Velocity Estimation
Velocity estimation, the process of determining the speed and direction of objects or systems, is a crucial area of research with applications spanning robotics, autonomous driving, and human motion analysis. Current research focuses on improving accuracy and robustness across diverse scenarios, employing methods such as Kalman filters with learned dynamics models, spiking neural networks inspired by biological systems, and deep learning architectures that fuse data from multiple sensor modalities (e.g., cameras, radar, IMU). These advancements are driving progress in areas like autonomous navigation, object tracking, and human motion capture, leading to more reliable and efficient systems in various fields.
Papers
NeuroVE: Brain-inspired Linear-Angular Velocity Estimation with Spiking Neural Networks
Xiao Li, Xieyuanli Chen, Ruibin Guo, Yujie Wu, Zongtan Zhou, Fangwen Yu, Huimin Lu
Learning dynamics models for velocity estimation in autonomous racing
Jan Węgrzynowski, Grzegorz Czechmanowski, Piotr Kicki, Krzysztof Walas