Keep off the Grass: Permissible Driving Routes from Radar with Weak Audio Supervision

Abstract

Reliable outdoor deployment of mobile robots requires the robust identification of permissible driving routes in a given environment. The performance of LiDAR and vision-based perception systems deteriorates significantly if certain environmental factors are present e.g. rain, fog, darkness. Perception systems based on Frequency-Modulated Continuous Wave scanning radar maintain full performance regardless of environmental conditions and with a longer range than alternative sensors. Learning to segment a radar scan based on driveability in a fully supervised manner is not feasible as labelling each radar scan on a bin-by-bin basis is both difficult and time-consuming to do by hand. We therefore weakly supervise the training of the radarbased classifier through an audio-based classifier that is able to predict the terrain type underneath the robot. By combining odometry, GPS and the terrain labels from the audio classifier, we are able to construct a terrain labelled trajectory of the robot in the environment which is then used to label the radar scans. Using a curriculum learning procedure, we then train a radar segmentation network to generalise beyond the initial labelling and to detect all permissible driving routes in the environment.

Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning

“…A related avenue of research has been to localize radar scans using existing satellite imagery [46] [47]. Further research has tackled radar-based perception through occupancy [48], traversability [12,49], and semantic segmentation [30].…”

Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning

“…A related avenue of research has been to localize radar scans using existing satellite imagery [41] [42]. Further research has tackled radar-based perception through occupancy [43], traversability [10,44], and semantic segmentation [27].…”

On the Road: Route Proposal from Radar Self-Supervised by Fuzzy LiDAR Traversability

“…Consider, however, as a broad sweep of the available prior work, that state-of-the-art systems using hundreds of hours of driving data to train models which can understand where a vehicle must drive are well developed in the camera domain, such as for [3], and more recently in [4]. The most relevant radar system available currently is that of [5], which is shown only to segment grassy areas from gravel areas-with traversability being dictated by the designers rather than understood by the algorithm through geometry as in this work.…”

“…In comparison, path proposal based on radar is in its infancy, despite its advantages over both LiDAR and vision. Early work in this area includes [5], where an approach is presented for learning permissible paths in radar using audio data for weak supervision.…”

“…Nevertheless, a crisp distinction between what is traversable and what is not is less representative for what the autonomous vehicle (AV) will experience in a real-world deployment-plenty of surfaces are driveable, but not ideally so-and a continuous traversability score can lead to more robust and effective path-planning policies, enabling more flexible operation. In this light, previous works [5,17] have used generative models to recover categorical representations of traversability from radar scans; this work, in contrast, aims to relax this assumption by directly regressing a continuous-valued traversability score. However, the extension to continuous traversability scores is less clear.…”