Rescue robotics sets high requirements to perception algorithms due to the unstructured and potentially vision-denied environments. Pivoting Frequency-Modulated Continuous Wave radars are an emerging sensing modality for SLAM in this kind of environment. However, the complex noise characteristics of radar SLAM makes, particularly indoor, applications computationally demanding and slow. In this work, we introduce a novel radar SLAM framework, RaNDT SLAM, that operates fast and generates accurate robot trajectories. The method is based on the Normal Distributions Transform augmented by radar intensity measures. Motion estimation is based on fusion of motion model, IMU data, and registration of the intensity-augmented Normal Distributions Transform. We evaluate RaNDT SLAM in a new benchmark dataset and the Oxford Radar RobotCar dataset. The new dataset contains indoor and outdoor environments besides multiple sensing modalities (LiDAR, radar, and IMU).

翻译：救援机器人技术对感知算法提出了极高要求，因其工作环境通常是非结构化的且可能缺乏视觉信息。调频连续波旋转雷达是此类环境中用于SLAM的一种新兴传感模态。然而，雷达SLAM复杂的噪声特性使得应用（尤其是室内场景）计算量大且运行缓慢。本研究提出了一种新颖的雷达SLAM框架——RaNDT SLAM，该框架运行速度快并能生成精确的机器人运动轨迹。该方法基于通过雷达强度测量增强的正态分布变换。运动估计融合了运动模型、IMU数据以及强度增强正态分布变换的配准结果。我们在新的基准数据集和牛津雷达机器人车数据集上评估了RaNDT SLAM。新数据集除包含室内外环境外，还具备多传感模态（激光雷达、雷达和IMU）。