arXiv subjects

Paolo Robuffo Giordano

Publications and source records attributed to Paolo Robuffo Giordano.

14 recordsLinked to original sources

arXiv2026

Sampling-Based Coordination-Informed Multi-Objective Multi-Robot Reinforcement Learning

Multi-robot systems must simultaneously optimize competing objectives while maintaining coordinated behavior. Existing multi-agent reinforcement learning approaches often rely on fixed or centralized coordination, which limits adaptability and violates distributed constraints. This work introduces the Coordination-Informed Multi-Objective Reinforcement Learning (CIMORL) framework, integrating a distributed weight prediction mechanism, a privileged expert training strategy, and theoretical guarantees for Pareto-optimal solutions. We present the base CIMORL method alongside two sampling-based variants, CIMORL-TS (Tree Search) and CIMORL-MPPI (MPPI), which leverage privileged global information during training to enable fully decentralized deployment. Experimental validation in cooperative and adversarial scenarios demonstrates a $21.2\%$ hypervolume improvement and superior policy stability compared to state-of-the-art baselines. Real-world experiments with Crazyflie drones further validate the framework's robustness in resource allocation and multi-attacker multi-defend scenarios under partial observability.

cs.RO↗

arXiv2026

A Gated Graph Neural Network Approach to Fast-Convergent Dynamic Average Estimation

Dynamic average estimation is a critical problem in multi-agent systems, enabling agents to collaboratively estimate time-varying signals using only local information exchange. Traditional model-based approaches often face challenges related to convergence speed and sensitivity to network topology changes. This paper introduces a novel learning-based solution leveraging Gated Graph Neural Networks (GGNNs) for fast-convergent dynamic average estimation in a fully distributed manner. Taking advantage of the inherent structure of GGNNs, the proposed method models the estimation process as a distributed autoregressor, ensuring rapid convergence while maintaining stability. We incorporate a regularization term during training to enforce convergence guarantees and introduce an encoding-decoding mechanism to reduce communication overhead without sacrificing accuracy compared to standard GGNNs. Extensive numerical experiments demonstrate that our approach significantly outperforms conventional model-based estimators in terms of both convergence speed and precision, making it a promising alternative for multi-agent applications that require dynamic average estimation.

cs.LG↗

arXiv2026

Impact-Robust Posture Optimization for Aerial Manipulation

We present a novel method for optimizing the posture of kinematically redundant torque-controlled robots to improve robustness during impacts. A rigid impact model is used as the basis for a configuration-dependent metric that quantifies the variation between pre- and post-impact velocities. By finding configurations (postures) that minimize the aforementioned metric, spikes in the robot's state and input commands can be significantly reduced during impacts, improving safety and robustness. The problem of identifying impact-robust postures is posed as a min-max optimization of the aforementioned metric. To overcome the real-time intractability of the problem, we reformulate it as a gradient-based motion task that iteratively guides the robot towards configurations that minimize the proposed metric. This task is embedded within a task-space inverse dynamics (TSID) whole-body controller, enabling seamless integration with other control objectives. The method is applied to a kinematically redundant aerial manipulator performing repeated point contact tasks. We test our method inside a realistic physics simulator and compare it with the nominal TSID. Our method leads to a reduction (up to 51% w.r.t. standard TSID) of post-impact spikes in the robot's configuration and successfully avoids actuator saturation. Moreover, we demonstrate the importance of kinematic redundancy for impact robustness using additional numerical simulations on a quadruped and a humanoid robot, resulting in up to 45% reduction of post-impact spikes in the robot's state w.r.t. nominal TSID.

cs.RO↗

arXiv2026

Decentralized Reinforcement Learning for Multi-Agent Multi-Resource Allocation via Dynamic Cluster Agreements

This paper addresses the challenge of allocating heterogeneous resources among multiple agents in a decentralized manner. Our proposed method, Liquid-Graph-Time Clustering-IPPO, builds upon Independent Proximal Policy Optimization (IPPO) by integrating dynamic cluster consensus, a mechanism that allows agents to form and adapt local sub-teams based on resource demands. This decentralized coordination strategy reduces reliance on global information and enhances scalability. We evaluate LGTC-IPPO against standard multi-agent reinforcement learning baselines and a centralized expert solution across a range of team sizes and resource distributions. Experimental results demonstrate that LGTC-IPPO achieves more stable rewards, better coordination, and robust performance even as the number of agents or resource types increases. Additionally, we illustrate how dynamic clustering enables agents to reallocate resources efficiently also for scenarios with discharging resources.

stat.ML↗

arXiv2025

Liquid-Graph Time-Constant Network for Multi-Agent Systems Control

In this paper, we propose the Liquid-Graph Time-constant (LGTC) network, a continuous graph neural network(GNN) model for control of multi-agent systems based on therecent Liquid Time Constant (LTC) network. We analyse itsstability leveraging contraction analysis and propose a closed-form model that preserves the model contraction rate and doesnot require solving an ODE at each iteration. Compared todiscrete models like Graph Gated Neural Networks (GGNNs),the higher expressivity of the proposed model guaranteesremarkable performance while reducing the large amountof communicated variables normally required by GNNs. Weevaluate our model on a distributed multi-agent control casestudy (flocking) taking into account variable communicationrange and scalability under non-instantaneous communication

cs.MA↗

arXiv2024

Multi-UAVs end-to-end Distributed Trajectory Generation over Point Cloud Data

This paper introduces an end-to-end trajectory planning algorithm tailored for multi-UAV systems that generates collision-free trajectories in environments populated with both static and dynamic obstacles, leveraging point cloud data. Our approach consists of a 2-fork neural network fed with sensing and localization data, able to communicate intermediate learned features among the agents. One network branch crafts an initial collision-free trajectory estimate, while the other devises a neural collision constraint for subsequent optimization, ensuring trajectory continuity and adherence to physicalactuation limits. Extensive simulations in challenging cluttered environments, involving up to 25 robots and 25% obstacle density, show a collision avoidance success rate in the range of 100 -- 85%. Finally, we introduce a saliency map computation method acting on the point cloud data, offering qualitative insights into our methodology.

cs.MA↗

arXiv2024

Input State Stability of Gated Graph Neural Networks

In this paper, we aim to find the conditions for input-state stability (ISS) and incremental input-state stability ($δ$ISS) of Gated Graph Neural Networks (GGNNs). We show that this recurrent version of Graph Neural Networks (GNNs) can be expressed as a dynamical distributed system and, as a consequence, can be analysed using model-based techniques to assess its stability and robustness properties. Then, the stability criteria found can be exploited as constraints during the training process to enforce the internal stability of the neural network. Two distributed control examples, flocking and multi-robot motion control, show that using these conditions increases the performance and robustness of the gated GNNs.

cs.RO↗

arXiv2024

Neural Style Transfer with Twin-Delayed DDPG for Shared Control of Robotic Manipulators

Neural Style Transfer (NST) refers to a class of algorithms able to manipulate an element, most often images, to adopt the appearance or style of another one. Each element is defined as a combination of Content and Style: the Content can be conceptually defined as the what and the Style as the how of said element. In this context, we propose a custom NST framework for transferring a set of styles to the motion of a robotic manipulator, e.g., the same robotic task can be carried out in an angry, happy, calm, or sad way. An autoencoder architecture extracts and defines the Content and the Style of the target robot motions. A Twin Delayed Deep Deterministic Policy Gradient (TD3) network generates the robot control policy using the loss defined by the autoencoder. The proposed Neural Policy Style Transfer TD3 (NPST3) alters the robot motion by introducing the trained style. Such an approach can be implemented either offline, for carrying out autonomous robot motions in dynamic environments, or online, for adapting at runtime the style of a teleoperated robot. The considered styles can be learned online from human demonstrations. We carried out an evaluation with human subjects enrolling 73 volunteers, asking them to recognize the style behind some representative robotic motions. Results show a good recognition rate, proving that it is possible to convey different styles to a robot using this approach.

cs.RO↗

arXiv2022

COP: Control & Observability-aware Planning

In this research, we aim to answer the question: How to combine Closed-Loop State and Input Sensitivity-based with Observability-aware trajectory planning? These possibly opposite optimization objectives can be used to improve trajectory control tracking and, at the same time, estimation performance. Our proposed novel Control & Observability-aware Planning (COP) framework is the first that uses these possibly opposing objectives in a Single-Objective Optimization Problem (SOOP) based on the Augmented Weighted Tchebycheff method to perform the balancing of them and generation of Bézier curve-based trajectories. Statistically relevant simulations for a 3D quadrotor unmanned aerial vehicle (UAV) case study produce results that support our claims and show the negative correlation between both objectives. We were able to reduce the positional mean integral error norm as well as the estimation uncertainty with the same trajectory to comparable levels of the trajectories optimized with individual objectives.

cs.RO↗

arXiv2017

Human-in-the-loop optimisation: mixed initiative grasping for optimally facilitating post-grasp manipulative actions

This paper addresses the problem of mixed initiative, shared control for master-slave grasping and manipulation. We propose a novel system, in which an autonomous agent assists a human in teleoperating a remote slave arm/gripper, using a haptic master device. Our system is designed to exploit the human operator's expertise in selecting stable grasps (still an open research topic in autonomous robotics). Meanwhile, a-priori knowledge of: i) the slave robot kinematics, and ii) the desired post-grasp manipulative trajectory, are fed to an autonomous agent which transmits force cues to the human, to encourage maximally manipulable grasp pose selections. Specifically, the autonomous agent provides force cues to the human, during the reach-to-grasp phase, which encourage the human to select grasp poses which maximise manipulation capability during the post-grasp object manipulation phase. We introduce a task-relevant velocity manipulability cost function (TOV), which is used to identify the maximum kinematic capability of a manipulator during post-grasp motions, and feed this back as force cues to the human during the pre-grasp phase. We show that grasps which minimise TOV result in significantly reduced control effort of the manipulator, compared to other feasible grasps. We demonstrate the effectiveness of our approach by experiments with both real and simulated robots.

cs.RO↗

arXiv2017

Decentralized Simultaneous Multi-target Exploration using a Connected Network of Multiple Robots

This paper presents a novel decentralized control strategy for a multi-robot system that enables parallel multi-target exploration while ensuring a time-varying connected topology in cluttered 3D environments. Flexible continuous connectivity is guaranteed by building upon a recent connectivity maintenance method, in which limited range, line-of-sight visibility, and collision avoidance are taken into account at the same time. Completeness of the decentralized multi-target exploration algorithm is guaranteed by dynamically assigning the robots with different motion behaviors during the exploration task. One major group is subject to a suitable downscaling of the main traveling force based on the traveling efficiency of the current leader and the direction alignment between traveling and connectivity force. This supports the leader in always reaching its current target and, on a larger time horizon, that the whole team realizes the overall task in finite time. Extensive Monte~Carlo simulations with a group of several quadrotor UAVs show the scalability and effectiveness of the proposed method and experiments validate its practicability.

cs.RO↗

arXiv2016

Online Leader Selection for Improved Collective Tracking and Formation Maintenance

The goal of this work is to propose an extension of the popular leader-follower framework for multi-agent collective tracking and formation maintenance in presence of a time- varying leader. In particular, the leader is persistently selected online so as to optimize the tracking performance of an exogenous collective velocity command while also maintaining a desired formation via a (possibly time-varying) communication-graph topology. The effects of a change in the leader identity are theoretically analyzed and exploited for defining a suitable error metric able to capture the tracking performance of the multi- agent group. Both the group performance and the metric design are found to depend upon the spectral properties of a special directed graph induced by the identity of the chosen leader. By exploiting these results, as well as distributed estimation techniques, we are then able to detail a fully-decentralized adaptive strategy able to periodically select online the best leader among the neighbors of the current leader. Numerical simulations show that the application of the proposed technique results in an improvement of the overall performance of the group behavior w.r.t. other possible strategies.

eess.SY↗

arXiv2014

Decentralized Rigidity Maintenance Control with Range Measurements for Multi-Robot Systems

This work proposes a fully decentralized strategy for maintaining the formation rigidity of a multi-robot system using only range measurements, while still allowing the graph topology to change freely over time. In this direction, a first contribution of this work is an extension of rigidity theory to weighted frameworks and the rigidity eigenvalue, which when positive ensures the infinitesimal rigidity of the framework. We then propose a distributed algorithm for estimating a common relative position reference frame amongst a team of robots with only range measurements in addition to one agent endowed with the capability of measuring the bearing to two other agents. This first estimation step is embedded into a subsequent distributed algorithm for estimating the rigidity eigenvalue associated with the weighted framework. The estimate of the rigidity eigenvalue is finally used to generate a local control action for each agent that both maintains the rigidity property and enforces additional con- straints such as collision avoidance and sensing/communication range limits and occlusions. As an additional feature of our approach, the communication and sensing links among the robots are also left free to change over time while preserving rigidity of the whole framework. The proposed scheme is then experimentally validated with a robotic testbed consisting of 6 quadrotor UAVs operating in a cluttered environment.

eess.SY↗

arXiv2013

Rigidity Theory in SE(2) for Unscaled Relative Position Estimation using only Bearing Measurements

This work considers the problem of estimating the unscaled relative positions of a multi-robot team in a common reference frame from bearing-only measurements. Each robot has access to a relative bearing measurement taken from the local body frame of the robot, and the robots have no knowledge of a common or inertial reference frame. A corresponding extension of rigidity theory is made for frameworks embedded in the \emph{special Euclidean group} $SE(2) = \mathbb{R}^2 \times \mathcal{S}^1$. We introduce definitions describing rigidity for $SE(2)$ frameworks and provide necessary and sufficient conditions for when such a framework is \emph{infinitesimally rigid} in $SE(2)$. Analogous to the rigidity matrix for point formations, we introduce the \emph{directed bearing rigidity matrix} and show that an $SE(2)$ framework is infinitesimally rigid if and only if the rank of this matrix is equal to $2|\mathcal{V}|-4$, where $|\mathcal{V}|$ is the number of agents in the ensemble. The directed bearing rigidity matrix and its properties are then used in the implementation and convergence proof of a distributed estimator to determine the {unscaled}{} relative positions in a common frame. Some simulation results are also given to support the analysis.

math.OC↗