#sensor fusion
6 resultsRobust Legged Robot State Estimation Using Factor Graph Optimization
David Wisth, Marco Camurri, Maurice Fallon
The paper introduces a factor‑graph‑based state estimator that tightly fuses inertial, leg, and visual odometry to improve the accuracy of quadruped robots operating on challenging…
Agile Autonomous Driving using End-to-End Deep Imitation Learning
Yunpeng Pan, Ching-An Cheng, Kamil Saigol +4
The paper introduces an end-to-end deep imitation learning system that enables high-speed off‑road autonomous driving using only low‑cost sensors, by training a neural network to m…
Localizing Backscatters by a Single Robot With Zero Start-up Cost
Shengkai Zhang, Wei Wang, Sheyang Tang +2
The paper introduces Rover, a system that lets a single robot equipped with inertial sensors and WiFi locate multiple low‑power backscatter tags indoors without any prior map or la…
Fusion of Sensors Data in Automotive Radar Systems: A Spectral Estimation Approach
Bin Zhu, Augusto Ferrante, Johan Karlsson +1
The paper proposes methods to combine data from multiple automotive radar sensors using multivariate multidimensional spectral estimation, showing that leveraging the magnitude of…
PROBE: Predictive Robust Estimation for Visual-Inertial Navigation
Valentin Peretroukhin, Lee Clement, Matthew Giamou +1
The paper introduces a method that learns to weight visual features based on their predicted impact on localization error, improving accuracy in visual‑inertial navigation systems.
Confidence Propagation through CNNs for Guided Sparse Depth Regression
Abdelrahman Eldesokey, Michael Felsberg, Fahad Shahbaz Khan
The paper introduces a normalized convolution layer that propagates confidence through CNNs to handle highly sparse depth inputs, enabling efficient depth completion by fusing dept…