AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

TraversRL: Traversable Pedestrian Pathway Generation With Reinforcement Learning

Bin Han, Robert Wolfe, Bill Howe

ECCV 2026 · Reinforcement learning › Visual and representation RL · approach: Goal-conditioned policy learning · 0 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
add RL fine-tuning with terminal graph rewardTraversRL-Pre · all datasetsbuffered IoU: 5.1% on WashingtonInter, 5.6% on Seattle, 5.2% on D.C.Improved
add local stepwise reward shaping on top of global reward (ablation)TraversRL-Global · all datasetsbuffered IoU: 1.6%, 4.1%, 2.1%Improved
add local reward shapingTraversRL-Global · D.C. (ViT-S)buffered IoU: 0.226 -> 0.221No clear effect
RL fine-tuning reduces graph densityTraversRL-Pre · SeattleAvgDeg: 0.574 -> 0.519Improved
add RL fine-tuning (global reward)TraversRL-Pre · WashingtonInterTravSim: 0.595 -> 0.599Improved
add local shapingTraversRL-Pre · SeattleTravSim: 0.389 -> 0.411Improved
use larger evaluation buffer 4m vs 1m (ablation)TraversRL-Global · WashingtonInterIoU gain over Pre: 2.1% at 4m, 3.1% at 2m, 5.2% at 1mMixed
use stricter 1m buffer for local reward (ablation)TraversRL-Local · WashingtonInterIoU gain over Pre: 2.5% at 4m, 4.0% at 2m, 6.8% at 1mImproved
increase action space from |A|=181 to 361 (ablation)TraversRL-Local ResNet-18 · WashingtonInterIoU/TravSim: 0.448/0.581 -> 0.540/0.605Improved
increase action space from |A|=361 to 721 (ablation)TraversRL-Local ResNet-18 · WashingtonInterIoU/TravSim: 0.540/0.605 -> 0.569/0.618Improved
increase action space from |A|=361 to 721 (ablation)TraversRL-Local ResNet-18 · SeattleIoU/TravSim: 0.199/0.403 -> 0.198/0.383Hurt
increase action space from |A|=361 to 721 (ablation)TraversRL-Local ResNet-18 · D.C.IoU/TravSim: 0.227/0.513 -> 0.237/0.520Improved

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