# 基于接触感知图神经动力学模型的张拉整体机器人模型预测控制

> 原文链接：https://robotics.hellobike.com/papers/2026-09-08-2609-08958
> 频道：papers | 更新日期：2026-09-08 | 标签：arxiv, cs.RO
> 核心摘要：针对张拉整体机器人在接触丰富环境中难建模难控制问题，提出基于接触感知GNN动力学模型的MPPI控制器，并在MuJoCo五类导航任务中验证。

# 基于接触感知图神经动力学模型的张拉整体机器人模型预测控制

::: v-pre
> 原文链接：[Model Predictive Control of Tensegrity Robots via Contact-Aware Graph Neural Dynamics Model](https://arxiv.org/abs/2609.08958)（arXiv 2609.08958 · 发布日期：2026-09-08）

**Model Predictive Control of Tensegrity Robots via Contact-Aware Graph Neural Dynamics Model**

针对张拉整体机器人在接触丰富环境中难建模难控制问题，提出基于接触感知GNN动力学模型的MPPI控制器，并在MuJoCo五类导航任务中验证。

## 核心要点

- 张拉整体机器人适合复杂地形移动，但接触丰富动力学和部分可观测性使建模控制困难。
- 方法将可微接触检测加入GNN动力学模型，以处理非水平平面地形、障碍和自碰撞。
- 学习模型与MPPI在闭环采集中迭代改进，并结合转向运动基元形成混合MPPI。
- 实验显示其预测精度优于平地基线，导航性能优于A*重规划和仅MPPI变体。

**验证范围与局限**：验证限于MuJoCo中的三杆张拉整体机器人五类导航任务。

## 英文摘要 (Abstract)

Tensegrity robots offer lightweight, compliant mobility over challenging terrain but remain difficult to model and control due to complex contact-rich dynamics and partial observability. This work presents a model predictive path integral (MPPI) controller for a three-bar tensegrity robot driven by a learned graph neural network (GNN) dynamics model. This work first extends prior GNN-based models with a differentiable contact detection module. The extension allows the dynamics model to reason over non-horizontal planar terrains, obstacles, as well as self-collisions. Then, the learned dynamics model and the MPPI controller operate in a closed data-collection loop, iteratively improving model accuracy and control performance. This work further introduces a hybrid MPPI strategy that combines MPPI with turning motion primitives to improve maneuverability. Experiments are performed in MuJoCo across five navigation tasks, which include, wall obstacles, inclines, narrow corridors, low-clearance structures, and a composite 3D obstacle course. The experiments demonstrate that the hybrid MPPI controller operating over the learned GNN dynamics model improves predictive accuracy over a flat-ground baseline model and achieves superior navigation performance compared to $A^*$-based re-planning and MPPI-only variants. Results show that the contact-aware learned dynamics combined with the sampling-based model predictive control enable robust tensegrity navigation in complex, contact-rich environments.

作者：Nelson Chen, Patrick Meng, Charles Tang, Angelina Degay, Zachary Brei, Rebecca K. Kramer-Bottiglio, Kostas E. Bekris, Mridul Aanjaneya
:::

## 原始参考来源 (Sources)

- [arXiv 2609.08958：Model Predictive Control of Tensegrity Robots via Contact-Aware Graph Neural Dynamics Model](https://arxiv.org/abs/2609.08958)