An adversarial RL framework that both finds collision-inducing scenarios and retrains a motion planner against them, cutting crash rates in a two-vehicle highway simulator.
ISO 26262: Road vehicles - Functional safety
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CRASH: Challenging Reinforcement-Learning Based Adversarial Scenarios For Safety Hardening
An adversarial RL framework that both finds collision-inducing scenarios and retrains a motion planner against them, cutting crash rates in a two-vehicle highway simulator.