Co-training an SDC and pedestrians with MAPPO yields 78% goal success and 14% collisions versus 35%/33% for rule-based baselines, with jaywalking causing 62% of collisions and evidence of poor anticipation via speed differentials.
JAX: composable transformations of Python+NumPy programs
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A CBF quadratic program filters human-to-humanoid imitation commands to enforce collision-free motion in simulation.
citing papers explorer
-
Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty
Co-training an SDC and pedestrians with MAPPO yields 78% goal success and 14% collisions versus 35%/33% for rule-based baselines, with jaywalking causing 62% of collisions and evidence of poor anticipation via speed differentials.
-
Safe Human-to-Humanoid Motion Imitation Using Control Barrier Functions
A CBF quadratic program filters human-to-humanoid imitation commands to enforce collision-free motion in simulation.