AI Paper Atlas

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

Large Scale Interactive Motion Forecasting for Autonomous Driving: The Waymo Open Motion Dataset

Scott Ettinger, Shuyang Cheng, Benjamin Caine, Chenxi Liu, Hang Zhao, Sabeek Pradhan, Yuning Chai, Ben Sapp, Charles R. Qi, Yin Zhou, Zoey Yang, Aurélien Chouard and 6 more

ICCV 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Interactive multi-agent trajectory prediction · 666 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 road graph encoding (ablation)LSTM baseline · Waymo standard validation, vehicleminADE: 2.63 -> 1.54Improved
add high-order interactions (ablation)LSTM baseline · Waymo standard validation, vehicleminADE: 2.63 -> 1.67Improved
add high-order interactions to road graph model (ablation)LSTM + rg · Waymo standard validation, vehicleminADE: 1.54 -> 1.36Improved
add traffic signal states to road graph model (ablation)LSTM + rg · Waymo standard validation, vehicleminADE: 1.54 -> 1.52Improved
add traffic signal states to road graph plus interactions model (ablation)LSTM + rg + hi · Waymo standard validation, vehiclemAP: 0.22 -> 0.23Improved
add all of road graph, signals and interactions (ablation)LSTM baseline · Waymo standard validation, vehiclemAP: 0.07 -> 0.23Improved
add traffic signals and interactions to road graph model (ablation)LSTM + rg · Waymo interactive validation, pedestrian (joint)miss rate: 0.86 -> 1.00Hurt
train jointly for the two interacting agents instead of marginally (ablation)LSTM baseline · Waymo interactive validation, vehicle, 8sminADE: 4.16 -> 3.81Improved
train jointly for the two interacting agents instead of marginally (ablation)LSTM baseline · Waymo interactive validation, vehicle, 3sminADE: 0.65 -> 0.65No clear effect
train jointly instead of marginally (ablation)LSTM baseline · Waymo interactive validation, vehiclemAP: 0.07 -> 0.06Mixed
use interactive split instead of regular split (ablation)Const. Vel. · Waymo validation, vehicleoverlap rate: 38.4% -> 44.2%Hurt
increase number of predictions Kbest LSTM · Waymo standard validationminADE vs mAPMixed

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