State Estimation
State estimation aims to accurately determine the current state of a system—be it a robot, vehicle, or other dynamic entity—by fusing data from various sensors and incorporating models of system dynamics. Current research emphasizes robust and efficient algorithms, such as Kalman filters (including variations like Invariant Extended Kalman Filters and Moving Horizon Estimation), particle filters, and neural network-based approaches, to handle nonlinearity, sensor noise, and uncertainties in complex environments. These advancements are crucial for improving the performance and reliability of autonomous systems in diverse applications, ranging from robotics and autonomous driving to marine navigation and multi-agent coordination.
Papers
State estimation of urban air pollution with statistical, physical, and super-learning graph models
Matthieu Dolbeault, Olga Mula, Agustín Somacal
Estimation of conditional average treatment effects on distributed confidential data
Yuji Kawamata, Ryoki Motai, Yukihiko Okada, Akira Imakura, Tetsuya Sakurai
A Group Theoretic Metric for Robot State Estimation Leveraging Chebyshev Interpolation
Varun Agrawal, Frank Dellaert
OptiState: State Estimation of Legged Robots using Gated Networks with Transformer-based Vision and Kalman Filtering
Alexander Schperberg, Yusuke Tanaka, Saviz Mowlavi, Feng Xu, Bharathan Balaji, Dennis Hong