Qwen-RobotNav技术报告：一种面向智能体导航系统的可扩展导航模型

摘要

智能体导航系统需要一个基础导航模型，其观察策略能在推理阶段通过外部方式重新配置，因为指令跟随、目标搜索、目标跟踪和自动驾驶共享相同的感知-规划主干，却需要截然不同的策略来消费视觉信息流。我们提出Qwen-RobotNav，这是一个基于Qwen-RobotNav构建的可扩展导航模型，通过一个包含两个互补维度的参数化接口来解决这一问题：多种选择导航行为的任务模式，以及控制视觉历史编码方式的可调节观察参数（如令牌预算、各摄像头权重）。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具有鲁棒性，且无需对Qwen-RobotNav主干进行任何架构修改。我们在1560万个样本上训练Qwen-RobotNav；与视觉语言数据的联合训练避免了纯轨迹训练中观察到的退化为响应式动作序列映射器的问题。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，并在回合过程中动态切换Qwen-RobotNav的任务模式和上下文策略，通过重复调用同一模型来组合复杂行为。大量实验表明，Qwen-RobotNav在多个主流导航基准测试中均创下最新最优结果。该模型在参数规模从20亿扩展到80亿时展现出良好扩展性，联合多任务训练形成了跨任务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.