Crazyflie
PulseAugur coverage of Crazyflie — every cluster mentioning Crazyflie across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AI models compared for wingbeat counting in flapping-wing vehicles
Researchers have evaluated three types of temporal models—convolutional, spiking, and attention-based—for counting wingbeats in flapping-wing vehicles using optical flow data. The study, conducted in the MuJoCo simulati…
-
New self-adaptive learning method tracks unknown dynamics
Researchers have developed a novel self-adaptive online learning method for control systems designed to track unknown and potentially switching target dynamics. This method simultaneously learns multiple predictors and …
-
New algorithm enables robots to team adaptively in unseen environments · 2 sources tracked
Researchers have introduced the Hypergraphic Open-ended Learning Algorithm (HOLA) to address the challenge of multi-robot teaming in dynamic and unpredictable environments. This new formulation allows robots to adapt to…
-
Crazyflow simulator accelerates drone AI development with JAX
Researchers have developed Crazyflow, a new GPU-accelerated drone simulator built with JAX. This simulator offers significant speed improvements, being over ten times faster for single drones and capable of simulating t…
-
Quadrotor flight control enhanced with adaptive reinforcement learning
Researchers have developed a new adaptive control system for quadrotors using deep reinforcement learning. This system enhances flight control by actively predicting and reacting to real-time disturbances, moving beyond…