# Topo2Seq: Enhanced Topology Reasoning via Topology Sequence Learning

arXiv: https://arxiv.org/abs/2502.08974 · HTML: https://mlsanity.com/paper/2502.08974/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning.
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [Pix2seq: A Language Modeling Framework for Object Detection](https://mlsanity.com/paper/2109.10852/) (2021)
- [MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2208.14437/) (2022)
- [MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2308.05736/) (2023)
- [LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving](https://mlsanity.com/paper/2312.16108/) (2023)
- [Graph-based Topology Reasoning for Driving Scenes](https://mlsanity.com/paper/2304.05277/) (2023)
- [Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction](https://mlsanity.com/paper/2303.08815/) (2023)
- [Leveraging Enhanced Queries of Point Sets for Vectorized Map Construction](https://mlsanity.com/paper/2402.17430/) (2024)
- [TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning](https://mlsanity.com/paper/2310.06753/) (2023)
- [Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane Priors](https://mlsanity.com/paper/2406.03105/) (2024)
- [RoadPainter: Points Are Ideal Navigators for Topology transformER](https://mlsanity.com/paper/2407.15349/) (2024)

## Built on by (most cited first, 9 of 9)

- [LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature Generation](https://mlsanity.com/paper/2511.06272/) (2025)
- [TopoStreamer: Temporal Lane Segment Topology Reasoning in Autonomous Driving](https://mlsanity.com/paper/2507.00709/) (2025)
- [FASTopoWM: Fast-Slow Lane Segment Topology Reasoning with Latent World Models](https://mlsanity.com/paper/2507.23325/) (2025)
- [From Static to Dynamic: a Survey of Topology-Aware Perception in Autonomous Driving](https://mlsanity.com/paper/2509.23641/) (2025)
- [GeoReFormer: Geometry-Aware Refinement for Lane Segment Detection and Topology Reasoning](https://mlsanity.com/paper/2603.26018/) (2026)
- [TopoHR: Hierarchical Centerline Representation for Cyclic Topology Reasoning in Driving Scenes with Point-to-Instance Relations](https://mlsanity.com/paper/2604.24119/) (2026)
- [Fine-Grained Representation for Lane Topology Reasoning](https://mlsanity.com/paper/2511.12590/) (2025)
- [Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior](https://mlsanity.com/paper/2606.31814/) (2026)
- [HGeo-TopoMap: Boosting Topological Mapping with Hierarchical Geometric Priors](https://mlsanity.com/paper/2607.21281/) (2026)

## Abstract (arXiv)

Extracting lane topology from perspective views (PV) is crucial for planning and control in autonomous driving. This approach extracts potential drivable trajectories for self-driving vehicles without relying on high-definition (HD) maps. However, the unordered nature and weak long-range perception of the DETR-like framework can result in misaligned segment endpoints and limited topological prediction capabilities. Inspired by the learning of contextual relationships in language models, the connectivity relations in roads can be characterized as explicit topology sequences. In this paper, we introduce Topo2Seq, a novel approach for enhancing topology reasoning via topology sequences learning. The core concept of Topo2Seq is a randomized order prompt-to-sequence learning between lane segment decoder and topology sequence decoder. The dual-decoder branches simultaneously learn the lane topology sequences extracted from the Directed Acyclic Graph (DAG) and the lane graph containing geometric information. Randomized order prompt-to-sequence learning extracts unordered key points from the lane graph predicted by the lane segment decoder, which are then fed into the prompt design of the topology sequence decoder to reconstruct an ordered and complete lane graph. In this way, the lane segment decoder learns powerful long-range perception and accurate topological reasoning from the topology sequence decoder. Notably, topology sequence decoder is only introduced during training and does not affect the inference efficiency. Experimental evaluations on the OpenLane-V2 dataset demonstrate the state-of-the-art performance of Topo2Seq in topology reasoning.