# SHRED：无需专家示范的异构道路用户自博弈

> 原文链接：https://robotics.hellobike.com/papers/2026-10-14-2610-20866
> 频道：papers | 更新日期：2026-10-14 | 标签：arxiv, cs.RO
> 核心摘要：SHRED通过异构自博弈从随机初始化训练车辆、行人和骑行者，并在WOSAC、Waymo零样本和InterPlan上验证。

# SHRED：无需专家示范的异构道路用户自博弈

::: v-pre
> 原文链接：[SHRED: Self-Play for Heterogeneous Road-Users without Expert Demonstrations](https://arxiv.org/abs/2610.20866)（arXiv 2610.20866 · 发布日期：2026-10-14）

**SHRED: Self-Play for Heterogeneous Road-Users without Expert Demonstrations**

SHRED通过异构自博弈从随机初始化训练车辆、行人和骑行者，并在WOSAC、Waymo零样本和InterPlan上验证。

## 核心要点

- 动机：真实交通仿真和自动驾驶规划需要刻画动力学、约束和行为各异的道路用户交互。
- 方法：SHRED从随机初始化进行大规模异构自博弈，联合训练车辆、行人和骑行者，不用示范或轨迹回放。
- 设计：结合类型特定动力学与目标、程序化场景生成和逐智能体随机化，让多样行为在闭环交互中涌现。
- 结果：在WOSAC优于相关自博弈基线，在InterPlan优于比较规划器；消融显示异构性提升真实感和规划性能。

**验证范围与局限**：验证范围为WOSAC、Waymo零样本评估和InterPlan规划基准。

## 英文摘要 (Abstract)

Realistic traffic simulation and autonomous planning both depend on modeling interactions among heterogeneous road users whose dynamics, constraints, and behaviors differ fundamentally. Existing approaches predominantly learn realistic interaction behavior from large-scale human driving demonstrations. In this work, we ask whether such behavior can instead emerge purely through self-play. We present SHRED, a framework that jointly trains vehicles, pedestrians, and cyclists through large-scale heterogeneous self-play from random initialization, without demonstrations or logged-trajectory replay. SHRED combines type-specific dynamics and objectives with procedural scenario generation and per-agent randomization, allowing diverse behaviors to emerge through closed-loop interaction. On the Waymo Open Sim Agents Challenge (WOSAC), SHRED jointly controls all three road-user types and outperforms both the closest demonstration-free self-play baseline and prior self-play methods that use demonstration-trained reference policies. Policies trained only on nuPlan map geometry retain comparable realism under zero-shot evaluation on Waymo. For planning, SHRED outperforms all compared planners on the interaction-heavy InterPlan benchmark. Controlled ablations show that heterogeneity in self-play improves both traffic realism and planning performance, with particularly large planning gains in interaction-heavy scenarios. Together, these results establish heterogeneous procedural self-play as a scalable, demonstration-free paradigm for learning realistic and interactive traffic behavior.

作者：Wei-Jer Chang, Zhouchonghao Wu, Akshay Rangesh, Weixin Li, Masayoshi Tomizuka, Wei Zhan
:::

## 原始参考来源 (Sources)

- [arXiv 2610.20866：SHRED: Self-Play for Heterogeneous Road-Users without Expert Demonstrations](https://arxiv.org/abs/2610.20866)