用可微接触图高效生成机械操作可行解
Efficient Gradient-Based Inference for Manipulation Planning in Contact Factor Graphs
- 构建可微接触因子图建模操作中的物理接触约束
- 通过结构化条件概率实现高效推断并近似后验分布
- 适合机器人路径规划与复杂抓取任务研究者
本文提出一种框架，用于解决机械操作中涉及复杂几何-物理推理的规划问题，通常与接触和动态约束相关。我们引入接触因子图（CFG）以图形化方式建模这些多样化因素，从而在图上进行推断，近似解的分布并采样合适方案。提出一种新方法，将接触操作中的多种现象作为可微分因子纳入模型，并开发了利用这种可微性及接触结构带来的条件概率的高效推断算法。结果表明，该框架在多种操作场景中均能生成可行解并有效逼近后验分布。
原文摘要 · Abstract (English)
This paper presents a framework designed to tackle a range of planning problems arise in manipulation, which typically involve complex geometric-physical reasoning related to contact and dynamic constraints. We introduce the Contact Factor Graph (CFG) to graphically model these diverse factors, enabling us to perform inference on the graphs to approximate the distribution and sample appropriate solutions. We propose a novel approach that can incorporate various phenomena of contact manipulation as differentiable factors, and develop an efficient inference algorithm for CFG that leverages this differentiability along with the conditional probabilities arising from the structured nature of contact. Our results demonstrate the capability of our framework in generating viable samples and approximating posterior distributions for various manipulation scenarios.
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。