Qwen-RobotNav 技术报告：为智能体导航系统设计的可扩展导航模型
Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System
- Qwen Team（通义实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出 Qwen-RobotNav 可扩展导航模型，通过参数化接口支持多种任务模式和可调观测参数，在15.6M样本上训练，联合视觉语言数据防止行为坍缩，在多个导航基准上取得新最优结果，并展示零样本泛化能力。
AI中文摘要：
智能体导航系统需要一个基础导航模型，其观测策略可以在推理时从外部重新配置，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，但对视觉流的消费方式有根本不同的要求。我们提出 Qwen-RobotNav，一个建立在 Qwen-RobotNav 上的可扩展导航模型，通过一个具有两个互补维度的参数化接口来解决这个问题：多个任务模式选择导航行为，以及可控的观测参数（例如，token 预算、每个摄像头的权重）控制视觉历史的编码方式。通过训练时对所有参数进行随机化，Qwen-RobotNav 对任何推理时配置都具有鲁棒性，无需对 Qwen-RobotNav 主干进行任何架构修改。我们在15.6M样本上训练 Qwen-RobotNav；与视觉语言数据联合训练防止了在仅轨迹训练中观察到的反应性动作序列映射器的坍缩。参数化接口也使 Qwen-RobotNav 成为智能体系统的自然构建块：对于长时域场景，上层规划器将目标分解为子任务，并在情节中动态切换 Qwen-RobotNav 的任务模式和上下文策略，通过重复调用同一模型组合出复杂行为。大量实验表明，Qwen-RobotNav 在主要导航基准上取得了新的最优结果。该模型从2B到8B参数展现出良好的扩展性，联合多任务训练发展出一个跨任务族迁移的共享空间规划基板，并在多样环境中对真实世界机器人展现出强大的零样本泛化能力。
英文摘要：
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.
