FORESEER: Recognize and Utilize Uncertainties by Integrating Data-Based Learning and Symbolic Feedback

Jindou Jia, Kexin Guo, Yuyang Wang, Sicheng Zhou, Jiayi Zhang, Yuhang Liu,

Xiang Yu, Yang Shi, Lei Guo

Abstract—Uncertainties resulting from intricate internal model and external environmental disturbances significantly degrade robot planning and control performance. However, recognizing such persistently varying uncertainties in an explainable and lightweight manner is exceptionally challenging. We present two converged uncertainty prediction frameworks through the Fusion of Online Reactive Estimation and Sustained Experience Exploitation for Robots (FORESEER), enabling accurate prediction of two general kinds of uncertainties, respectively. Both frameworks feature properties of precision, lightweight, universality, and stability, in comparison with existing solutions. At first, a prediction algorithm for nonlinearly parametric uncertainties is developed by merging analytical basis learning with online symbolic adaptive estimation. Furthermore, an online prediction algorithm for composite uncertainties is proposed by seamlessly integrating learning-based feedforward and model-based/symbolic feedback techniques. Benchmark comparisons on flying drones showcase the accuracy of the FORESEER on various real uncertainties including mass, aerodynamic drag, rain, and rope tension, leading to subsequent high-precision control. Moreover, an energy-saving and time-saving planning strategy is presented by utilizing the predicted wind. The developed algorithms hold the promising potential for direct combination with existing planning/control algorithms, promoting the environmental adaptability of robots.

Overview of this work

Five types of drones are employed in this work. A. A drone with a gripper (named Capturer) is commanded to capture an unknown target and maneuver aggressively. B. The algorithm developed for the Capturer is generalized to a small faster drone seamlessly. C. A waterproof drone flies under the high aerodynamic drag and rain disturbance. A foam board is attached to the drone to increase the drag. D. Planning an energy-saving and time-saving trajectory by utilizing the external wind. E. A flying drone drags a car with an inelastic rope, which tension changes rapidly. The mass uncertainty in (A-B) is a kind of parametric uncertainty, while uncertainties in (C-E) belong to the composite uncertainty affected by both internal and external factors.