AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Learning and Aggregating Lane Graphs for Urban Automated Driving

Martin Büchner, Jannik Zürn, Ion-George Todoran, Abhinav Valada, Wolfram Burgard

CVPR 2023 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use LaneGNN instead of skeletonized regressionSuccessor-LGP · UrbanLaneGraphSDA20: 0.020 -> 0.227Improved
Use LaneGNN instead of LaneGraphNetSuccessor-LGP · UrbanLaneGraphTOPO P/R: 0.0/0.0 -> 0.600/0.699Improved
Use proposed iterative aggregation instead of naïve aggregationLaneGNN · Full-LGP, Miami test setGraph IoU: 0.376 -> 0.384Improved
Use proposed aggregation instead of LaneExtractionLane graph path planning · Miami test areaMMD [m]: 157.0 -> 2.2Improved
Use proposed aggregation instead of LaneExtractionLane graph path planning · Miami test areaSR: 0.47 -> 0.46Hurt
Add causal message passing (ablation)LaneGNN · Successor-LGP, UrbanLaneGraphAPLS: 0.188 -> 0.202Improved
Add aerial edge features (ablation)LaneGNN · Successor-LGP, UrbanLaneGraphGraph IoU: 0.320 -> 0.347Improved
Use the ego-lane mask instead of the standard lane mask for proposal sampling (ablation)LaneGNN · Successor-LGP, UrbanLaneGraphGraph IoU: 0.250 -> 0.347Improved
Add aerial edge features rather than aerial node features (ablation)LaneGNN · Successor-LGP, UrbanLaneGraphGraph IoU: 0.320 -> 0.347Improved
Add the node loss term (ablation)LaneGNN · Successor-LGP, UrbanLaneGraphAPLS: 0.144 -> 0.202Improved
Increase proposal nodes from 200 to 400 (ablation)LaneGNN · Successor-LGP, UrbanLaneGraphAPLS: 0.077 -> 0.202Improved
Use six message-passing layers instead of none (ablation)LaneGNN · Successor-LGP, UrbanLaneGraphAPLS: 0.057 -> 0.202Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy