arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.11658cs.RO
收藏

张量张量与凸集图的耦合:在C空间中实现有效的压缩、探索与规划

Coupling Tensor Trains with Graph of Convex Sets: Effective Compression, Exploration, and Planning in the C-Space

Technical University of Munich(慕尼黑技术大学);Northeastern University(东北大学)

Gerhard Reinerth, Riddhiman Laha, Marcello Romano

AI总结:

TANGO通过结合张量压缩与图优化,在C空间中实现高效、几何感知的运动规划,提升轨迹生成的质量和效率。

摘要:

我们提出了TANGO(张量与图优化),一种新的运动规划框架,该框架整合了基于张量的压缩与结构化图优化,以实现高效且可扩展的轨迹生成。虽然基于优化的规划器如凸集图(GCS)提供了生成平滑、最优轨迹的强大工具,但它们通常依赖于对高维配置空间的预定义凸特性化——这一要求往往难以满足一般机器人任务。TANGO进一步利用张量张量分解来近似可行的配置空间,以压缩形式进行快速发现和估计任务相关的区域。这些区域随后嵌入到类似GCS的结构中,允许具有几何意识的运动规划,既尊重系统约束,又尊重环境复杂性。通过将基于张量的压缩与结构化图推理相结合,TANGO实现了高效的、具有几何意识的运动规划,并为未来机器人系统中配置空间的更丰富和可扩展的表示奠定了基础。严格的平面和真实机器人模拟研究加强了我们关于有效压缩和更高质量轨迹的主张。

英文摘要:

We present TANGO (Tensor ANd Graph Optimization), a novel motion planning framework that integrates tensor-based compression with structured graph optimization to enable efficient and scalable trajectory generation. While optimization-based planners such as the Graph of Convex Sets (GCS) offer powerful tools for generating smooth, optimal trajectories, they typically rely on a predefined convex characterization of the high-dimensional configuration space-a requirement that is often intractable for general robotic tasks. TANGO builds further by using Tensor Train decomposition to approximate the feasible configuration space in a compressed form, enabling rapid discovery and estimation of task-relevant regions. These regions are then embedded into a GCS-like structure, allowing for geometry-aware motion planning that respects both system constraints and environmental complexity. By coupling tensor-based compression with structured graph reasoning, TANGO enables efficient, geometry-aware motion planning and lays the groundwork for more expressive and scalable representations of configuration space in future robotic systems. Rigorous simulation studies on planar and real robots reinforce our claims of effective compression and higher quality trajectories.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑