Qwen-RobotNav技術報告：一個可擴展的導航模型，專為代理性導航系統設計

摘要

智能体导航系统需要一个基础导航模型，其观察策略可在推理时通过外部重新配置，这是因为指令跟随、目标搜索、目标追踪和自动驾驶共享相同的感知-规划主干网络，却需要截然不同的策略来消耗视觉流。我们提出Qwen-RobotNav，一个基于Qwen-RobotNav构建的可扩展导航模型，通过一个参数化接口解决该问题，该接口具有两个互补维度：选择导航行为的多种任务模式，以及控制视觉历史编码方式的可调观察参数（例如令牌预算、相机权重）。通过在训练时对所有参数进行随机化处理，Qwen-RobotNav对任何推理时配置均保持鲁棒性，且无需对Qwen-RobotNav主干网络进行任何架构修改。我们在1560万样本上训练Qwen-RobotNav；与视觉-语言数据的联合训练阻止了仅在轨迹数据训练中观察到的向反应式动作序列映射器退化的现象。参数化接口还使Qwen-RobotNav成为智能体系统的天然构建模块：对于长时域场景，上层规划器将目标分解为子任务，并在任务过程中动态切换Qwen-RobotNav的任务模式与上下文策略，通过反复调用同一模型来组合出复杂行为。大量实验表明，Qwen-RobotNav在主要导航基准测试中取得了新的最优结果。模型在参数量从2B扩展到8B时表现出良好的可扩展性，联合多任务训练形成了跨任务家族迁移的共享空间规划基础，并在多样化的真实世界机器人环境中展现出强大的零样本泛化能力。

English

Agentic navigation systems require a base navigation model whose observation strategy can be externally reconfigured at inference time, because instruction following, object search, target tracking, and autonomous driving share the same perception-planning backbone yet demand fundamentally different strategies for consuming the visual stream. We present Qwen-RobotNav, a scalable navigation model built on Qwen-RobotNav that addresses it through a parameterised interface with two complementary dimensions: multiple task modes that select the navigation behaviour, and controllable observation parameters (e.g., token budget, per-camera weights) that govern how visual history is encoded. With training-time randomization over all parameters, Qwen-RobotNav is robust to any inference-time configuration requiring zero architectural modification to the Qwen-RobotNav backbone. We train Qwen-RobotNav on 15.6M samples; co-training with vision-language data prevents the collapse into reactive action-sequence mappers observed in trajectory-only training. The parameterised interface also makes Qwen-RobotNav a natural building block for agentic systems: for long-horizon scenarios, an upper-level planner decomposes goals into sub-tasks and dynamically switches Qwen-RobotNav's task mode and context strategy mid-episode, composing complex behaviours from repeated calls to the same model. Extensive experiments show that Qwen-RobotNav sets new state-of-the-art results across major navigation benchmarks. The model exhibits favourable scaling from 2B to 8B parameters, with joint multi-task training developing a shared spatial-planning substrate that transfers across task families, and demonstrates strong zero-shot generalisation to real-world robots across diverse environments.