AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving

Zhiyu Huang, Haochen Liu, Chen Lv

ICCV 2023 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Data-driven traffic simulation · 210 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 level-k iterative decoding (0 to 4 levels) (ablation)GameFormer planner · WOMD open-loop planningcollision rate: 0.0384 -> 0.0198Improved
increase decoding levels beyond 4 (ablation)GameFormer planner · WOMD open-loop planningcollision rate: 0.0198 -> 0.0245 (level 5)Hurt
feed previous-level agent future trajectories into the next decoding level (ablation)GameFormer · WOMD open-loop planningplanning ADE: 0.9210 -> 0.8329Improved
add self-attention over agent futures (ablation)GameFormer · WOMD open-loop planningplanning ADE: 0.8666 -> 0.8329Improved
add interaction loss (ablation)GameFormer · WOMD open-loop planningcollision rate: 0.0417 -> 0.0198Improved
use independent decoder layers instead of one shared decoder (ablation)GameFormer · WOMD open-loop planningplanning ADE: 0.9196 -> 0.8329Improved
supervise intermediate decoding level trajectories (ablation)GameFormer · WOMD open-loop planningplanning ADE: 0.9584 -> 0.8329Improved
use 6 decoding layers rather than 8 for interaction prediction (ablation)GameFormer · WOMD interaction predictionminADE: 0.9839 -> 0.9133Improved
add cost-based refinement plannerGameFormer · WOMD closed-loop planningsuccess rate (%): 73.16 -> 94.50Improved
use marginal model with EM aggregation instead of joint modelGameFormer · WOMD interaction predictionmAP: mAP 0.1376 -> 0.1923, minFDE 1.9373 -> 2.2146Mixed

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