BehaviorBench reveals that self-play RL policies for autonomous driving overfit to their training traffic agents and do not generalize to other behaviors, motivating a hybrid rule-based plus learned planner.
Title resolution pending
4 Pith papers cite this work, alongside 3,935 external citations. Polarity classification is still indexing.
4
Pith papers citing it
3,935
external citations · Crossref
years
2026 4verdicts
UNVERDICTED 4representative citing papers
SCSL enables composing tests from elementary scenarios with online execution and dynamic reconfiguration to handle nondeterminism and changing configurations in distributed robot systems.
Dynamic traffic emissions from an online-calibrated SUMO model improve hyperlocal NO2 hotspot predictions and peak representation over static baselines when coupled to the CAIRDIO dispersion model.
A conditional flow matching model generates realistic safety-critical traffic scenarios by turning nominal scenes into dangerous rollouts using combined simulation and real data.
citing papers explorer
-
Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving
BehaviorBench reveals that self-play RL policies for autonomous driving overfit to their training traffic agents and do not generalize to other behaviors, motivating a hybrid rule-based plus learned planner.
-
Scenario-based System Testing for Distributed Robotics Applications
SCSL enables composing tests from elementary scenarios with online execution and dynamic reconfiguration to handle nondeterminism and changing configurations in distributed robot systems.
-
Hyperlocal urban NO2 hotspot modeling driven by microscopic traffic data
Dynamic traffic emissions from an online-calibrated SUMO model improve hyperlocal NO2 hotspot predictions and peak representation over static baselines when coupled to the CAIRDIO dispersion model.
-
Conditional Flow-VAE for Safety-Critical Traffic Scenario Generation
A conditional flow matching model generates realistic safety-critical traffic scenarios by turning nominal scenes into dangerous rollouts using combined simulation and real data.