用生成模型优化局部路径规划，让机器人在密集人群中更顺畅行走。
CrowdSurfer: Sampling Optimization Augmented with Vector-Quantized Variational AutoEncoder for Dense Crowd Navigation
- 用向量量化变分自编码器学习专家轨迹先验，作为路径优化起点。
- 运行时结合采样优化，成功率提升40%，旅行时间减少6%。
- 无需预测动态障碍物，适合实时移动机器人导航场景。
在密集人群中的导航对移动机器人仍具挑战性，尤其当环境布局变化时，先前计算的全局路径可能失效。本文表明，仅通过改进局部规划器即可显著提升导航性能。方法结合生成建模与推理时优化，在交互速率下生成复杂的长时程局部路径。具体而言，训练一个向量量化变分自编码器（VQ-VAE），基于感知输入学习专家轨迹分布的先验。运行时，该先验用于初始化基于采样的优化器进行进一步精炼。本方法无需复杂动态障碍物预测，但仍达到业界领先性能。与近期DRL-VO方法对比，成功率达40%提升，旅行时间减少6%。
原文摘要 · Abstract (English)
Navigation amongst densely packed crowds remains a challenge for mobile robots. The complexity increases further if the environment layout changes, making the prior computed global plan infeasible. In this paper, we show that it is possible to dramatically enhance crowd navigation by just improving the local planner. Our approach combines generative modelling with inference time optimization to generate sophisticated long-horizon local plans at interactive rates. More specifically, we train a Vector Quantized Variational AutoEncoder to learn a prior over the expert trajectory distribution conditioned on the perception input. At run-time, this is used as an initialization for a sampling-based optimizer for further refinement. Our approach does not require any sophisticated prediction of dynamic obstacles and yet provides state-of-the-art performance. In particular, we compare against the recent DRL-VO approach and show a 40% improvement in success rate and a 6% improvement in travel time.
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。