DiffuserLite: Towards Real-time Diffusion Planning
Dong, Zibin, Hao, Jianye, Yuan, Yifu, Ni, Fei, Wang, Yitian, Li, Pengyi, Zheng, Yan
–arXiv.org Artificial Intelligence
Diffusion planning has been recognized as an effective decision-making paradigm in various domains. The capability of conditionally generating high-quality long-horizon trajectories makes it a promising research direction. However, existing diffusion planning methods suffer from low decision-making frequencies due to the expensive iterative sampling cost. To address this issue, we introduce DiffuserLite, a super fast and lightweight diffusion planning framework. DiffuserLite employs a planning refinement process (PRP) to generate coarse-to-fine-grained trajectories, significantly reducing the modeling of redundant information and leading to notable increases in decision-making frequency. Our experimental results demonstrate that DiffuserLite achieves a decision-making frequency of $122$Hz ($112.7$x faster than previous mainstream frameworks) and reaches state-of-the-art performance on D4RL benchmarks. In addition, our neat DiffuserLite framework can serve as a flexible plugin to enhance decision frequency in other diffusion planning algorithms, providing a structural design reference for future works. More details and visualizations are available at https://diffuserlite.github.io/.
arXiv.org Artificial Intelligence
Feb-2-2024
- Country:
- Asia > China
- Tianjin Province > Tianjin (0.04)
- North America > United States
- California > San Diego County > San Diego (0.04)
- Asia > China
- Genre:
- Research Report > New Finding (1.00)
- Technology: