Deep Measurement Updates for Bayes Filters
This addresses the need for more automated and general update rules in robotics and state estimation, though it appears incremental as it builds on existing neural network and Bayes filter frameworks.
The paper tackles the problem of hand-crafted heuristics in measurement update rules for Bayes filters by proposing Deep Measurement Update (DMU), a conditional encoder-decoder neural network that processes depth images, achieving good performance on real-world data despite training only on synthetic data.
Measurement update rules for Bayes filters often contain hand-crafted heuristics to compute observation probabilities for high-dimensional sensor data, like images. In this work, we propose the novel approach Deep Measurement Update (DMU) as a general update rule for a wide range of systems. DMU has a conditional encoder-decoder neural network structure to process depth images as raw inputs. Even though the network is trained only on synthetic data, the model shows good performance at evaluation time on real-world data. With our proposed training scheme primed data training , we demonstrate how the DMU models can be trained efficiently to be sensitive to condition variables without having to rely on a stochastic information bottleneck. We validate the proposed methods in multiple scenarios of increasing complexity, beginning with the pose estimation of a single object to the joint estimation of the pose and the internal state of an articulated system. Moreover, we provide a benchmark against Articulated Signed Distance Functions(A-SDF) on the RBO dataset as a baseline comparison for articulation state estimation.