用扩散模型从噪声生成路径，让AI学会在迷宫中自主规划路线。
GenPlanner: From Noise to Plans -- Emergent Reasoning in Flow Matching and Diffusion Models
- 基于扩散与流匹配模型，从随机噪声逐步生成路径。
- 在迷宫任务中性能远超传统CNN，流匹配版仅需少量步骤即高效求解。
- 适合研究生成模型推理能力、路径规划或强化学习的开发者参考。
复杂环境中的路径规划是人工智能的关键挑战，需同时理解空间几何与全局问题结构。本文探索生成模型作为规划与推理机制的潜力，提出基于扩散模型和流匹配的GenPlanner方法，包含DiffPlanner与FlowPlanner两个变体。通过多通道条件（障碍物图、起点与终点信息）引导轨迹生成，模型从随机噪声开始，逐步演化为正确路径。与标准方法不同，本方法迭代生成路径，无需预先定义搜索策略。实验表明，该方法显著优于基线CNN模型；其中FlowPlanner在生成步数有限的情况下仍保持高精度，展现了强泛化能力。
原文摘要 · Abstract (English)
Path planning in complex environments is one of the key problems of artificial intelligence because it requires simultaneous understanding of the geometry of space and the global structure of the problem. In this paper, we explore the potential of using generative models as planning and reasoning mechanisms. We propose GenPlanner, an approach based on diffusion models and flow matching, along with two variants: DiffPlanner and FlowPlanner. We demonstrate the application of generative models to find and generate correct paths in mazes. A multi-channel condition describing the structure of the environment, including an obstacle map and information about the starting and destination points, is used to condition trajectory generation. Unlike standard methods, our models generate trajectories iteratively, starting with random noise and gradually transforming it into a correct solution. Experiments conducted show that the proposed approach significantly outperforms the baseline CNN model. In particular, FlowPlanner demonstrates high performance even with a limited number of generation steps.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。