← Back to Benchmarks
simmediumrlmetric · varies
Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
Description
Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-of-distribution crowd sizes due to density-sensitive observation normalization and social-cost scaling, while analytical solvers often remain safe but freeze in tight interactions. We propose a reinforcement learning approach for dense, variable-density navigation that attains zero-shot density generalization using a d