Fast Action Generation Via Knowledge Distillation with Flow Matching for Social Navigation

Mobile robot navigation in dynamic environments that contain pedestrians is one of the key challenges in the devel- opment of autonomous mobile service robots. This field, known as social navigation, has seen significant research progress using reinforcement learning approaches. In recent years, numerous diffusion-based reinforcement learning methods capable of generating diverse actions have been proposed. However, com- pared to conventional reinforcement learning approaches, the diffusion model’s slow generation process presents a significant barrier to real-time processing. To address this, we propose a method for knowledge distillation of conditional diffusion models by combining Gaussian Prior with Flow Matching to enable faster action generation in dynamic environments. Experiments using a crowd navigation benchmark in simu- lation environments demonstrate that a significant reduction of the time required for action generation is possible while maintaining nearly the same performance as teacher models.