# 通过基于扩散的轨迹规划实现移动机器人非抓取多物体放置

> 原文链接：https://robotics.hellobike.com/papers/2026-10-08-2610-12684
> 频道：papers | 更新日期：2026-10-08 | 标签：arxiv, cs.RO
> 核心摘要：针对移动机器人多物体精确非抓取放置，提出因果分解扩散规划，并在Push-T、多箱环境和TurtleBot 3上验证。

# 通过基于扩散的轨迹规划实现移动机器人非抓取多物体放置

::: v-pre
> 原文链接：[Non-Prehensile Multi-Object Placement with Mobile Robots via Diffusion-Based Trajectory Planning](https://arxiv.org/abs/2610.12684)（arXiv 2610.12684 · 发布日期：2026-10-08）

**Non-Prehensile Multi-Object Placement with Mobile Robots via Diffusion-Based Trajectory Planning**

针对移动机器人多物体精确非抓取放置，提出因果分解扩散规划，并在Push-T、多箱环境和TurtleBot 3上验证。

## 核心要点

- 移动机器人纠正精确放置误差常需绕物体大范围重定位。
- 将多物体推动形式化为紧容差下的多目标分配问题。
- 因果分解扩散规划可为单个机器人计划采样多个物体结果。
- Push-T成功率最高且不合理运动最低；多箱环境提升21.5个百分点。

**验证范围与局限**：验证范围包括Push-T、三个类仓库多箱推动环境和一台TurtleBot 3 Burger真机。

## 英文摘要 (Abstract)

Non-prehensile manipulation with mobile robots has primarily targeted placement in coarse goal regions. Precision placement has been studied with manipulators on benchmarks such as Push-T, where an omnidirectional end effector can readily re-approach an object from any side. For a mobile robot, correcting the same placement errors may require wide repositioning maneuvers around the object. We formalize multi-object pushing with a mobile robot as a multi-target assignment problem at tight tolerances. We propose a diffusion planner with a causal factorization: each robot denoising step is followed by an object step conditioned on the current clean robot estimate. This factorization allows us to sample multiple object outcomes for a single robot plan, capturing the multi-modality of pushing. We also design a set of pushing-specific costs for mobile robots, used for both guidance and best-of-$N$ sampling at inference. On Push-T, our planner attains the highest success rate of the methods we compare, while having the lowest rate of implausible object motion. Across three multi-box pushing environments resembling warehouse scenarios, it raises the fraction of boxes placed by $21.5$ percentage points over an unguided baseline, and replans $1.8\times$ faster than a planner that denoises the two trajectories together. Lastly, we deploy the guided planner on a TurtleBot 3 Burger with object shapes absent from the training data, where it places $85.0\%$ of objects within tolerance against Diffusion Policy's $37.5\%$.

作者：Lance Pharand, Megnath Ramesh, Mark Chiu, Yash Vardhan Pant, Stephen L. Smith
:::

## 原始参考来源 (Sources)

- [arXiv 2610.12684：Non-Prehensile Multi-Object Placement with Mobile Robots via Diffusion-Based Trajectory Planning](https://arxiv.org/abs/2610.12684)