Searcharxiv⌕ Search

arXiv subjects

Francesco Borrelli

Publications and source records attributed to Francesco Borrelli.

At least 19 recordsLinked to original sources

Learning Dynamic Games for Cooperative Iterative Tasks

We consider cooperative and iterative tasks involving multiple agents whose interactions are modeled as a dynamic game with shared constraints. We propose a general learning framework applicable to nonlinear and nonconvex dynamic games that uses previously executed feasible trajectories to construct a sampled joint safe set and player-specific cost-to-go functions. At each time step, the agents jointly select a previously sampled terminal state and a Generalized Nash equilibrium used to reach it. A new solution is adopted only if it satisfies a cooperative acceptance rule agreed upon by the players. The framework accommodates individual non-degradation requirements and selection criteria such as weighted costs and Nash bargaining. We show that the proposed framework guarantees recursive feasibility and characterize conditions under which each player's cost is non-increasing across iterations.

cs.RO↗

Interleaved Projected Gradient Descent for Safe Imitation Learning

We propose an imitation-learning design for neural-network control policies under state and input constraints. Training alternates a standard imitation gradient step with a block of $k$ safety steps that pull the network's actions toward their projection onto the safe set; at run time, the controller is the trained network alone, with no safety filter. We analyze this scheme as inexact projected gradient descent in the space of policy actions. When the projected actions are recomputed at every safety step and each step moves the actions consistently toward the safe set, letting $k$ grow logarithmically yields asymptotic constraint satisfaction on the training states and bounds the distance to the constrained optimum of the imitation loss; with the projected actions held fixed, the same holds only if they are exactly representable by the network. On a nonlinear autonomous racing task, we compare our method with adding a weighted constraint-violation penalty to the imitation loss. With a sufficiently large weight, our method matches the lap time of unconstrained imitation while reducing the fraction of violating episodes from $15\%$ to $1\%$, about six times fewer than the penalty approach at its best weight. Its lap times are less sensitive to the weight, which instead sets how quickly violations vanish during training. In racing, the safety corrections are sparse and the conditions of the analysis do not hold; the gain arises instead through the data collected during training. These gains come at the cost of additional training computation.

eess.SY↗

RACER: Residual-Adaptive Closed-Loop Estimation for Sampling-Based Planning in Wheeled-Quadruped Racing

We present RACER, a hierarchical control framework for wheel-based quadruped racing that combines an MPPI planner with a learned residual dynamics model and a low-level RL velocity tracker. The planner augments a nominal unicycle kinematic model with a neural residual term to capture the closed-loop tracking behavior of the RL policy. To train this residual model under limited real-world data, we propose Low-Rank Residual Adaptation (LoRRA), a two-stage approach that pre-trains on large-scale simulation data for broad coverage and then fine-tunes on a small real-world dataset with a low-rank constraint. In simulation, we empirically validate our engineering choices by showing (A) Residual dynamics improve the overall performance of our pipeline by capturing the tracking error of RL velocity tracker at high-speed cornering. (B) Residual dynamics trained with both source-domain and target-domain data gives racing performance significantly better than the residual dynamics trained with only target-domain data. (C) Low-rank constraint at target-domain adaptation gives higher success rates and higher performance than full-tune and from-scratch when domain gap in ground coefficient or joint gain increases.

cs.RO↗

Data-Driven Modeling and Predictive Control of Chronic Diseases: An Ulcerative Colitis Application

The clinical management of chronic disease is naturally structured as a feedback control problem. Physicians observe the disease state at clinic visits and make decisions based on the patient's history and current state. We propose a framework that models the dynamics of chronic disease in response to therapy as an event-based controlled stochastic system, in which treatment decisions are made at discrete, irregularly spaced events while the disease evolves between events as a continuous-time Markov chain (CTMC) with state and input dependent transition rates. We demonstrate this framework in the setting of ulcerative colitis, where we identify the model from real-world clinical data in the electronic health record (EHR) of more than 3,000 patients with ulcerative colitis. Using the learned model, we formulate therapy selection as a model predictive control problem (MPC) that maximizes the expected time spent in inactive disease states, and we evaluate the resulting policy. In closed-loop simulation on 10 patients, the MPC achieves a cost at or below the observed clinical course in the majority of its realizations for 4 of the 10 patients, and its outcomes in all cases are comparable to observed care and within clinical guidelines.

eess.SY↗

An Adaptive-Sampling Control Framework for Constrained Linear Systems with Robust Safety Guarantees

Adaptive-sampling control balances control performance with resource efficiency. However, existing methods either fail to guarantee robust constraint satisfaction during rate transitions or require computationally expensive online optimization. This paper proposes an adaptive-sampling control framework for linear systems subject to polytopic state and input constraints and bounded additive disturbances. Given a time-varying reference control update rate provided by a reasoner, our framework continuously calculates Model Predictive Control (MPC) update rates that ensure robust constraint satisfaction at all time steps. Offline, robust M-step hold control invariance is used to precompute invariant sets for a list of update rates and transition sets between them. Online, these sets are used in real time to guarantee recursive feasibility and finite-time transitions to the reference update rate. The utility of the architecture is demonstrated in a cruise control simulation.

eess.SY↗

Racing a Wheeled Quadruped: Active Load Transfer Mitigation via Model Predictive Control

This paper presents a hierarchical control framework using model predictive control (MPC) and reinforcement learning (RL) for active roll control to manage lateral load transfer during autonomous racing of a wheeled quadruped. The framework integrates offline time-optimal raceline generation, an online MPC planner that actively minimizes the lateral Load Transfer Ratio (LTR), and a low-level, whole-body RL policy deployed directly onto the robot's 16 actuators. The MPC is based on a vehicle dynamics bicycle model of the Unitree Go2-W platform. The robot's leg actuators act as active suspension where knee joints generate anti-roll torque to bank into turns. Physical track experiments demonstrate that active roll control reduces mean LTR by up to 44%, improves the fastest lap time by 8.7%, and boosts peak lateral acceleration capability by 21.3% to 1.98 $m/s^2$, maintaining robust high-speed stability beyond the range of a non-tilting baseline controller. Supplementary code and video can be found at https://github.com/meisman-ucb/go2w-roll-control-mpc

cs.RO↗

Constrained Policy Optimization via Sampling-Based Weight-Space Projection

Safety-critical learning requires policies that improve performance without leaving the safe operating regime. We study constrained policy learning where model parameters must satisfy rollout-based safety constraints that can be evaluated but not differentiated analytically. We propose SCPO, a sampling-based weight-space projection method that enforces safety directly in parameter space without requiring gradient access to the constraint functions. SCPO constructs a local safe region by combining rollout-based safety evaluations with smoothness bounds relating parameter perturbations to changes in safety metrics, and projects each gradient update via a convex QCQP. We establish a safe-by-induction guarantee: starting from any safe initialization, all intermediate policies remain safe given feasible projections. In constrained control settings with a stabilizing backup policy, SCPO further ensures closed-loop stability while enabling safe adaptation beyond the conservative backup. Experiments on constrained regression with harmful supervision and double-integrator imitation with a malicious expert show that SCPO rejects unsafe updates, maintains feasibility throughout training, and achieves meaningful objective improvement.

cs.LG↗

SHIELD: Scalable Optimal Control with Certification using Duality and Convexity

We present SHIELD, a hierarchical algorithm that reduces both the decision-variable dimension and the constraint set in $\ell_1$-regularized convex programs. From strong convexity and Lagrangian duality, we derive certificates that \emph{safely} discard constraints and decision variables while guaranteeing that all removed constraints remain satisfied and all removed variables are null. To further accelerate the proposed algorithm, we propose a transformer-based deep neural network to guide the dual certificate inference. We validate SHIELD on stochastic model predictive control (SMPC) in complex, multi-modal traffic scenarios, comparing against a full-dimensional SMPC policy. Numerical simulations demonstrate order-of-magnitude computational speedups while preserving feasibility and closed-loop safety, highlighting the practicality of certifiably safe, lightweight MPC in complex driving scenes.

cs.RO↗

Safe Adaptive-Sampling Control via Robust M-Step Hold Model Predictive Control

In adaptive-sampling control, the control frequency can be adjusted during task execution. Ensuring that these changes do not jeopardize the safety of the system being controlled requires attention. We introduce robust M-step hold model predictive control (MPC) to address this. Our formulation provides robust constraint satisfaction for an uncertain discrete-time system model with a fixed sampling time subject to an adaptable multi-step input hold (referred to as M-step hold). We show how to ensure recursive feasibility of the MPC utilizing M-step hold extensions of robust invariant sets, and demonstrate how to enable safe adaptive-sampling control via the online selection of M. We evaluate the utility of the robust M-step hold MPC formulation in a cruise control example.

eess.SY↗

Non Normalized Shared-Constraint Dynamic Games for Human-Robot Collaboration with Asymmetric Responsibility

This paper proposes a dynamic game formulation for cooperative human-robot navigation in shared workspaces with obstacles, where the human and robot jointly satisfy shared safety constraints while pursuing a common task. A key contribution is the introduction of a non-normalized equilibrium structure for the shared constraints. This structure allows the two agents to contribute different levels of effort towards enforcing safety requirements such as collision avoidance and inter-players spacing. We embed this non-normalized equilibrium into a receding-horizon optimal control scheme.

cs.RO↗

Energy-Aware Lane Planning for Connected Electric Vehicles in Urban Traffic: Design and Vehicle-in-the-Loop Validation

Urban driving with connected and automated vehicles (CAVs) offers potential for energy savings, yet most eco-driving strategies focus solely on longitudinal speed control within a single lane. This neglects the significant impact of lateral decisions, such as lane changes, on overall energy efficiency, especially in environments with traffic signals and heterogeneous traffic flow. To address this gap, we propose a novel energy-aware motion planning framework that jointly optimizes longitudinal speed and lateral lane-change decisions using vehicle-to-infrastructure (V2I) communication. Our approach estimates long-term energy costs using a graph-based approximation and solves short-horizon optimal control problems under traffic constraints. Using a data-driven energy model calibrated to an actual battery electric vehicle, we demonstrate with vehicle-in-the-loop experiments that our method reduces motion energy consumption by up to 24 percent compared to a human driver, highlighting the potential of connectivity-enabled planning for sustainable urban autonomy.

eess.SY↗

Parking of Connected Automated Vehicles: Vehicle Control, Parking Assignment, and Multi-agent Simulation

This paper introduces a comprehensive approach to optimize parking efficiency for connected and Automated vehicle (CAVs) fleets. We present a multi-vehicle parking simulator, equipped with hierarchical path planning and collision avoidance capabilities for individual CAVs. The simulator is designed to capture the key decision-making processes in parking, from low-level vehicle control to high-level parking assignment, and it enables the effective assessment of parking strategies for large fleets of ground vehicles. We formulate and compare different strategic parking spot assignments to minimize a collective cost. While the proposed framework is designed to optimize various objective functions, we choose the total parking time for the experiment, as it directly reflects the congestion level and the cost associated with the parking efficiency. We validate the effectiveness of the proposed strategies through an empirical evaluation against a dataset of real-world parking lot dynamics, realizing a substantial reduction in parking time by up to 43.8%. This improvement is attributed to the synergistic benefits of driving automation, the utilization of shared infrastructure state data, the exclusion of pedestrian traffic, and the real-time computation of optimal parking spot allocation.

eess.SY↗

Generalized Nash Equilibrium Solutions in Dynamic Games With Shared Constraints

In dynamic games with shared constraints, Generalized Nash Equilibria (GNE) are often computed using the normalized solution concept, which assumes identical Lagrange multipliers for shared constraints across all players. While widely used, this approach excludes other potentially valuable GNE. This paper presents a novel method based on the Mixed Complementarity Problem (MCP) formulation to compute non-normalized GNE, expanding the solution space. We also propose a systematic approach for selecting the optimal GNE based on predefined criteria, enhancing practical flexibility. Numerical examples illustrate the methods effectiveness, offering an alternative to traditional normalized solutions.

cs.RO↗

Robust MPC for Uncertain Linear Systems -- Combining Model Adaptation and Iterative Learning

This paper presents a robust adaptive learning Model Predictive Control (MPC) framework for linear systems with parametric uncertainties and additive disturbances performing iterative tasks. The approach refines the parameter estimates online using set-membership estimation. Performance enhancement over iterations is achieved by learning the terminal cost from data. Safety is enforced using a terminal set, which is also learned iteratively. The proposed method guarantees recursive feasibility, constraint satisfaction, and a robust bound on the closed-loop cost. Numerical simulations on a mass-spring-damper system demonstrate improved computational efficiency and control performance compared to a robust adaptive MPC scheme without iterative learning of the terminal ingredients.

eess.SY↗

Regulation-Aware Game-Theoretic Motion Planning for Autonomous Racing

This paper presents a regulation-aware motion planning framework for autonomous racing scenarios. Each agent solves a Regulation-Compliant Model Predictive Control problem, where racing rules - such as right-of-way and collision avoidance responsibilities - are encoded using Mixed Logical Dynamical constraints. We formalize the interaction between vehicles as a Generalized Nash Equilibrium Problem (GNEP) and approximate its solution using an Iterative Best Response scheme. Building on this, we introduce the Regulation-Aware Game-Theoretic Planner (RA-GTP), in which the attacker reasons over the defender's regulation-constrained behavior. This game-theoretic layer enables the generation of overtaking strategies that are both safe and non-conservative. Simulation results demonstrate that the RA-GTP outperforms baseline methods that assume non-interacting or rule-agnostic opponent models, leading to more effective maneuvers while consistently maintaining compliance with racing regulations.

eess.SY↗

A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous Racing

Guaranteeing constraint satisfaction is challenging in imitation learning (IL), particularly in tasks that require operating near a system's handling limits. Traditional IL methods, such as Behavior Cloning (BC), often struggle to enforce constraints, leading to suboptimal performance in high-precision tasks. In this paper, we present a simple approach to incorporating safety into the IL objective. Through simulations, we empirically validate our approach on an autonomous racing task with both full-state and image feedback, demonstrating improved constraint satisfaction and greater consistency in task performance compared to BC.

cs.LG↗

A learning model predictive control for virtual coupling in railroads

The objective of this paper is to present a novel intelligent train control system for virtual coupling in railroads based on a Learning Model Predictive Control (LMPC). Virtual coupling is an emerging railroad technology that reduces the distance between trains to increase the capacity of the line, whereas LMPC is an optimization-based controller that incorporates artificial intelligence methods to improve its control policies. By incorporating data from past experiences into the optimization problem, LMPC can learn unmodeled dynamics and enhance system performance while satisfying constraints. The LMPC developed in this paper is simulated and compared, in terms of energy consumption, with a general MPC, without learning capabilities. The simulations are divided into two main practical applications: a LMPC applied only to the rear trains (followers) and a LMPC applied to both the followers and the first front train of the convoy (leader). Within each application, the LMPC is independently tested for three railroad categories: metro, regional, and high-speed. The results show that the LMPC reduces energy consumption in all simulation cases while approximately maintaining speed and travel time. The effect is more pronounced in rail applications with frequent speed variations, such as metro systems, compared to high-speed rail. Future research will investigate the impact of using real-world data in place of simulated data.

math.OC↗

Learning Two-agent Motion Planning Strategies from Generalized Nash Equilibrium for Model Predictive Control

We introduce an Implicit Game-Theoretic MPC (IGT-MPC), a decentralized algorithm for two-agent motion planning that uses a learned value function that predicts the game-theoretic interaction outcomes as the terminal cost-to-go function in a model predictive control (MPC) framework, guiding agents to implicitly account for interactions with other agents and maximize their reward. This approach applies to competitive and cooperative multi-agent motion planning problems which we formulate as constrained dynamic games. Given a constrained dynamic game, we randomly sample initial conditions and solve for the generalized Nash equilibrium (GNE) to generate a dataset of GNE solutions, computing the reward outcome of each game-theoretic interaction from the GNE. The data is used to train a simple neural network to predict the reward outcome, which we use as the terminal cost-to-go function in an MPC scheme. We showcase emerging competitive and coordinated behaviors using IGT-MPC in scenarios such as two-vehicle head-to-head racing and un-signalized intersection navigation. IGT-MPC offers a novel method integrating machine learning and game-theoretic reasoning into model-based decentralized multi-agent motion planning.

cs.MA↗