AI Paper Atlas

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

Exploring the Limitations of Behavior Cloning for Autonomous Driving

Felipe Codevilla, Eder Santana, Antonio M. Lopez, Adrien Gaidon

ICCV 2019 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Data-driven traffic simulation · 610 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 speed prediction branch (ablation)CILR · CARLA original, Nav. Dynamic (new town & weather)success rate (%): 82 -> 90Improved
add speed prediction branch (ablation)CILR · NoCrash Dense (new town & weather)success rate (%): 13 -> 24Improved
add speed prediction branch (ablation)CILR · NoCrash Dense (training conditions)success rate (%): 28 -> 42Improved
add speed prediction branch (ablation)CILR · NoCrash Dense (new weather)success rate (%): 27 -> 47Improved
add speed prediction branch (ablation)CILR · NoCrash Empty (new town & weather)success rate (%): 66 -> 90Improved
initialize with ImageNet pretraining (ablation)CILRS · NoCrash Emptyvariance of success rate (%): 23% -> 4%Improved
initialize with ImageNet pretraining (ablation)CILRS · NoCrash Densevariance of success rate (%): 42% -> 38%Improved
increase traffic from empty to denseCILRS · NoCrash (training / new conditions)success rate: -55% / -66%Hurt
change to new town and weather in empty townCILRS · NoCrash Emptysuccess rate: -7%Hurt
increase training data from 10 to 100 hours (ablation)CILRS · NoCrash Dense (new town & weather)success rateNo clear effect
increase amount of training data (ablation)CILRS · NoCrashepisodes failed by inertiaHurt
train with a different random seedCILRS · NoCrash Dense (new weather & town)success rateMixed

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