This paper is about fast motion estimation with scanning radar. We use weak supervision to train a focus of attention policy which actively down-samples the measurement stream before data association steps are undertaken. At training, we avoid laborious manual labelling by exploiting shortterm sensor coherence from multiple poses in the presence of an external ego-motion estimator (for example, wheel odometry). In this way, we generate copious annotated measurements which can be used for training a learning algorithm in a weakly-supervised fashion. We demonstrate the validity of the approach in the context of a Radar Odometry (RO) task, prefiltering raw data with a popular image segmentation network trained as presented. We evaluate our system against 26 km of data collected in Central Oxford and show consistent motion estimation with greatly reduced radar processing times (by a factor of 2.36).
This paper is about detecting failures under uncertainty and improving the reliability of radar-only motion estimation. We use weak supervision together with inertial measurement fusion to train a classifier that exploits the principal eigenvector associated with our radar scan matching algorithm at run-time and produces a prior belief in the robot's motion estimate. This prior is used in a filtering framework to correct for vehicle motion estimates. We demonstrate the system on a challenging outdoor dataset, for which current radar motion estimation algorithms fail frequently. By knowing when failure is likely, we achieve qualitatively superior motion estimates and quantitatively fewer odometry failures. Specifically, we see 24.7 % fewer failures in motion estimation over the course of a 15.81 km drive through a difficult, mixed rural-andurban scene, with lower RMSE in translational and rotational estimates during particularly challenging conditions.
This paper presents a method that leverages vehicle motion constraints to refine data associations in a point-based radar odometry system. By using the strong prior on how a nonholonomic robot is constrained to move smoothly through its environment, we develop the necessary framework to estimate ego-motion from a single landmark association rather than considering all of these correspondences at once. This allows for informed outlier detection of poor matches that are a dominant source of pose estimate error. By refining the subset of matched landmarks, we see an absolute decrease of 2.15 % (from 4.68 % to 2.53 %) in translational error, approximately halving the error in odometry (reducing by 45.94 %) than when using the full set of correspondences. This contribution is relevant to other pointbased odometry implementations that rely on a range sensor and provides a lightweight and interpretable means of incorporating vehicle dynamics for ego-motion estimation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.