Active Area Coverage from Equilibrium
This work addresses the challenge of balancing stability and active data acquisition for robots, which is incremental as it builds on hybrid systems theory and sparse Gaussian processes to enhance coverage in specific robotic applications.
The paper tackles the problem of enabling robots to actively collect informative measurements while maintaining stability, achieving this by integrating safe equilibrium policies into active coverage control. The method is demonstrated on tasks such as shape estimation, dynamic model learning for a quadrotor, and generating gaits for a half-cheetah system, showing successful maintenance of Lyapunov attractiveness during data collection.
This paper develops a method for robots to integrate stability into actively seeking out informative measurements through coverage. We derive a controller using hybrid systems theory that allows us to consider safe equilibrium policies during active data collection. We show that our method is able to maintain Lyapunov attractiveness while still actively seeking out data. Using incremental sparse Gaussian processes, we define distributions which allow a robot to actively seek out informative measurements. We illustrate our methods for shape estimation using a cart double pendulum, dynamic model learning of a hovering quadrotor, and generating galloping gaits starting from stationary equilibrium by learning a dynamics model for the half-cheetah system from the Roboschool environment.