HTCE: Homeomorphism-inspired Topological Cross-Scene Experience Canonicalization and Reuse for Object Navigation
Organizations: the MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China · the School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China · Tsinghua University · University of Chinese Academy of Sciences
Abstract
As embodied agents perform object-goal navigation across residential environments, they accumulate successful experiences whose semantic structure recurs across scenes even when geometric trajectories do not. Reusing such experience is challenging because differences in region naming and observation granularity produce distinct graph representations of similar approaches, while meaningful differences in anchors, branches, and endpoints must stay distinguishable. We introduce HTCE, a homeomorphism-inspired topological framework that canonicalizes and reuses navigation experience. Feature and topology subdivisions characterize representational variations, and their semantically constrained reductions produce comparable semantic sequences and structural signatures while preserving semantic anchors, branching relations, and navigation endpoints. HTCE then retrieves historical successful approaches through subdivision-aware matching as guidance for a frozen vision-language policy. Canonicalization compresses the experience index losslessly, merging 17.7--23.6% of distinct stored route descriptions while retaining full task performance. Under a single frozen vision-language backbone shared by all compared systems, HTCE attains the best SR and SPL in every setting---59.9%/31.8% on HM3D v0.1, 71.0%/31.5% on HM3D v0.2, and 46.6%/16.6% on MP3D---with SR gains of up to 4.9 points and structured retrieval contributing up to 2.8 SPL points. The code is available in https://github.com/startracker0/htce.git
Figures & tables
| HM3D v0.1 | HM3D v0.2 | MP3D | ||||
|---|---|---|---|---|---|---|
| Method | SR | SPL | SR | SPL | SR | SPL |
| OpenFMNav ∗ | 52.1 | 23.5 | 37.6 | 14.1 | 27.1 | 7.5 |
| L3MVN ∗ | 37.8 | 19.4 | 29.6 | 13.3 | 22.4 | 7.4 |
| VLMNav ∗ | 40.1 | 14.9 | 46.5 | 14.0 | 35.2 | 11.0 |
| WMNav ∗ | 55.0 | 31.7 | 70.0 | 30.0 | 43.5 | 15.6 |
| WMNav + TM ∗ | 56.3 | 30.3 | 67.2 | 30.7 | 43.3 | 15.7 |
| Component | HM3D v0.1 | HM3D v0.2 | |||||
|---|---|---|---|---|---|---|---|
| G | P | R | M | SR | SPL | SR | SPL |
| 56.3 | 30.3 | 67.2 | 30.7 | ||||
| ✓ | ✓ | ✓ | 58.3 | 31.2 | 70.9 | 31.1 | |
| ✓ | ✓ | ✓ | 59.0 | 30.7 | 70.8 | 31.3 | |
| ✓ | ✓ | ✓ | 59.1 | 29.0 | 71.0 | 30.2 | |
| ✓ | ✓ | ✓ | ✓ | 59.9 | 31.8 | 71.0 | 31.5 |
| Structural change | Distinguishes the pair? | |
|---|---|---|
| Online | Exact | |
| Branch positions swapped | ||
| Same-role leaves: | ||
| Measurement | Order A | Order B |
|---|---|---|
| Retrieval (ms/call) | 0.139 | 0.132 |
| Update (ms/episode) | 61.6 | 62.6 |
| Largest snapshot (bytes) | 550,077 | 514,524 |
Appendix figures & tables6 assets
Supplementary material from the paper’s appendix.
Appendix
| Setting | Value |
|---|---|
| Region association | |
| Name agreement: exact / alias / other | 1 / 0.7 / 0 |
| Topology term: previous / neighbor / non-neighbor | 0.05 / 0.12 / |
| Semantic agreement below which the non-neighbor term applies | 0.70 |
| Recent-position term | |
| Confirmed association | |
| Inputs | Relation | Preserved information |
|---|---|---|
| , | Same | Transition-role normalization |
| , | Same | Passage subdivision |
| , | Same | Adjacent repetition |
| , | Different | Destination category |
| , | Different | Nonpalindromic order |
| , | Different | Connector type |
| Graph edit | Same | R | F | T | S | Mean |
| approach? | score | |||||
| Hallway step relabeled corridor | Yes | ✓ | ✓ | 1.000 | ||
| Extra hallway steps inserted | Yes | ✓ | ✓ | 0.867 | ||
| Both of the above | Yes | ✓ | 0.867 | |||
| Kitchen branch added at a hallway step | No | ✓ | ✓ | ✓ | ✓ | 0.725 |
| Start room replaced | No | ✓ | ✓ | ✓ | ✓ | 0.742 |
| Transformation | Pattern | Pairs | Correct |
|---|---|---|---|
| Transition alias | Same | 193 | 193 |
| Transition subdivision | Same | 193 | 193 |
| Adjacent anchor repeat | Same | 270 | 270 |
| Destination change | Different | 270 | 270 |
| Order reversal | Different | 206 | 206 |
| Transition removal | Different | 193 | 193 |
| Transformation | Pairs | Raw | Reduced |
|---|---|---|---|
| Transition alias | 193 | 193 | 193 |
| Transition subdivision | 193 | 193 | 193 |
| Adjacent anchor repeat | 270 | 257 | 270 |
| Destination change | 270 | 230 | 228 |
| Order reversal | 206 | 45 | 50 |
| Transition removal | 193 | 152 | 156 |
| Graph context | Verified property |
|---|---|
| Small-graph edge refinements | Correspondence follows semantic chain-word preservation |
| Parallel passages | Distinct connections retain multiplicity |
| Returning cycles | Loops retain their protected attachment |
| Transition endpoints | Start and target remain explicit |
| Cropped junctions | Stored degree and boundary mark remain explicit |
| Distinct same-role anchors | Separate region vertices remain distinct |
Object-Goal Navigation
Object-goal navigation studies how robots find and approach requested objects in unfamiliar environments using visual, spatial, and language cues.
See all 93 papers