arXiv subjects

Nicolas Bredeche

Publications and source records attributed to Nicolas Bredeche.

At least 19 recordsLinked to original sources

arXiv2026

Aggregating swarms through morphology handling design contingencies: from the sweet spot to a rich expressivity

Morphological computing, the use of the physical design of a robot to ease the realization of a given task has been proven to be a relevant concept in the context of swarm robotics. Here we demonstrate both experimentally and numerically, that the success of such a strategy may heavily rely on the type of policy adopted by the robots, as well as on the details of the physical design. To do so, we consider a swarm of robots, composed of Kilobots embedded in an exoskeleton, the design of which controls the propensity of the robots to align or anti-align with the direction of the external force they experience. We find experimentally that the contrast that was observed between the two morphologies in the success rate of a simple phototactic task, where the robots were programmed to stop when entering a light region, becomes dramatic, if the robots are not allowed to stop, and can only slow down. Building on a faithful physical model of the self-aligning dynamics of the robots, we perform numerical simulations and demonstrate on one hand that a precise tuning of the self-aligning strength around a sweet spot is required to achieve an efficient phototactic behavior, on the other hand that exploring a range of self-alignment strength allows for a rich expressivity of collective behaviors.

cond-mat.soft↗

arXiv2025

Maze-solving with density-driven swarms

We propose a new kind of collective motion where swarms of simple agents are able to find and fix the solution of two-dimensional mazes. The model consists of active memoryless particles interacting exclusively via short-ranged perception of local density and orientations. This system generates traveling density waves when constrained in one dimension, and self-organized swarms exploring local branches in two-dimensional mazes. Depending on a single kinetic parameter, the swarms can develop large tails and further gain long-term persistence, which ultimately allows them to robustly solve mazes of virtually any kind and size. By systematic exploration of the parameter space, we show that there exists a fast solving regime where the resolution time is linear in number of squares, hence making it an efficient maze-solving algorithm. Our model represents a new class of active systems with unprecedented contrast between the minimality of the processed information and the complexity of the resolved task, which is of prime importance for the interpretation and modeling of collective intelligence in living systems as well as for the design of future swarms of active particles and robots.

cond-mat.soft↗

arXiv2025

Pogosim -- a Simulator for Pogobot robots

Pogobots are a new type of open-source/open-hardware robots specifically designed for swarm robotics research. Their cost-effective and modular design, complemented by vibration-based and wheel-based locomotion, fast infrared communication and extensive software architecture facilitate the implementation of swarm intelligence algorithms. However, testing even simple distributed algorithms directly on robots is particularly labor-intensive. Scaling to more complex problems or calibrate user code parameters will have a prohibitively high strain on available resources. In this article we present Pogosim, a fast and scalable simulator for Pogobots, designed to reduce as much as possible algorithm development costs. The exact same code will be used in both simulation and to experimentally drive real robots. This article details the software architecture of Pogosim, explain how to write configuration files and user programs and how simulations approximate or differ from experiments. We describe how a large set of simulations can be launched in parallel, how to retrieve and analyze the simulation results, and how to optimize user code parameters using optimization algorithms.

cs.RO↗

arXiv2025

Towards Language-Augmented Multi-Agent Deep Reinforcement Learning

Most prior works on communication in multi-agent reinforcement learning have focused on emergent communication, which often results in inefficient and non-interpretable systems. Inspired by the role of language in natural intelligence, we investigate how grounding agents in a human-defined language can improve the learning and coordination of embodied agents. We propose a framework in which agents are trained not only to act but also to produce and interpret natural language descriptions of their observations. This language-augmented learning serves a dual role: enabling efficient and interpretable communication between agents, and guiding representation learning. We demonstrate that language-augmented agents outperform emergent communication baselines across various tasks. Our analysis reveals that language grounding leads to more informative internal representations, better generalization to new partners, and improved capability for human-agent interaction. These findings demonstrate the effectiveness of integrating structured language into multi-agent learning and open avenues for more interpretable and capable multi-agent systems.

cs.MA↗

arXiv2025

Pogobot: an Open-Source, Low-Cost Robot for Swarm Robotics and Programmable Active Matter

This paper describes the Pogobot, an open-source platform specifically designed for research at the interface of swarm robotics and active matter. Pogobot features vibration-based or wheel-based locomotion, fast infrared communication, and an array of sensors in a cost-effective package (approx. 250euros/unit). The platform's modular design, comprehensive API, and extensible architecture facilitate the implementation of swarm intelligence algorithms and collective motion. Pogobots offer an accessible alternative to existing platforms while providing advanced capabilities including directional communication between units and fast locomotion, all with a compact form factor. More than 200 Pogobots are already being used on a daily basis in several Universities to study self-organizing systems, programmable active matter, discrete reaction-diffusion-advection systems and computational models of social learning and evolution. This paper details the hardware and software architecture, communication protocols, locomotion mechanisms, and the infrastructure built around the Pogobots.

cs.RO↗

arXiv2024

Signaling and Social Learning in Swarms of Robots

This paper investigates the role of communication in improving coordination within robot swarms, focusing on a paradigm where learning and execution occur simultaneously in a decentralized manner. We highlight the role communication can play in addressing the credit assignment problem (individual contribution to the overall performance), and how it can be influenced by it. We propose a taxonomy of existing and future works on communication, focusing on information selection and physical abstraction as principal axes for classification: from low-level lossless compression with raw signal extraction and processing to high-level lossy compression with structured communication models. The paper reviews current research from evolutionary robotics, multi-agent (deep) reinforcement learning, language models, and biophysics models to outline the challenges and opportunities of communication in a collective of robots that continuously learn from one another through local message exchanges, illustrating a form of social learning.

cs.RO↗

arXiv2024

Hearing the shape of an arena with spectral swarm robotics

Swarm robotics promises adaptability to unknown situations and robustness against failures. However, it still struggles with global tasks that require understanding the broader context in which the robots operate, such as identifying the shape of the arena in which the robots are embedded. Biological swarms, such as shoals of fish, flocks of birds, and colonies of insects, routinely solve global geometrical problems through the diffusion of local cues. This paradigm can be explicitly described by mathematical models that could be directly computed and exploited by a robotic swarm. Diffusion over a domain is mathematically encapsulated by the Laplacian, a linear operator that measures the local curvature of a function. Crucially the geometry of a domain can generally be reconstructed from the eigenspectrum of its Laplacian. Here we introduce spectral swarm robotics where robots diffuse information to their neighbors to emulate the Laplacian operator - enabling them to "hear" the spectrum of their arena. We reveal a universal scaling that links the optimal number of robots (a global parameter) with their optimal radius of interaction (a local parameter). We validate experimentally spectral swarm robotics under challenging conditions with the one-shot classification of arena shapes using a sparse swarm of Kilobots. Spectral methods can assist with challenging tasks where robots need to build an emergent consensus on their environment, such as adaptation to unknown terrains, division of labor, or quorum sensing. Spectral methods may extend beyond robotics to analyze and coordinate swarms of agents of various natures, such as traffic or crowds, and to better understand the long-range dynamics of natural systems emerging from short-range interactions.

cs.RO↗

arXiv2024

Joint Intrinsic Motivation for Coordinated Exploration in Multi-Agent Deep Reinforcement Learning

Multi-agent deep reinforcement learning (MADRL) problems often encounter the challenge of sparse rewards. This challenge becomes even more pronounced when coordination among agents is necessary. As performance depends not only on one agent's behavior but rather on the joint behavior of multiple agents, finding an adequate solution becomes significantly harder. In this context, a group of agents can benefit from actively exploring different joint strategies in order to determine the most efficient one. In this paper, we propose an approach for rewarding strategies where agents collectively exhibit novel behaviors. We present JIM (Joint Intrinsic Motivation), a multi-agent intrinsic motivation method that follows the centralized learning with decentralized execution paradigm. JIM rewards joint trajectories based on a centralized measure of novelty designed to function in continuous environments. We demonstrate the strengths of this approach both in a synthetic environment designed to reveal shortcomings of state-of-the-art MADRL methods, and in simulated robotic tasks. Results show that joint exploration is crucial for solving tasks where the optimal strategy requires a high level of coordination.

cs.MA↗

arXiv2024

Self-Aligning Active Agents with Inertia and Active Torque

We extend the study of the inertial effects on the dynamics of active agents to the case where self-alignment is present. In contrast with the most common models of active particles, we find that self-alignment, which couples the rotational dynamics to the translational one, produces unexpected and non-trivial dynamics, already at the deterministic level. Examining first the motion of a free particle, we contrast the role of inertia depending on the sign of the self-aligning torque. When positive, inertia does not alter the steady-state linear motion of an a-chiral self-propelled particle. On the contrary, for a negative self-aligning torque, inertia leads to the destabilization of the linear motion into a spontaneously broken chiral symmetry orbiting dynamics. Adding an active torque, or bias, to the angular dynamics the bifurcation becomes imperfect in favor of the chiral orientation selected by the bias. In the case of a positive self-alignment, the interplay of the active torque and inertia leads to the emergence, out of a saddle-node bifurcation, of truly new solutions, which coexist with the simply biased linear motion. In the context of a free particle, the rotational inertia leaves unchanged the families of steady-state solutions but can modify their stability properties. The situation is radically different when considering the case of a collision with a wall, where a very singular oscillating dynamics takes place which can only be captured if both translational and rotational inertia are present.

cond-mat.soft↗

arXiv2024

Is Limited Information Enough? An Approximate Multi-agent Coverage Control in Non-Convex Discrete Environments

Conventional distributed approaches to coverage control may suffer from lack of convergence and poor performance, due to the fact that agents have limited information, especially in non-convex discrete environments. To address this issue, we extend the approach of [Marden 2016] which demonstrates how a limited degree of inter-agent communication can be exploited to overcome such pitfalls in one-dimensional discrete environments. The focus of this paper is on extending such results to general dimensional settings. We show that the extension is convergent and keeps the approximation ratio of 2, meaning that any stable solution is guaranteed to have a performance within 50% of the optimal one. The experimental results exhibit that our algorithm outperforms several state-of-the-art algorithms, and also that the runtime is scalable.

cs.GT↗

arXiv2023

Morphological computation and decentralized learning in a swarm of sterically interacting robots

Whereas naturally occurring swarms thrive when crowded, physical interactions in robotic swarms are either avoided or carefully controlled, thus limiting their operational density. Here we present a mechanical design rule that allows robots to act in a collision-dominated environment. We introduce the Morphobots -- a robotic swarm platform developed to implement embodied computation through a morpho-functional design. By engineering a 3D-printed exoskeleton we encode a re-orientation response to an external body force (such as gravity) or a surface force (such as a collision). We show that the force-orientation response is generic, and can augment existing swarm-robotic platforms (e.g Kilobots) as well as custom robots even 10 times larger. At the individual level, the exoskeleton improves the motility and stability, and also allows to encode two contrasting dynamical behaviors in response to an external force or a collision (including collision with a wall or a movable obstacle, and on a dynamically tilting plane). This force-orientation response adds a mechanical layer to the robot's sense-act cycle at the swarm level, leveraging steric interactions for collective phototaxis when crowded. Enabling collisions also promotes information flow, facilitating online distributed learning. Each robot runs an embedded algorithm that ultimately optimizes collective performance. We identify an effective parameter that controls the force-orientation response and explore its implications in swarms that transition from dilute to crowded. \green{Experimenting with both physical swarms (of up to 64 robots), and simulated swarms (of up to 8192 agents) show that the effect of morphological-computation increases with growing swarm size.

cond-mat.soft↗

arXiv2022

Reactive Stepping for Humanoid Robots using Reinforcement Learning: Application to Standing Push Recovery on the Exoskeleton Atalante

State-of-the-art reinforcement learning is now able to learn versatile locomotion, balancing and push-recovery capabilities for bipedal robots in simulation. Yet, the reality gap has mostly been overlooked and the simulated results hardly transfer to real hardware. Either it is unsuccessful in practice because the physics is over-simplified and hardware limitations are ignored, or regularity is not guaranteed, and unexpected hazardous motions can occur. This paper presents a reinforcement learning framework capable of learning robust standing push recovery for bipedal robots that smoothly transfer to reality, providing only instantaneous proprioceptive observations. By combining original termination conditions and policy smoothness conditioning, we achieve stable learning, sim-to-real transfer and safety using a policy without memory nor explicit history. Reward engineering is then used to give insights into how to keep balance. We demonstrate its performance in reality on the lower-limb medical exoskeleton Atalante.

cs.RO↗

arXiv2022

Meta-control of social learning strategies

Social learning, copying other's behavior without actual experience, offers a cost-effective means of knowledge acquisition. However, it raises the fundamental question of which individuals have reliable information: successful individuals versus the majority. The former and the latter are known respectively as success-based and conformist social learning strategies. We show here that while the success-based strategy fully exploits the benign environment of low uncertainly, it fails in uncertain environments. On the other hand, the conformist strategy can effectively mitigate this adverse effect. Based on these findings, we hypothesized that meta-control of individual and social learning strategies provides effective and sample-efficient learning in volatile and uncertain environments. Simulations on a set of environments with various levels of volatility and uncertainty confirmed our hypothesis. The results imply that meta-control of social learning affords agents the leverage to resolve environmental uncertainty with minimal exploration cost, by exploiting others' learning as an external knowledge base.

cs.SI↗

arXiv2021

Policy Search with Rare Significant Events: Choosing the Right Partner to Cooperate with

This paper focuses on a class of reinforcement learning problems where significant events are rare and limited to a single positive reward per episode. A typical example is that of an agent who has to choose a partner to cooperate with, while a large number of partners are simply not interested in cooperating, regardless of what the agent has to offer. We address this problem in a continuous state and action space with two different kinds of search methods: a gradient policy search method and a direct policy search method using an evolution strategy. We show that when significant events are rare, gradient information is also scarce, making it difficult for policy gradient search methods to find an optimal policy, with or without a deep neural architecture. On the other hand, we show that direct policy search methods are invariant to the rarity of significant events, which is yet another confirmation of the unique role evolutionary algorithms has to play as a reinforcement learning method.

cs.LG↗

arXiv2020

DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics

Robots are still limited to controlled conditions, that the robot designer knows with enough details to endow the robot with the appropriate models or behaviors. Learning algorithms add some flexibility with the ability to discover the appropriate behavior given either some demonstrations or a reward to guide its exploration with a reinforcement learning algorithm. Reinforcement learning algorithms rely on the definition of state and action spaces that define reachable behaviors. Their adaptation capability critically depends on the representations of these spaces: small and discrete spaces result in fast learning while large and continuous spaces are challenging and either require a long training period or prevent the robot from converging to an appropriate behavior. Beside the operational cycle of policy execution and the learning cycle, which works at a slower time scale to acquire new policies, we introduce the redescription cycle, a third cycle working at an even slower time scale to generate or adapt the required representations to the robot, its environment and the task. We introduce the challenges raised by this cycle and we present DREAM (Deferred Restructuring of Experience in Autonomous Machines), a developmental cognitive architecture to bootstrap this redescription process stage by stage, build new state representations with appropriate motivations, and transfer the acquired knowledge across domains or tasks or even across robots. We describe results obtained so far with this approach and end up with a discussion of the questions it raises in Neuroscience.

cs.AI↗

arXiv2020

Online Trajectory Planning Through Combined Trajectory Optimization and Function Approximation: Application to the Exoskeleton Atalante

Autonomous robots require online trajectory planning capability to operate in the real world. Efficient offline trajectory planning methods already exist, but are computationally demanding, preventing their use online. In this paper, we present a novel algorithm called Guided Trajectory Learning that learns a function approximation of solutions computed through trajectory optimization while ensuring accurate and reliable predictions. This function approximation is then used online to generate trajectories. This algorithm is designed to be easy to implement, and practical since it does not require massive computing power. It is readily applicable to any robotics systems and effortless to set up on real hardware since robust control strategies are usually already available. We demonstrate the computational performance of our algorithm on flat-foot walking with the self-balanced exoskeleton Atalante.

cs.RO↗

arXiv2019

Exploring Self-Assembling Behaviors in a Swarm of Bio-micro-robots using Surrogate-Assisted MAP-Elites

Swarms of molecular robots are a promising approach to create specific shapes at the microscopic scale through self-assembly. However, controlling their behavior is a challenging problem as it involves complex non-linear dynamics and high experimental variability. Hand-crafting a molecular controller will often be time-consuming and give sub-optimal results. Optimization methods, like the bioNEAT algorithm, were previously employed to partially overcome these difficulties, but they still had to cope with deceptive high-dimensional search spaces and computationally expensive simulations. Here, we describe a novel approach to solve this problem by using MAP-Elites, an algorithm that searches for both high-performing and diverse solutions. We then apply it to a molecular robotic framework we recently introduced that allows sensing, signaling and self-assembly at the micro-scale and show that MAP-Elites outperforms previous approaches. Additionally, we propose a surrogate model of micro-robots physics and chemical reaction dynamics to reduce the computational costs of simulation. We show that the resulting methodology is capable of optimizing controllers with similar accuracy as when using only a full-fledged realistic model, with half the computational budget.

cs.RO↗

arXiv2019

Automatic Calibration of Artificial Neural Networks for Zebrafish Collective Behaviours using a Quality Diversity Algorithm

During the last two decades, various models have been proposed for fish collective motion. These models are mainly developed to decipher the biological mechanisms of social interaction between animals. They consider very simple homogeneous unbounded environments and it is not clear that they can simulate accurately the collective trajectories. Moreover when the models are more accurate, the question of their scalability to either larger groups or more elaborate environments remains open. This study deals with learning how to simulate realistic collective motion of collective of zebrafish, using real-world tracking data. The objective is to devise an agent-based model that can be implemented on an artificial robotic fish that can blend into a collective of real fish. We present a novel approach that uses Quality Diversity algorithms, a class of algorithms that emphasise exploration over pure optimisation. In particular, we use CVT-MAP-Elites, a variant of the state-of-the-art MAP-Elites algorithm for high dimensional search space. Results show that Quality Diversity algorithms not only outperform classic evolutionary reinforcement learning methods at the macroscopic level (i.e. group behaviour), but are also able to generate more realistic biomimetic behaviours at the microscopic level (i.e. individual behaviour).

cs.NE↗