Robostral导航

摘要

大规模部署导航系统需要一种能够最小化传感器假设、跨机器人形态泛化且训练高效的方案。然而，当前最先进的系统仍依赖于深度传感器、多相机阵列或预建地图，这限制了其支持的硬件类型并增加了部署成本。我们提出 Robostral Navigate，一个基于 8B 参数的视觉-语言模型，专为此规模化目标设计。该模型仅需接收单目 RGB 图像流——这是机器人平台上最普遍的传感器——并通过在当前相机视角中指向下一个目标位置来预测航点。纯图像空间操作而非机器人专用坐标的决策方式，使策略自然具备对相机内参及场景尺度变化的鲁棒性，从而无需重新校准即可部署于轮式、足式及空中机器人。我们生成了覆盖 35 万模拟场景的 240 万条轨迹，以减少对真实世界数据采集的依赖并实现轻松扩展。进一步地，我们引入一种前缀缓存训练方案，将完整轨迹打包为单一训练序列，实现训练 token 数量减少 22 倍，训练时间从数月缩短至数天。基于树的注意力掩码机制可防止模型依赖先前真实动作，促进基于视觉感知的动作预测；同时采用强化学习进一步提升探索与恢复能力。在连续环境下的 Room-to-Room 与 Room-Across-Room 基准测试中，Robostral Navigate 刷新了当前最优性能。在 R2R-CE 上，其成功率达 77.4%，超越最佳单目方法 10.5 个百分点，且仅使用单个 RGB 相机即比最先进的深度或多相机系统高出 5.3 个百分点。在 RxR-CE 上，其成功率达 75.1%，全面超越所有单目基线方法。

English

Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently. Yet, today's best systems depend on depth sensors, multi-camera rigs, or pre-built maps, limiting the hardware they support and increasing deployment cost. We introduce Robostral Navigate, an 8B vision-language model built around this scalability objective. The model consumes only a stream of monocular RGB images - the most ubiquitous sensor across robotic platforms and predicts waypoints by pointing to the next target location in the current camera view. Operating purely in image space, rather than robot-specific coordinates, makes the policy naturally robust to changes in camera intrinsics and scene scale, enabling deployment across wheeled, legged, and aerial robots without recalibration. We generate 2.4 million trajectories across 350k simulated scenes to reduce the reliance on real-world data collection and scale easily. We further introduce a prefix-caching training recipe that packs entire episodes into single training sequences, reducing training tokens by 22x and cutting training time from months to days. A tree-based attention mask prevents conditioning on previous ground-truth actions, encouraging visually grounded action prediction, and reinforcement learning is used to further improve exploration and recovery capabilities. On the Room-to-Room and Room-Across-Room in Continuous Environments (R2R-CE and RxR-CE) benchmarks, Robostral Navigate sets a new state of the art. On R2R-CE, it achieves a 77.4% success rate, surpassing the best monocular method by 10.5 points and the strongest depth- or multi-camera system by 5.3 points despite using only a single RGB camera. On RxR-CE, it reaches 75.1% success rate, outperforming all monocular baselines.