RaNDT SLAM: Radar SLAM Based on Intensity-Augmented Normal Distributions Transform
This addresses the challenge of perception for rescue robotics in environments where vision fails, though it appears incremental as it builds on existing NDT methods with radar intensity augmentation.
The authors tackled the problem of slow and computationally demanding radar SLAM in unstructured, vision-denied environments by introducing RaNDT SLAM, a framework that uses intensity-augmented Normal Distributions Transform, resulting in fast and accurate robot trajectories as evaluated on new and existing datasets.
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).