Marco M. Nicotra

Marco M. Nicotra, Dominic Liao-McPherson, Ilya V. Kolmanovsky

This paper introduces a continuous-time constrained nonlinear control scheme which implements a model predictive control strategy as a continuous-time dynamic system. The approach is based on the idea that the solution of the optimal control problem can be embedded into the internal states of a dynamic control law which runs in parallel to the system. Using input to state stability arguments, it is shown that if the controller dynamics are sufficiently fast with respect to the plant dynamics, the interconnection between the two systems is asymptotically stable. Additionally, it is shown that, by augmenting the proposed scheme with an add-on unit known as an Explicit Reference Governor, it is possible to drastically increase the set of initial conditions that can be steered to the desired reference without violating the constraints. Numerical examples demonstrate the effectiveness of the proposed scheme.

Marco M. Nicotra, Tam Nguyen, Emanuele Garone et al.

This paper introduces an explicit reference governor approach for controlling time delay linear systems subject to state and input constraints. The proposed framework relies on suitable invariant sets that can be built using both Lyapunov-Razumikhin and Lyapunov-Krasovskii arguments. The proposed method is validated both numerically and experimentally using several alternative formulations.

Victor Freire, Marco M. Nicotra

This paper presents an approach to design control barrier functions (CBFs) for arbitrary state and input constraints using tools from the reference governor literature. In particular, it is shown that dynamic safety margins (DSMs) are CBFs for an augmented system obtained by concatenating the state with a virtual reference. The proposed approach is agnostic to the relative degree and can handle multiple state and input constraints using the control-sharing property of CBFs. The construction of CBFs using Lyapunov-based DSMs is then investigated in further detail. Numerical simulations show that the method outperforms existing DSM-based approaches, while also guaranteeing safety and persistent feasibility of the associated optimization program.

Yaashia Gautam, Gilberto Briscoe-Martinez, Adhitya Mohan et al.

This paper introduces the Compliant Explicit Reference Governor (CERG), a modular reference management system that enables robots to interact physically with their environment under provable guarantees. The CERG is an intermediate layer that can be placed between a high-level planner and a low-level controller: it enforces operational constraints and enables smooth transitions between free-motion and contact operations. The CERG ensures safety by limiting the total energy available to the robotic arm at the time of contact. In the absence of contact, however, the CERG does not penalize the system performance. Simulation and hardware experiments validate the CERG on increasingly complex systems.

Guohui Ding, Joewie J. Koh, Kelly Merckaert et al.

We consider solving a cooperative multi-robot object manipulation task using reinforcement learning (RL). We propose two distributed multi-agent RL approaches: distributed approximate RL (DA-RL), where each agent applies Q-learning with individual reward functions; and game-theoretic RL (GT-RL), where the agents update their Q-values based on the Nash equilibrium of a bimatrix Q-value game. We validate the proposed approaches in the setting of cooperative object manipulation with two simulated robot arms. Although we focus on a small system of two agents in this paper, both DA-RL and GT-RL apply to general multi-agent systems, and are expected to scale well to large systems.

Dominic Liao-McPherson, Marco Nicotra, Ilya Kolmanovsky

Suboptimal model predictive control is a technique that can reduce the computational cost of model predictive control (MPC) by exploiting its robustness to incomplete optimization. Instead of solving the optimal control problem exactly, this method maintains an estimate of the optimal solution and updates it at each sampling instance. The resulting controller can be viewed as a dynamic compensator which runs in parallel with the plant. This paper explores the use of the semismooth predictor-corrector method to implement suboptimal MPC. The dynamic interconnection of the combined plant-optimizer system is studied using the input-to-state stability framework and sufficient conditions for closed-loop asymptotic stability and constraint enforcement are derived using small gain arguments. Numerical simulations demonstrate the efficacy of the scheme.