Prescribing optimal operation based on the condition of the system and, thereby, potentially prolonging the remaining useful lifetime has a large potential for actively managing the availability, maintenance and costs of complex systems. Reinforcement learning (RL) algorithms are particularly suitable for this type of problems given their learning capabilities. A special case of a prescriptive operation is the power allocation task, which can be considered as a sequential allocation problem, where the action space is bounded by a simplex constraint. A general continuous action-space solution of such sequential allocation problems has still remained an open research question for RL algorithms. In continuous action-space, the standard Gaussian policy applied in reinforcement learning does not support simplex constraints, while the Gaussian-softmax policy introduces a bias during training. In this work, we propose the Dirichlet policy for continuous allocation tasks and analyze the bias and variance of its policy gradients. We demonstrate that the Dirichlet policy is bias-free and provides significantly faster convergence, better performance and better hyperparameters robustness over the Gaussian-softmax policy. Moreover, we demonstrate the applicability of the proposed algorithm on a prescriptive operation case, where we propose the Dirichlet power allocation policy and evaluate the performance on a case study of a set of multiple lithium-ion (Li-I) battery systems. The experimental results show the potential to prescribe optimal operation, improve the efficiency and sustainability of multi-power source systems.
Flying manipulators are aerial drones with attached rigid-bodied robotic arms and belong to the latest and most actively developed research areas in robotics. The rigid nature of these arms often lack compliance, flexibility, and smoothness in movement. This work proposes to use a soft-bodied robotic arm attached to an omnidirectional micro aerial vehicle (OMAV) to leverage the compliant and flexible behavior of the arm, while remaining maneuverable and dynamic thanks to the omnidirectional drone as the floating base. The unification of the arm with the drone poses challenges in the modeling and control of such a combined platform; these challenges are addressed with this work. We propose a unified model for the flying manipulator based on three modeling principles: the Piecewise Constant Curvature (PCC) and Augmented Rigid Body Model (ARBM) hypotheses for modeling soft continuum robots and a floating-base approach borrowed from the traditional rigid-body robotics literature. To demonstrate the validity and usefulness of this parametrisation, a hierarchical model-based feedback controller is implemented. The controller is verified and evaluated in simulation on various dynamical tasks, where the nullspace motions, disturbance recovery, and trajectory tracking capabilities of the platform are examined and validated. The soft flying manipulator platform could open new application fields in aerial construction, goods delivery, human assistance, maintenance, and warehouse automation.
Reinforcement learning (RL) is promising for complicated stochastic nonlinear control problems. Without using a mathematical model, an optimal controller can be learned from data evaluated by certain performance criteria through trial-and-error. However, the data-based learning approach is notorious for not guaranteeing stability, which is the most fundamental property for any control system. In this paper, the classic Lyapunov's method is explored to analyze the uniformly ultimate boundedness stability (UUB) solely based on data without using a mathematical model. It is further shown how RL with UUB guarantee can be applied to control dynamic systems with safety constraints. Based on the theoretical results, both off-policy and on-policy learning algorithms are proposed respectively. As a result, optimal controllers can be learned to guarantee UUB of the closed-loop system both at convergence and during learning. The proposed algorithms are evaluated on a series of robotic continuous control tasks with safety constraints. In comparison with the existing RL algorithms, the proposed method can achieve superior performance in terms of maintaining safety. As a qualitative evaluation of stability, our method shows impressive resilience even in the presence of external disturbances.
Deep Reinforcement Learning (DRL) has achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation. However, stability is not guaranteed in DRL. From a control-theoretic perspective, stability is the most important property for any control system, since it is closely related to safety, robustness, and reliability of robotic systems. In this paper, we propose a DRL framework with stability guarantee by exploiting the Lyapunov's method in control theory. A sampling-based stability theorem is proposed for stochastic nonlinear systems modeled by the Markov decision process. Then we show that the stability condition could be exploited as a critic in the actor-critic RL framework and propose an efficient DRL algorithm to learn a controller/policy with a stability guarantee. In the simulated experiments, our approach is evaluated on several well-known examples including the classic CartPole balancing, 3-dimensional robot control, and control of synthetic biology gene regulatory networks. As a qualitative evaluation of stability, we show that the learned policies can enable the systems to recover to the equilibrium or tracking target when interfered by uncertainties such as unseen disturbances and system parametric variations to a certain extent.
Reinforcement learning is showing great potentials in robotics applications, including autonomous driving, robot manipulation and locomotion. However, with complex uncertainties in the real-world environment, it is difficult to guarantee the successful generalization and sim-to-real transfer of learned policies theoretically. In this paper, we introduce and extend the idea of robust stability and $H_\infty$ control to design policies with both stability and robustness guarantee. Specifically, a sample-based approach for analyzing the Lyapunov stability and performance robustness of a learning-based control system is proposed. Based on the theoretical results, a maximum entropy algorithm is developed for searching Lyapunov function and designing a policy with provable robust stability guarantee. Without any specific domain knowledge, our method can find a policy that is robust to various uncertainties and generalizes well to different test environments. In our experiments, we show that our method achieves better robustness to both large impulsive disturbances and parametric variations in the environment than the state-of-art results in both robust and generic RL, as well as classic control. Anonymous code is available to reproduce the experimental results at https://github.com/RobustStabilityGuaranteeRL/RobustStabilityGuaranteeRL.