Uncertainty-Aware Self-Supervised Learning of Spatial Perception Tasks
This addresses spatial perception challenges for robotics, but it is incremental as it builds on existing self-supervised learning methods by incorporating uncertainty awareness.
The paper tackles the problem of learning spatial perception tasks like object pose estimation and robot localization from onboard sensors using a self-supervised approach that leverages continuous state estimates and sporadic detector supervision. It demonstrates the method in three scenarios, showing it works well and that accounting for uncertainty leads to statistically significant performance improvements.
We propose a general self-supervised learning approach for spatial perception tasks, such as estimating the pose of an object relative to the robot, from onboard sensor readings. The model is learned from training episodes, by relying on: a continuous state estimate, possibly inaccurate and affected by odometry drift; and a detector, that sporadically provides supervision about the target pose. We demonstrate the general approach in three different concrete scenarios: a simulated robot arm that visually estimates the pose of an object of interest; a small differential drive robot using 7 infrared sensors to localize a nearby wall; an omnidirectional mobile robot that localizes itself in an environment from camera images. Quantitative results show that the approach works well in all three scenarios, and that explicitly accounting for uncertainty yields statistically significant performance improvements.