-Bench: An Open-Source Topological Mapping Evaluation Framework with Quantifiable Perceptual Aliasing”, IEEE International Conference on Robotics and Automation (ICRA)

@inproceedings{wang2026topobench, title={TOPO-Bench: An Open-Source Topological Mapping Evaluation Framework with Quantifiable Perceptual Aliasing}, author={Wang, Jiaming and Liu, Diwen and Chen, Jizhuo and Soh, Harold}, booktitle={IEEE International Conference on Robotics and Automation (ICRA)}, year={2026} }