# Lodos-v2开源：GPU并行精确摩擦接触求解器提升仿真吞吐

> 原文链接：https://robotics.hellobike.com/papers/2026-11-09-2611-08868-cd8b60b6
> 频道：papers | 更新日期：2026-11-09 | 标签：auto, arxiv
> 核心摘要：Lodos-v2发布GPU加速刚体动力学框架，通过原语形式级联凸松弛算法解决精确摩擦接触问题，消除v1版本物理伪影并支持关节限位等复合约束集成，在多网格碰撞场景下吞吐量显著优于主流仿真器，代码已开源。

# Lodos-v2开源：GPU并行精确摩擦接触求解器提升仿真吞吐

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[Lodos-v2: An Efficient Primal Formulation of the Exact Frictional Contact Problem](https://arxiv.org/abs/2611.08868)（arXiv 2611.08868）

## 核心内容

针对大规模网格碰撞仿真中接触动力学精度与效率瓶颈，Lodos-v2作为GPU并行刚体动力学框架正式发布。该框架旨在解决前代Lodos-v1因采用锥互补凸松弛导致的法向人工柔顺、切向蠕变及抬升等物理伪影问题，同时突破原有接触组重参数化方案无法兼容关节限位与焊接约束的限制。实验验证表明，新框架在保持高保真度的前提下，实现了较现有主流刚体仿真框架更高的计算吞吐量，源码已在GitHub开源。

技术上，Lodos-v2提出一种高效精确摩擦接触求解算法，在外层近端最小化循环内顺序求解原语形式的级联凸松弛问题，确保接触力计算的物理一致性。架构层面，将接触组重参数化方案扩展至锥互补动力学的原语表述，使其能与全功能仿真器所需的各类约束无缝集成。该方案专为包含大量精细网格碰撞的复杂场景设计，利用GPU大规模并行能力显著提升Sim-to-Real训练数据生成效率，为具身智能算法验证提供高置信度物理引擎支撑。

## 关键看点

- **精确接触求解**：采用外层近端最小化循环内级联求解原语形式凸松弛，消除法向柔顺与切向蠕变伪影
- **约束系统集成**：扩展接触组重参数化至原语形式，支持关节限位与焊接约束联合求解
- **GPU并行加速**：面向大规模精细网格碰撞场景优化，吞吐量超越主流刚体动力学仿真框架
- **开源资产释放**：完整代码托管于martius-lab/lodos仓库，支持具身智能高保真仿真研究

## 工程与产业观察

Lodos-v2通过原语形式精确摩擦接触求解与GPU并行架构，解决了高保真刚体仿真中长期存在的物理伪影与约束兼容性难题。其开源为具身智能领域提供了兼顾精度与吞吐量的Sim-to-Real基础设施，对提升操作技能迁移成功率具有直接工程价值。

## 英文摘要 (Abstract)

Lodos-v2 is a GPU-based simulation framework for massively parallel rigid-body dynamics with contact. It is specifically designed to achieve high throughput in scenes involving collisions among large numbers of detailed meshes. Its predecessor, Lodos-v1, had two main limitations. First, it solved the standard convex relaxation of cone-complementarity-based contact dynamics, thereby inheriting well-known physical artifacts, including lift-off and artificial compliance in the normal direction, as well as creep in the tangential direction. Second, its contact-group reparameterization scheme, which rescales spring-damper forces using a single factor per collision pair, could not be integrated with other constraints required by a full-fledged simulator, such as joint limits and welds. Lodos-v2 addresses both limitations through two main contributions. First, it introduces an efficient algorithm for solving the exact frictional contact problem by sequentially solving a cascade of convex relaxations in primal form within an outer proximal minimization loop. Second, it extends the contact-group reparameterization scheme of Lodos-v1 to the primal formulation of cone-complementarity-based contact dynamics, enabling its integration with the other constraints of a full-fledged simulator. Experiments demonstrate that these contributions result in throughput improvements over established rigid-body simulation frameworks. The source code is available at https://github.com/martius-lab/lodos.

作者：Onur Beker, Andreas Ren\'e Geist, Georg Martius
:::

## 原始参考来源 (Sources)

- [arXiv 2611.08868：Lodos-v2: An Efficient Primal Formulation of the Exact Frictional Contact Problem](https://arxiv.org/abs/2611.08868)