[论文解读] Towards navigation without precise localization: Weakly supervised learning of goal-directed navigation cost map
该论文提出了一种弱监督导航框架,利用原始视觉输入、GPS级别定位和导航指令生成目标导向的导航代价图,而无需精确的几何定位。通过采用确定性条件对抗网络学习多样化且语义基础的路径,该系统在定位误差下表现出鲁棒性,并通过与人类驾驶轨迹对比验证的代价图实现有效的运动规划。
Autonomous navigation based on precise localization has been widely developed in both academic research and practical applications. The high demand for localization accuracy has been essential for safe robot planing and navigation while it makes the current geometric solutions less robust to environmental changes. Recent research on end-to-end methods handle raw sensory data with forms of navigation instructions and directly output the command for robot control. However, the lack of intermediate semantics makes the system more rigid and unstable for practical use. To explore these issues, this paper proposes an innovate navigation framework based on the GPS-level localization, which takes the raw perception data with publicly accessible navigation maps to produce an intermediate navigation cost map that allows subsequent flexible motion planning. A deterministic conditional adversarial network is adopted in our method to generate visual goal-directed paths under diverse navigation conditions. The adversarial loss avoids the pixel-level annotation and enables a weakly supervised training strategy to implicitly learn both of the traffic semantics in image perceptions and the planning intentions in navigation instructions. The navigation cost map is then rendered from the goal-directed path and the concurrently collected laser data, indicating the way towards the destination. Comprehensive experiments have been conducted with a real vehicle running in our campus and the results have verified the robustness to localization error of the proposed navigation system.
研究动机与目标
- 为解决在缺乏地标环境中的精确定位限制问题。
- 克服端到端学习型导航系统中僵化和可解释性差的问题。
- 开发一种利用语义线索和粗略定位模仿人类导航的导航框架。
- 生成支持灵活且安全运动规划的导航代价图,而无需像素级标注。
提出的方法
- 使用确定性条件对抗网络从原始图像、GPS定位和导航指令生成视觉目标导向路径。
- 采用弱监督方式训练模型,利用对抗损失避免像素级标注,并隐式学习道路语义和导航意图。
- 将预测路径转换为局部势场,并使用高斯核与基于激光的障碍物数据融合,生成俯视导航代价图。
- 在规划空间中解耦机器人和障碍物状态,将可通行区域、自由空间和障碍物嵌入语义感知的代价图中。
- 框架采用UNet架构处理视觉和导航指令的裁剪输入,提升对定位偏移的鲁棒性。
- 采用离线地图渲染方法,将代价图的预测能力与真实人类驾驶员轨迹进行对比验证。
实验结果
研究问题
- RQ1导航系统是否能在不依赖精确几何定位的情况下,于GPS级别定位误差下实现鲁棒性能?
- RQ2弱监督学习方法如何有效从原始图像和导航指令中捕捉视觉语义和导航意图?
- RQ3所学习的导航代价图在多样化场景中预测类人驾驶行为的程度如何?
- RQ4系统是否能在不同定位偏移下仍生成安全且合理的导航路径?
- RQ5语义道路结构与障碍物数据的融合在多大程度上提升了运动规划的鲁棒性?
主要发现
- 在随机感知偏移下,$\text{rand\_per}$ 模型对定位误差表现出最高鲁棒性,仅在航向精度上略有下降($\Delta{\text{yaw}}/\text{deg}$)。
- 在5米预测距离下,导航代价图的轨迹概率达到86%,在10米时上升至68%,表明其具有出色的预测保真度。
- $\text{rand\_per}$ 模型在复杂场景中表现优于其他模型,其NLL成本更低(10米时为0.384),而 $\text{basic}$ 为0.476,$\text{rand\_navi}$ 为0.514。
- 视觉结果显示,85%的高置信度预测轨迹(概率 >0.85)位于地图的低代价区域。
- 失败案例主要源于导航信号的大幅延迟或提前,但预测路径仍处于安全区域,可通过更新指令进行纠正。
- 导航代价图成功捕捉了类人驾驶行为,经与真实人类轨迹对比验证,支持有效的运动规划。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。