Ignacio Carlucho

Ibrahim H. Ahmed, Cillian Brewitt, Ignacio Carlucho et al. · microsoft-research

The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systems control, with a specific focus on deep reinforcement learning and multi-agent reinforcement learning. Research problems include scalable learning of coordinated agent policies and inter-agent communication; reasoning about the behaviours, goals, and composition of other agents from limited observations; and sample-efficient learning based on intrinsic motivation, curriculum learning, causal inference, and representation learning. This article provides a broad overview of the ongoing research portfolio of the group and discusses open problems for future directions.

Pierre Nicolay, Yvan Petillot, Mykhaylo Marfeychuk et al.

Autonomous underwater vehicles (AUVs) play a crucial role in surveying marine environments, carrying out underwater inspection tasks, and ocean exploration. However, in order to ensure that the AUV is able to carry out its mission successfully, a control system capable of adapting to changing environmental conditions is required. Furthermore, to ensure the robotic platform's safe operation, the onboard controller should be able to operate under certain constraints. In this work, we investigate the feasibility of Model Predictive Path Integral Control (MPPI) for the control of an AUV. We utilise a non-linear model of the AUV to propagate the samples of the MPPI, which allow us to compute the control action in real time. We provide a detailed evaluation of the effect of the main hyperparameters on the performance of the MPPI controller. Furthermore, we compared the performance of the proposed method with a classical PID and Cascade PID approach, demonstrating the superiority of our proposed controller. Finally, we present results where environmental constraints are added and show how MPPI can handle them by simply incorporating those constraints in the cost function.

Arrasy Rahman, Ignacio Carlucho, Niklas Höpner et al.

Open ad hoc teamwork is the problem of training a single agent to efficiently collaborate with an unknown group of teammates whose composition may change over time. A variable team composition creates challenges for the agent, such as the requirement to adapt to new team dynamics and dealing with changing state vector sizes. These challenges are aggravated in real-world applications in which the controlled agent only has a partial view of the environment. In this work, we develop a class of solutions for open ad hoc teamwork under full and partial observability. We start by developing a solution for the fully observable case that leverages graph neural network architectures to obtain an optimal policy based on reinforcement learning. We then extend this solution to partially observable scenarios by proposing different methodologies that maintain belief estimates over the latent environment states and team composition. These belief estimates are combined with our solution for the fully observable case to compute an agent's optimal policy under partial observability in open ad hoc teamwork. Empirical results demonstrate that our solution can learn efficient policies in open ad hoc teamwork in fully and partially observable cases. Further analysis demonstrates that our methods' success is a result of effectively learning the effects of teammates' actions while also inferring the inherent state of the environment under partial observability.

Arrasy Rahman, Elliot Fosong, Ignacio Carlucho et al.

Ad hoc teamwork (AHT) is the challenge of designing a robust learner agent that effectively collaborates with unknown teammates without prior coordination mechanisms. Early approaches address the AHT challenge by training the learner with a diverse set of handcrafted teammate policies, usually designed based on an expert's domain knowledge about the policies the learner may encounter. However, implementing teammate policies for training based on domain knowledge is not always feasible. In such cases, recent approaches attempted to improve the robustness of the learner by training it with teammate policies generated by optimising information-theoretic diversity metrics. The problem with optimising existing information-theoretic diversity metrics for teammate policy generation is the emergence of superficially different teammates. When used for AHT training, superficially different teammate behaviours may not improve a learner's robustness during collaboration with unknown teammates. In this paper, we present an automated teammate policy generation method optimising the Best-Response Diversity (BRDiv) metric, which measures diversity based on the compatibility of teammate policies in terms of returns. We evaluate our approach in environments with multiple valid coordination strategies, comparing against methods optimising information-theoretic diversity metrics and an ablation not optimising any diversity metric. Our experiments indicate that optimising BRDiv yields a diverse set of training teammate policies that improve the learner's performance relative to previous teammate generation approaches when collaborating with near-optimal previously unseen teammate policies.

Elliot Fosong, Arrasy Rahman, Ignacio Carlucho et al.

Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents. To facilitate efficient learning of complex multi-agent tasks, we propose an approach which uses an expert-provided decomposition of a task into simpler multi-agent sub-tasks. In each sub-task, a subset of the entire team is trained to acquire sub-task-specific policies. The sub-teams are then merged and transferred to the target task, where their policies are collectively fine-tuned to solve the more complex target task. We show empirically that such approaches can greatly reduce the number of timesteps required to solve a complex target task relative to training from-scratch. However, we also identify and investigate two problems with naive implementations of approaches based on sub-task decomposition, and propose a simple and scalable method to address these problems which augments existing actor-critic algorithms. We demonstrate the empirical benefits of our proposed method, enabling sub-task decomposition approaches to be deployed in diverse multi-agent tasks.

Elliot Fosong, Arrasy Rahman, Ignacio Carlucho et al.

We propose the novel few-shot teamwork (FST) problem, where skilled agents trained in a team to complete one task are combined with skilled agents from different tasks, and together must learn to adapt to an unseen but related task. We discuss how the FST problem can be seen as addressing two separate problems: one of reducing the experience required to train a team of agents to complete a complex task; and one of collaborating with unfamiliar teammates to complete a new task. Progress towards solving FST could lead to progress in both multi-agent reinforcement learning and ad hoc teamwork.

Michele Grimaldi, David Nakath, Oscar Pizarro et al.

Robust 3D reconstruction across varying environmental conditions remains a critical challenge for robotic perception, particularly when transitioning between air and water. To address this, we introduce BALTIC, a controlled benchmark designed to systematically evaluate modern 3D reconstruction methods under variations in medium and lighting. The benchmark comprises 13 datasets spanning two media (air and water) and three lighting conditions (ambient, artificial, and mixed), with additional variations in motion type, scanning pattern, and initialization trajectory, resulting in a diverse set of sequences. Our experimental setup features a custom water tank equipped with a monocular camera and an HTC Vive tracker, enabling accurate ground-truth pose estimation. We further investigate cross-domain reconstruction by augmenting underwater image sequences with a small number of in-air views captured under similar lighting conditions. We evaluate Structure-from-Motion reconstruction using COLMAP in terms of both trajectory accuracy and scene geometry, and use these reconstructions as input to Neural Radiance Fields and 3D Gaussian Splatting methods. The resulting models are assessed against ground-truth trajectories and in-air references, while rendered outputs are compared using perceptual and photometric metrics. Additionally, we perform a color restoration analysis to evaluate radiometric consistency across domains. Our results show that under controlled, texture-consistent conditions, Gaussian Splatting with simple preprocessing (e.g., white balance correction) can achieve performance comparable to specialized underwater methods, although its robustness decreases in more complex and heterogeneous real-world environments

Michele Grimaldi, Patryk Cieslak, Eduardo Ochoa et al.

Simulations are highly valuable in marine robotics, offering a cost-effective and controlled environment for testing in the challenging conditions of underwater and surface operations. Given the high costs and logistical difficulties of real-world trials, simulators capable of capturing the operational conditions of subsea environments have become key in developing and refining algorithms for remotely-operated and autonomous underwater vehicles. This paper highlights recent enhancements to the Stonefish simulator, an advanced open-source platform supporting development and testing of marine robotics solutions. Key updates include a suite of additional sensors, such as an event-based camera, a thermal camera, and an optical flow camera, as well as, visual light communication, support for tethered operations, improved thruster modelling, more flexible hydrodynamics, and enhanced sonar accuracy. These developments and an automated annotation tool significantly bolster Stonefish's role in marine robotics research, especially in the field of machine learning, where training data with a known ground truth is hard or impossible to collect.

Markus Buchholz, Ignacio Carlucho, Michele Grimaldi et al.

Achieving robust cognitive autonomy in robots navigating complex, unpredictable environments remains a fundamental challenge in robotics. This paper presents Underwater Robot Self-Organizing Autonomy (UROSA), a groundbreaking architecture leveraging distributed Large Language Model AI agents integrated within the Robot Operating System 2 (ROS 2) framework to enable advanced cognitive capabilities in Autonomous Underwater Vehicles. UROSA decentralises cognition into specialised AI agents responsible for multimodal perception, adaptive reasoning, dynamic mission planning, and real-time decision-making. Central innovations include flexible agents dynamically adapting their roles, retrieval-augmented generation utilising vector databases for efficient knowledge management, reinforcement learning-driven behavioural optimisation, and autonomous on-the-fly ROS 2 node generation for runtime functional extensibility. Extensive empirical validation demonstrates UROSA's promising adaptability and reliability through realistic underwater missions in simulation and real-world deployments, showing significant advantages over traditional rule-based architectures in handling unforeseen scenarios, environmental uncertainties, and novel mission objectives. This work not only advances underwater autonomy but also establishes a scalable, safe, and versatile cognitive robotics framework capable of generalising to a diverse array of real-world applications.

Hao Yu, Zebin Huang, Qingbo Liu et al.

This study presents a pioneering effort to replicate human neuromechanical experiments within a virtual environment utilising a digital human model. By employing MyoSuite, a state-of-the-art human motion simulation platform enhanced by Reinforcement Learning (RL), multiple types of impedance identification experiments of human elbow were replicated on a musculoskeletal model. We compared the elbow movement controlled by an RL agent with the motion of an actual human elbow in terms of the impedance identified in torque-perturbation experiments. The findings reveal that the RL agent exhibits higher elbow impedance to stabilise the target elbow motion under perturbation than a human does, likely due to its shorter reaction time and superior sensory capabilities. This study serves as a preliminary exploration into the potential of virtual environment simulations for neuromechanical research, offering an initial yet promising alternative to conventional experimental approaches. An RL-controlled digital twin with complete musculoskeletal models of the human body is expected to be useful in designing experiments and validating rehabilitation theory before experiments on real human subjects.

Shuguang Chu, Zebin Huang, Yutong Li et al.

This work presents the MarineGym, a high-performance reinforcement learning (RL) platform specifically designed for underwater robotics. It aims to address the limitations of existing underwater simulation environments in terms of RL compatibility, training efficiency, and standardized benchmarking. MarineGym integrates a proposed GPU-accelerated hydrodynamic plugin based on Isaac Sim, achieving a rollout speed of 250,000 frames per second on a single NVIDIA RTX 3060 GPU. It also provides five models of unmanned underwater vehicles (UUVs), multiple propulsion systems, and a set of predefined tasks covering core underwater control challenges. Additionally, the DR toolkit allows flexible adjustments of simulation and task parameters during training to improve Sim2Real transfer. Further benchmark experiments demonstrate that MarineGym improves training efficiency over existing platforms and supports robust policy adaptation under various perturbations. We expect this platform could drive further advancements in RL research for underwater robotics. For more details about MarineGym and its applications, please visit our project page: https://marine-gym.com/.

Sümer Tunçay, Alain Andres, Ignacio Carlucho

Autonomous Underwater Vehicles (AUVs) require reliable six-degree-of-freedom (6-DOF) position control to operate effectively in complex and dynamic marine environments. Traditional controllers are effective under nominal conditions but exhibit degraded performance when faced with unmodeled dynamics or environmental disturbances. Reinforcement learning (RL) provides a powerful alternative but training is typically slow and sim-to-real transfer remains challenging. This work introduces a GPU accelerated RL training pipeline built in JAX and MuJoCo-XLA (MJX). By jointly JIT-compiling large-scale parallel physics simulation and learning updates, we achieve training times of under two minutes. Through systematic evaluation of multiple RL algorithms, we show robust 6-DOF trajectory tracking and effective disturbance rejection in real underwater experiments, with policies transferred zero-shot from simulation.

Reuth Mirsky, Ignacio Carlucho, Arrasy Rahman et al.

Ad hoc teamwork is the research problem of designing agents that can collaborate with new teammates without prior coordination. This survey makes a two-fold contribution: First, it provides a structured description of the different facets of the ad hoc teamwork problem. Second, it discusses the progress that has been made in the field so far, and identifies the immediate and long-term open problems that need to be addressed in ad hoc teamwork.

James P. Oubre, Ignacio Carlucho, Corina Barbalata

The underwater environment poses a complex problem for developing autonomous capabilities for Underwater Vehicle Manipulator Systems (UVMSs). The modeling of UVMSs is a complicated and costly process due to the highly nonlinear dynamics and the presence of unknown hydrodynamical effects. This is aggravated in tasks where the manipulation of objects is necessary, as this may not only introduce external disturbances that can lead to a fast degradation of the control system performance, but also requires the coordinating with a vision system for the correct grasping and operation of the object. In this article, we introduce a control strategy for UVMSs working with unknown payloads. The proposed control strategy is based on a data-driven optimal controller. We present a number of experimental results showing the benefits of the proposed strategy. Furthermore, we include a discussion regarding the visual perception requirements for the UVMS in order to achieve full autonomy in underwater manipulation tasks of unknown payloads.

Jonatan Scharff Willners, Ignacio Carlucho, Tomasz Łuczyński et al.

Autonomous Underwater Vehicles (AUVs) are becoming increasingly important for different types of industrial applications. The generally high cost of (AUVs) restricts the access to them and therefore advances in research and technological development. However, recent advances have led to lower cost commercially available Remotely Operated Vehicles (ROVs), which present a platform that can be enhanced to enable a high degree of autonomy, similar to that of a high-end (AUV). In this article, we present how a low-cost commercial-off-the-shelf (ROV) can be used as a foundation for developing versatile and affordable (AUVs). We introduce the required hardware modifications to obtain a system capable of autonomous operations as well as the necessary software modules. Additionally, we present a set of use cases exhibiting the versatility of the developed platform for intervention and mapping tasks.

Ignacio Carlucho, Manuel F. Bailey, Mariano De Paula et al.

Autonomous Underwater Vehicles (AUVs) are platforms used for research and exploration of marine environments. However, these types of vehicles face many challenges that hinder their widespread use in the industry. One of the main limitations is obtaining accurate position estimation, due to the lack of GPS signal underwater. This estimation is usually done with Kalman filters. However, new developments in the neuroscience field have shed light on the mechanisms by which mammals are able to obtain a reliable estimation of their current position based on external and internal motion cues. A new type of neuron, called Grid cells, has been shown to be part of path integration system in the brain. In this article, we show how grid cells can be used for obtaining a position estimation of underwater vehicles. The model of grid cells used requires only the linear velocities together with heading orientation and provides a reliable estimation of the vehicle's position. We provide simulation results for an AUV which show the feasibility of our proposed methodology.

Ignacio Carlucho, Mariano De Paula, Gerardo G. Acosta et al.

In marine operations underwater manipulators play a primordial role. However, due to uncertainties in the dynamic model and disturbances caused by the environment, low-level control methods require great capabilities to adapt to change. Furthermore, under position and torque constraints the requirements for the control system are greatly increased. Reinforcement learning is a data driven control technique that can learn complex control policies without the need of a model. The learning capabilities of these type of agents allow for great adaptability to changes in the operative conditions. In this article we present a novel reinforcement learning low-level controller for the position control of an underwater manipulator under torque and position constraints. The reinforcement learning agent is based on an actor-critic architecture using sensor readings as state information. Simulation results using the Reach Alpha 5 underwater manipulator show the advantages of the proposed control strategy.