RoadRunner -- Learning Traversability Estimation for Autonomous Off-road Driving

📄 arXiv: 2402.19341v3 📥 PDF

作者: Jonas Frey, Manthan Patel, Deegan Atha, Julian Nubert, David Fan, Ali Agha, Curtis Padgett, Patrick Spieler, Marco Hutter, Shehryar Khattak

分类: cs.RO, cs.CV

发布日期: 2024-02-29 (更新: 2024-08-30)

备注: accepted for IEEE Transactions on Field Robotics (T-FR)


💡 一句话要点

提出RoadRunner以解决自主越野驾驶的可通行性估计问题

🎯 匹配领域: 支柱三:空间感知与语义 (Perception & Semantics)

关键词: 自主驾驶 越野导航 可通行性估计 传感器融合 自监督学习

📋 核心要点

  1. 现有方法在高速越野驾驶中面临图像质量下降和几何信息稀疏的问题,影响导航的可靠性。
  2. RoadRunner通过融合相机和LiDAR传感器数据,采用自监督学习方式,直接预测地形的可通行性和高程图。
  3. 实验结果表明,RoadRunner将系统延迟从500毫秒降低至140毫秒,同时提高了可通行性和高程图的预测准确性。

📝 摘要(中文)

自主越野驾驶在高速行驶时需要机器人全面理解周围环境,仅依靠车载传感器。越野环境的极端条件可能导致相机图像质量下降,光照不足和运动模糊,同时在高速行驶时LiDAR传感器提供的几何信息稀疏。本文提出了RoadRunner,一个新颖的框架,能够直接从相机和LiDAR传感器输入中预测地形可通行性和高程图。RoadRunner通过融合传感器信息、处理不确定性并生成关于地形几何和可通行性的上下文信息预测,从而实现可靠的自主导航。与现有依赖手工语义类别和启发式方法预测可通行性成本的方法不同,我们的方法采用自监督的端到端训练方式。RoadRunner网络架构基于流行的传感器融合网络架构,将LiDAR和相机信息嵌入到共同的鸟瞰视角中。通过利用现有的可通行性估计堆栈生成训练数据,RoadRunner将系统延迟从500毫秒降低到140毫秒,同时提高了可通行性成本和高程图预测的准确性。

🔬 方法详解

问题定义:本文旨在解决自主越野驾驶中对环境的可通行性估计问题。现有方法依赖手工设计的语义类别和启发式规则,导致在复杂环境下的导航性能不足。

核心思路:RoadRunner通过融合相机和LiDAR数据,采用自监督学习的方式进行端到端训练,直接预测地形的可通行性和高程图,从而提高了模型的适应性和准确性。

技术框架:RoadRunner的整体架构包括数据预处理、传感器信息融合、特征提取和可通行性预测模块。通过将LiDAR和相机信息转换为鸟瞰视角,增强了信息的互补性。

关键创新:RoadRunner的主要创新在于其自监督学习框架,避免了手工特征设计的局限性,能够在真实世界数据中自动生成训练样本。与传统方法相比,RoadRunner在处理不确定性和实时性方面表现更优。

关键设计:在网络结构上,RoadRunner采用了流行的传感器融合网络架构,设计了适应性损失函数以优化可通行性和高程图的预测精度,同时通过高效的模型设计降低了系统延迟。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

RoadRunner在实验中将系统延迟从500毫秒降低至140毫秒,提升了可通行性成本和高程图预测的准确性,展示了其在复杂越野环境下的有效性和可靠性。

🎯 应用场景

RoadRunner的研究成果在自主驾驶、农业机器人、探险机器人等领域具有广泛的应用潜力。通过提高越野环境下的导航安全性和可靠性,该技术可为未来的无人驾驶系统提供更强的环境适应能力,推动相关领域的发展。

📄 摘要(原文)

Autonomous navigation at high speeds in off-road environments necessitates robots to comprehensively understand their surroundings using onboard sensing only. The extreme conditions posed by the off-road setting can cause degraded camera image quality due to poor lighting and motion blur, as well as limited sparse geometric information available from LiDAR sensing when driving at high speeds. In this work, we present RoadRunner, a novel framework capable of predicting terrain traversability and an elevation map directly from camera and LiDAR sensor inputs. RoadRunner enables reliable autonomous navigation, by fusing sensory information, handling of uncertainty, and generation of contextually informed predictions about the geometry and traversability of the terrain while operating at low latency. In contrast to existing methods relying on classifying handcrafted semantic classes and using heuristics to predict traversability costs, our method is trained end-to-end in a self-supervised fashion. The RoadRunner network architecture builds upon popular sensor fusion network architectures from the autonomous driving domain, which embed LiDAR and camera information into a common Bird's Eye View perspective. Training is enabled by utilizing an existing traversability estimation stack to generate training data in hindsight in a scalable manner from real-world off-road driving datasets. Furthermore, RoadRunner improves the system latency by a factor of roughly 4, from 500 ms to 140 ms, while improving the accuracy for traversability costs and elevation map predictions. We demonstrate the effectiveness of RoadRunner in enabling safe and reliable off-road navigation at high speeds in multiple real-world driving scenarios through unstructured desert environments.