Giovanni Beltrame

Pierre-Yves Lajoie, Giovanni Beltrame

Collaborative Simultaneous Localization And Mapping (C-SLAM) is a vital component for successful multi-robot operations in environments without an external positioning system, such as indoors, underground or underwater. In this paper, we introduce Swarm-SLAM, an open-source C-SLAM system that is designed to be scalable, flexible, decentralized, and sparse, which are all key properties in swarm robotics. Our system supports inertial, lidar, stereo, and RGB-D sensing, and it includes a novel inter-robot loop closure prioritization technique that reduces communication and accelerates convergence. We evaluated our ROS-2 implementation on five different datasets, and in a real-world experiment with three robots communicating through an ad-hoc network. Our code is publicly available: https://github.com/MISTLab/Swarm-SLAM

Pierre-Yves Lajoie, Giovanni Beltrame

Visual place recognition techniques based on deep learning, which have imposed themselves as the state-of-the-art in recent years, do not generalize well to environments visually different from the training set. Thus, to achieve top performance, it is sometimes necessary to fine-tune the networks to the target environment. To this end, we propose a self-supervised domain calibration procedure based on robust pose graph optimization from Simultaneous Localization and Mapping (SLAM) as the supervision signal without requiring GPS or manual labeling. Moreover, we leverage the procedure to improve uncertainty estimation for place recognition matches which is important in safety critical applications. We show that our approach can improve the performance of a state-of-the-art technique on a target environment dissimilar from its training set and that we can obtain uncertainty estimates. We believe that this approach will help practitioners to deploy robust place recognition solutions in real-world applications. Our code is available publicly: https://github.com/MISTLab/vpr-calibration-and-uncertainty

Haechan Mark Bong, Rongge Zhang, Ricardo de Azambuja et al.

This work targets what we consider to be the foundational step for urban airborne robots, a safe landing. Our attention is directed toward what we deem the most crucial aspect of the safe landing perception stack: segmentation. We present a streamlined reactive UAV system that employs visual servoing by harnessing the capabilities of open vocabulary image segmentation. This approach can adapt to various scenarios with minimal adjustments, bypassing the necessity for extensive data accumulation for refining internal models, thanks to its open vocabulary methodology. Given the limitations imposed by local authorities, our primary focus centers on operations originating from altitudes of 100 meters. This choice is deliberate, as numerous preceding works have dealt with altitudes up to 30 meters, aligning with the capabilities of small stereo cameras. Consequently, we leave the remaining 20m to be navigated using conventional 3D path planning methods. Utilizing monocular cameras and image segmentation, our findings demonstrate the system's capability to successfully execute landing maneuvers at altitudes as low as 20 meters. However, this approach is vulnerable to intermittent and occasionally abrupt fluctuations in the segmentation between frames in a video stream. To address this challenge, we enhance the image segmentation output by introducing what we call a dynamic focus: a masking mechanism that self adjusts according to the current landing stage. This dynamic focus guides the control system to avoid regions beyond the drone's safety radius projected onto the ground, thus mitigating the problems with fluctuations. Through the implementation of this supplementary layer, our experiments have reached improvements in the landing success rate of almost tenfold when compared to global segmentation. All the source code is open source and available online (github.com/MISTLab/DOVESEI).

Marcel Kaufmann, Robert Trybula, Ryan Stonebraker et al.

Real-world deployment of new technology and capabilities can be daunting. The recent DARPA Subterranean (SubT) Challenge, for instance, aimed at the advancement of robotic platforms and autonomy capabilities in three one-year development pushes. While multi-agent systems are traditionally deployed in controlled and structured environments that allow for controlled testing (e.g., warehouses), the SubT challenge targeted various types of unknown underground environments that imposed the risk of robot loss in the case of failure. In this work, we introduce a video game-inspired interface, an autonomous mission assistant, and test and deploy these using a heterogeneous multi-agent system in challenging environments. This work leads to improved human-supervisory control for a multi-agent system reducing overhead from application switching, task planning, execution, and verification while increasing available exploration time with this human-autonomy teaming platform.

Abdalwhab Abdalwhab, Giovanni Beltrame, Samira Ebrahimi Kahou et al.

Robotics can help address the growing worker shortage challenge of the manufacturing industry. As such, machine tending is a task collaborative robots can tackle that can also highly boost productivity. Nevertheless, existing robotics systems deployed in that sector rely on a fixed single-arm setup, whereas mobile robots can provide more flexibility and scalability. In this work, we introduce a multi-agent multi-machine tending learning framework by mobile robots based on Multi-agent Reinforcement Learning (MARL) techniques with the design of a suitable observation and reward. Moreover, an attention-based encoding mechanism is developed and integrated into Multi-agent Proximal Policy Optimization (MAPPO) algorithm to boost its performance for machine tending scenarios. Our model (AB-MAPPO) outperformed MAPPO in this new challenging scenario in terms of task success, safety, and resources utilization. Furthermore, we provided an extensive ablation study to support our various design decisions.

Wenqiang Du, Giovanni Beltrame

We propose a novel real-time LiDAR intensity image-based simultaneous localization and mapping method , which addresses the geometry degeneracy problem in unstructured environments. Traditional LiDAR-based front-end odometry mostly relies on geometric features such as points, lines and planes. A lack of these features in the environment can lead to the failure of the entire odometry system. To avoid this problem, we extract feature points from the LiDAR-generated point cloud that match features identified in LiDAR intensity images. We then use the extracted feature points to perform scan registration and estimate the robot ego-movement. For the back-end, we jointly optimize the distance between the corresponding feature points, and the point to plane distance for planes identified in the map. In addition, we use the features extracted from intensity images to detect loop closure candidates from previous scans and perform pose graph optimization. Our experiments show that our method can run in real time with high accuracy and works well with illumination changes, low-texture, and unstructured environments.

Haechan Mark Bong, Simon Roy, Euhid Aman et al.

As robot fleets become more heterogeneous, including humanoids, rovers, quadrupeds, and drones, selecting the right robot for a task becomes a core systems problem. We study robot skill prediction: mapping a natural-language task description to the physical capabilities required to execute it, such as fly, wheels, legs, surface water, under water and hands. Since labelled data that maps natural-language task descriptions to robot's physical capabilities does not exist, we construct a synthetic task-to-skill dataset using LLM-assisted generation and targeted label auditing. Trained on this data, a ~133M-parameter ensemble of two fine-tuned sentence encoders (mpnet + MiniLM) reaches 83.5% task-to-skill matching on a stratified 200 task dataset, outperforming Kimi K2 (1T MoE) at 72.0%, GPT-OSS-120B at 71.5%, and Llama-4-Scout-17B at 69.0% under the same zero-shot prompt. These results suggest that, for fixed robot skill taxonomies, small specialized models trained on synthetic data can outperform much larger general-purpose LLMs for fleet-level task routing.

Monica M. Q. Li, Pierre-Yves Lajoie, Giovanni Beltrame

Three-dimensional reconstruction is a fundamental problem in robotics perception. We examine the problem of active view selection to perform 3D Gaussian Splatting reconstructions with as few input images as possible. Although 3D Gaussian Splatting has made significant progress in image rendering and 3D reconstruction, the quality of the reconstruction is strongly impacted by the selection of 2D images and the estimation of camera poses through Structure-from-Motion (SfM) algorithms. Current methods to select views that rely on uncertainties from occlusions, depth ambiguities, or neural network predictions directly are insufficient to handle the issue and struggle to generalize to new scenes. By ranking the potential views in the frequency domain, we are able to effectively estimate the potential information gain of new viewpoints without ground truth data. By overcoming current constraints on model architecture and efficacy, our method achieves state-of-the-art results in view selection, demonstrating its potential for efficient image-based 3D reconstruction.

Monica M. Q. Li, Pierre-Yves Lajoie, Jialiang Liu et al.

Efficient multi-agent 3D mapping is essential for robotic teams operating in unknown environments, but dense representations hinder real-time exchange over constrained communication links. In multi-agent Simultaneous Localization and Mapping (SLAM), systems typically rely on a centralized server to merge and optimize the local maps produced by individual agents. However, sharing these large map representations, particularly those generated by recent methods such as Gaussian Splatting, becomes a bottleneck in real-world scenarios with limited bandwidth. We present an improved multi-agent RGB-D Gaussian Splatting SLAM framework that reduces communication load while preserving map fidelity. First, we incorporate a compaction step into our SLAM system to remove redundant 3D Gaussians, without degrading the rendering quality. Second, our approach performs centralized loop closure computation without initial guess, operating in two modes: a pure rendered-depth mode that requires no data beyond the 3D Gaussians, and a camera-depth mode that includes lightweight depth images for improved registration accuracy and additional Gaussian pruning. Evaluation on both synthetic and real-world datasets shows up to 85-95\% reduction in transmitted data compared to state-of-the-art approaches in both modes, bringing 3D Gaussian multi-agent SLAM closer to practical deployment in real-world scenarios. Code: https://github.com/lemonci/coko-slam

Maeva Guerrier, Karthik Soma, Jana Pavlasek et al.

Visual Navigation Models (VNMs) promise generalizable, robot navigation by learning from large-scale visual demonstrations. Despite growing real-world deployment, existing evaluations rely almost exclusively on success rate, whether the robot reaches its goal, which conceals trajectory quality, collision behavior, and robustness to environmental change. We present a real-world evaluation of five state-of-the-art VNMs (GNM, ViNT, NoMaD, NaviBridger, and CrossFormer) across two robot platforms and five environments spanning indoor and outdoor settings. Beyond success rate, we combine path-based metrics with vision-based goal-recognition scores and assess robustness through controlled image perturbations (motion blur, sunflare). Our analysis uncovers three systematic limitations: (a) even architecturally sophisticated diffusion and transformer-based models exhibit frequent collisions, indicating limited geometric understanding; (b) models fail to discriminate between different locations that are perceptually similar, however some semantics differences are present, causing goal prediction errors in repetitive environments; and (c) performance degrades under distribution shift. We will publicly release our evaluation codebase and dataset to facilitate reproducible benchmarking of VNMs.

Haechan Mark Bong, Giovanni Beltrame

Safe autonomous Uncrewed Aerial Vehicle (UAV) navigation in urban environments requires real-time path planning that avoids obstacles. MaxConvNet is a potential-field planner that leverages properties of Maxwell's equations to generate a path to the goal without local minima. We extend the 2D MaxConvNet magnetic field planner to 3D, using a convolutional autoencoder to predict obstacle-aware potential fields from LiDAR-derived 101^3 voxel grids. Evaluation across 100 randomized closed-loop trials in two distinct Cosys-AirSim urban environments, a dense night-time cityscape and a suburban district shows a 100% path planning success rate on both maps without retraining. In offline path planning, 3DMaxConvNet produces path lengths comparable to A* on unseen maps while reducing runtime from 0.155--0.17s to 0.087--0.089s, or about 1.7--1.95 times faster than A*. Against RRT*(3k), 3DMaxConvNet achieves similar path quality while reducing planning runtime from 17.2--17.5s to about 0.09s, which is roughly 193--201 times faster than RRT*(3k).

Ricardo de Azambuja, Hassan Fouad, Yann Bouteiller et al.

Flying robots are usually rather delicate and require protective enclosures when facing the risk of collision, while high complexity and reduced payload are recurrent problems with collision-resilient flying robots. Inspired by arthropods' exoskeletons, we design a simple, open source, easily manufactured, semi-rigid structure with soft joints that can withstand high-velocity impacts. With an exoskeleton, the protective shell becomes part of the main robot structure, thereby minimizing its loss in payload capacity. Our design is simple to build and customize using cheap components (e.g. bamboo skewers) and consumer-grade 3D printers. The result is CogniFly, a sub-250g autonomous quadcopter that survives multiple collisions at speeds up to 7m/s. In addition to its collision-resiliency, CogniFly is easy to program using Python or Buzz, carries sensors that allow it to fly for approx. 17min without the need of GPS or an external motion capture system, has enough computing power to run deep neural network models on-board and was designed to facilitate integration with an automated battery swapping system. This structure becomes an ideal platform for high-risk activities (such as flying in a cluttered environment or reinforcement learning training) by dramatically reducing the risks of damaging its own hardware or the environment. Source code, 3D files, instructions and videos are available through the project's website (https://thecognifly.github.io).

Pierre-Yves Lajoie, Benjamin Ramtoula, Yun Chang et al.

To achieve collaborative tasks, robots in a team need to have a shared understanding of the environment and their location within it. Distributed Simultaneous Localization and Mapping (SLAM) offers a practical solution to localize the robots without relying on an external positioning system (e.g. GPS) and with minimal information exchange. Unfortunately, current distributed SLAM systems are vulnerable to perception outliers and therefore tend to use very conservative parameters for inter-robot place recognition. However, being too conservative comes at the cost of rejecting many valid loop closure candidates, which results in less accurate trajectory estimates. This paper introduces DOOR-SLAM, a fully distributed SLAM system with an outlier rejection mechanism that can work with less conservative parameters. DOOR-SLAM is based on peer-to-peer communication and does not require full connectivity among the robots. DOOR-SLAM includes two key modules: a pose graph optimizer combined with a distributed pairwise consistent measurement set maximization algorithm to reject spurious inter-robot loop closures; and a distributed SLAM front-end that detects inter-robot loop closures without exchanging raw sensor data. The system has been evaluated in simulations, benchmarking datasets, and field experiments, including tests in GPS-denied subterranean environments. DOOR-SLAM produces more inter-robot loop closures, successfully rejects outliers, and results in accurate trajectory estimates, while requiring low communication bandwidth. Full source code is available at https://github.com/MISTLab/DOOR-SLAM.git.

Karthik Soma, Mohamed S. Talamali, Genki Miyauchi et al.

In multi-agent systems, should limited resources be concentrated into a few capable agents or distributed among many simpler ones? This work formulates the split over $n$ resource sharing problem where a group of $n$ agents equally shares a common resource (e.g., monetary budget, computational resources, physical size). We present a case study in multi-agent coverage where the area of the disk-shaped footprint of agents scales as $1/n$. A formal analysis reveals that the initial coverage rate grows with $n$. However, if the speed of agents decreases proportionally with their radii, groups of all sizes perform equally well, whereas if it decreases proportionally with their footprints, a single agent performs best. We also present computer simulations in which resource splitting increases the failure rates of individual agents. The models and findings help identify optimal distributiveness levels and inform the design of multi-agent systems under resource constraints.

Maeva Guerrier, Hassan Fouad, Giovanni Beltrame

Reinforcement learning is a powerful technique for developing new robot behaviors. However, typical lack of safety guarantees constitutes a hurdle for its practical application on real robots. To address this issue, safe reinforcement learning aims to incorporate safety considerations, enabling faster transfer to real robots and facilitating lifelong learning. One promising approach within safe reinforcement learning is the use of control barrier functions. These functions provide a framework to ensure that the system remains in a safe state during the learning process. However, synthesizing control barrier functions is not straightforward and often requires ample domain knowledge. This challenge motivates the exploration of data-driven methods for automatically defining control barrier functions, which is highly appealing. We conduct a comprehensive review of the existing literature on safe reinforcement learning using control barrier functions. Additionally, we investigate various techniques for automatically learning the Control Barrier Functions, aiming to enhance the safety and efficacy of Reinforcement Learning in practical robot applications.

Dong Wang, Giovanni Beltrame

Deploying controllers trained with Reinforcement Learning (RL) on real robots can be challenging: RL relies on agents' policies being modeled as Markov Decision Processes (MDPs), which assume an inherently discrete passage of time. The use of MDPs results in that nearly all RL-based control systems employ a fixed-rate control strategy with a period (or time step) typically chosen based on the developer's experience or specific characteristics of the application environment. Unfortunately, the system should be controlled at the highest, worst-case frequency to ensure stability, which can demand significant computational and energy resources and hinder the deployability of the controller on onboard hardware. Adhering to the principles of reactive programming, we surmise that applying control actions only when necessary enables the use of simpler hardware and helps reduce energy consumption. We challenge the fixed frequency assumption by proposing a variant of RL with variable control rate. In this approach, the policy decides the action the agent should take as well as the duration of the time step associated with that action. In our new setting, we expand Soft Actor-Critic (SAC) to compute the optimal policy with a variable control rate, introducing the Soft Elastic Actor-Critic (SEAC) algorithm. We show the efficacy of SEAC through a proof-of-concept simulation driving an agent with Newtonian kinematics. Our experiments show higher average returns, shorter task completion times, and reduced computational resources when compared to fixed rate policies.

Dong Wang, Giovanni Beltrame

Traditional Reinforcement Learning (RL) policies are typically implemented with fixed control rates, often disregarding the impact of control rate selection. This can lead to inefficiencies as the optimal control rate varies with task requirements. We propose the Multi-Objective Soft Elastic Actor-Critic (MOSEAC), an off-policy actor-critic algorithm that uses elastic time steps to dynamically adjust the control frequency. This approach minimizes computational resources by selecting the lowest viable frequency. We show that MOSEAC converges and produces stable policies at the theoretical level, and validate our findings in a real-time 3D racing game. MOSEAC significantly outperformed other variable time step approaches in terms of energy efficiency and task effectiveness. Additionally, MOSEAC demonstrated faster and more stable training, showcasing its potential for real-world RL applications in robotics.

Ali Imran, Giovanni Beltrame, David St-Onge

In industrial environments, predicting human actions is essential for ensuring safe and effective collaboration between humans and robots. This paper introduces a perception framework that enables mobile robots to understand and share information about human actions in a decentralized way. The framework first allows each robot to build a spatial graph representing its surroundings, which it then shares with other robots. This shared spatial data is combined with temporal information to track human behavior over time. A swarm-inspired decision-making process is used to ensure all robots agree on a unified interpretation of the human's actions. Results show that adding more robots and incorporating longer time sequences improve prediction accuracy. Additionally, the consensus mechanism increases system resilience, making the multi-robot setup more reliable in dynamic industrial settings.

Euhid Aman, Esteban Carlin, Hsing-Kuo Pao et al.

Cross-attention transformers and other multimodal vision-language models excel at grounding and generation; however, their extensive, full-precision backbones make it challenging to deploy them on edge devices. Memory-augmented architectures enhance the utilization of past context; however, most works rarely pair them with aggressive edge-oriented quantization. We introduce BitMar, a quantized multimodal transformer that proposes an external human-like episodic memory for effective image-text generation on hardware with limited resources. BitMar utilizes 1.58-bit encoders, one for text (BitNet-style) and one for vision (DiNOv2-based), to create compact embeddings that are combined and used to query a fixed-size key-value episodic memory. During vector retrieval, the BitNet decoder applies per-layer conditioning, which increases the contextual relevance of generated content. The decoder also employs attention sinks with a sliding-window mechanism to process long or streaming inputs under tight memory budgets. The combination of per-layer conditioning and sliding-window attention achieves a strong quality-speed trade-off, delivering competitive captioning and multimodal understanding at low latency with a small model footprint. These characteristics make BitMar well-suited for edge deployment.

Maeva Guerrier, Karthik Soma, Hassan Fouad et al.

Safety stands as the primary obstacle preventing the widespread adoption of learning-based robotic systems in our daily lives. While reinforcement learning (RL) shows promise as an effective robot learning paradigm, conventional RL frameworks often model safety by using single scalar negative rewards with immediate episode termination, failing to capture the temporal consequences of unsafe actions (e.g., sustained collision damage). In this work, we introduce a novel approach that simulates these temporal effects by applying continuous negative rewards without episode termination. Our experiments reveal that standard RL methods struggle with this model, as the accumulated negative values in unsafe zones create learning barriers. To address this challenge, we demonstrate how Control Barrier Functions (CBFs), with their proven safety guarantees, effectively help robots avoid catastrophic regions while enhancing learning outcomes. We present three CBF-based approaches, each integrating traditional RL methods with Control Barrier Functions, guiding the agent to learn safe behavior. Our empirical analysis, conducted in both simulated environments and real-world settings using a four-wheel differential drive robot, explores the possibilities of employing these approaches for safe robotic learning.

Karthik Soma, Yann Bouteiller, Heiko Hamann et al.

Decision-making is an essential attribute of any intelligent agent or group. Natural systems are known to converge to optimal strategies through at least two distinct mechanisms: collective decision-making via imitation of others, and individual trial-and-error. This paper establishes an equivalence between these two paradigms by drawing from the well-established collective decision-making model of nest-hunting in swarms of honey bees. We show that the emergent distributed cognition (sometimes referred to as the $\textit{hive mind}$) arising from individual bees following simple, local imitation-based rules is that of a single online reinforcement learning (RL) agent interacting with many parallel environments. The update rule through which this macro-agent learns is a bandit algorithm that we coin $\textit{Maynard-Cross Learning}$. Our analysis implies that a group of cognition-limited organisms can be equivalent to a more complex, reinforcement-enabled entity, substantiating the idea that group-level intelligence may explain how seemingly simple and blind individual behaviors are selected in nature. From a biological perspective, this analysis suggests how such imitation strategies evolved: they constitute a scalable form of reinforcement learning at the group level, aligning with theories of kin and group selection. Beyond biology, the framework offers new tools for analyzing economic and social systems where individuals imitate successful strategies, effectively participating in a collective learning process. In swarm intelligence, our findings will inform the design of scalable collective systems in artificial domains, enabling RL-inspired mechanisms for coordination and adaptability at scale.

Yann Bouteiller, Karthik Soma, Giovanni Beltrame

The universe involves many independent co-learning agents as an ever-evolving part of our observed environment. Yet, in practice, Multi-Agent Reinforcement Learning (MARL) applications are typically constrained to small, homogeneous populations and remain computationally intensive. We propose a methodology that enables simulating populations of Reinforcement Learning agents at evolutionary scale. More specifically, we derive a fast, parallelizable implementation of Policy Gradient (PG) and Opponent-Learning Awareness (LOLA), tailored for evolutionary simulations where agents undergo random pairwise interactions in stateless normal-form games. We demonstrate our approach by simulating the evolution of very large populations made of heterogeneous co-learning agents, under both naive and advanced learning strategies. In our experiments, 200,000 PG or LOLA agents evolve in the classic games of Hawk-Dove, Stag-Hunt, and Rock-Paper-Scissors. Each game provides distinct insights into how populations evolve under both naive and advanced MARL rules, including compelling ways in which Opponent-Learning Awareness affects social evolution.

Abdalwhab Abdalwhab, Giovanni Beltrame, David St-Onge

The manufacturing sector was recently affected by workforce shortages, a problem that automation and robotics can heavily minimize. Simultaneously, reinforcement learning (RL) offers a promising solution where robots can learn through interaction with the environment. In this work, we leveraged a simplistic robotic system to work with RL with "real" data without having to deploy large expensive robots in a manufacturing setting. A real-world tabletop arena was designed with robots that mimic the agents' behavior in the simulation. Despite the difference in dynamics and machine size, the robots were able to depict the same behavior as in the simulation. In addition, those experiments provided an initial understanding of the real deployment challenges.

Dong Wang, Giovanni Beltrame

Traditional reinforcement learning (RL) methods typically employ a fixed control loop, where each cycle corresponds to an action. This rigidity poses challenges in practical applications, as the optimal control frequency is task-dependent. A suboptimal choice can lead to high computational demands and reduced exploration efficiency. Variable Time Step Reinforcement Learning (VTS-RL) addresses these issues by using adaptive frequencies for the control loop, executing actions only when necessary. This approach, rooted in reactive programming principles, reduces computational load and extends the action space by including action durations. However, VTS-RL's implementation is often complicated by the need to tune multiple hyperparameters that govern exploration in the multi-objective action-duration space (i.e., balancing task performance and number of time steps to achieve a goal). To overcome these challenges, we introduce the Multi-Objective Soft Elastic Actor-Critic (MOSEAC) method. This method features an adaptive reward scheme that adjusts hyperparameters based on observed trends in task rewards during training. This scheme reduces the complexity of hyperparameter tuning, requiring a single hyperparameter to guide exploration, thereby simplifying the learning process and lowering deployment costs. We validate the MOSEAC method through simulations in a Newtonian kinematics environment, demonstrating high task and training performance with fewer time steps, ultimately lowering energy consumption. This validation shows that MOSEAC streamlines RL algorithm deployment by automatically tuning the agent control loop frequency using a single parameter. Its principles can be applied to enhance any RL algorithm, making it a versatile solution for various applications.

Samuel Arseneault, David Vielfaure, Giovanni Beltrame

In robotics, data acquisition often plays a key part in unknown environment exploration. For example, storing information about the topography of the explored terrain or the natural dangers in the environment can inform the decision-making process of the robots. Therefore, it is crucial to store these data safely and to make it available quickly to the operators of the robotic system. In a decentralized system like a swarm of robots, this entails several challenges. To address them, we propose RASS, a decentralized risk-aware swarm storage and routing mechanism, which relies exclusively on local information sharing between neighbours to establish storage and routing fitness. We test our system through thorough experiments in a physics-based simulator and test its real-world applicability with physical experiments. We obtain convincing reliability, routing speeds, and swarm storage capacity results.

David Vielfaure, Samuel Arseneault, Pierre-Yves Lajoie et al.

Exploration of unknown environments is an important challenge in the field of robotics. While a single robot can achieve this task alone, evidence suggests it could be accomplished more efficiently by groups of robots, with advantages in terms of terrain coverage as well as robustness to failures. Exploration can be guided through belief maps, which provide probabilistic information about which part of the terrain is interesting to explore (either based on risk management or reward). This process can be centrally coordinated by building a collective belief map on a common server. However, relying on a central processing station creates a communication bottleneck and single point of failure for the system. In this paper, we present Distributed Online Risk-Aware (DORA) Explorer, an exploration system that leverages decentralized information sharing to update a common risk belief map. DORA Explorer allows a group of robots to explore an unknown environment discretized as a 2D grid with obstacles, with high coverage while minimizing exposure to risk, effectively reducing robot failures

Pierre-Yves Lajoie, Benjamin Ramtoula, Fang Wu et al.

Motivated by the tremendous progress we witnessed in recent years, this paper presents a survey of the scientific literature on the topic of Collaborative Simultaneous Localization and Mapping (C-SLAM), also known as multi-robot SLAM. With fleets of self-driving cars on the horizon and the rise of multi-robot systems in industrial applications, we believe that Collaborative SLAM will soon become a cornerstone of future robotic applications. In this survey, we introduce the basic concepts of C-SLAM and present a thorough literature review. We also outline the major challenges and limitations of C-SLAM in terms of robustness, communication, and resource management. We conclude by exploring the area's current trends and promising research avenues.

Nicolas Valenchon, Yann Bouteiller, Hugo R. Jourde et al.

Closed-loop brain stimulation refers to capturing neurophysiological measures such as electroencephalography (EEG), quickly identifying neural events of interest, and producing auditory, magnetic or electrical stimulation so as to interact with brain processes precisely. It is a promising new method for fundamental neuroscience and perhaps for clinical applications such as restoring degraded memory function; however, existing tools are expensive, cumbersome, and offer limited experimental flexibility. In this article, we propose the Portiloop, a deep learning-based, portable and low-cost closed-loop stimulation system able to target specific brain oscillations. We first document open-hardware implementations that can be constructed from commercially available components. We also provide a fast, lightweight neural network model and an exploration algorithm that automatically optimizes the model hyperparameters to the desired brain oscillation. Finally, we validate the technology on a challenging test case of real-time sleep spindle detection, with results comparable to off-line expert performance on the Massive Online Data Annotation spindle dataset (MODA; group consensus). Software and plans are available to the community as an open science initiative to encourage further development and advance closed-loop neuroscience research.

Ricardo de Azambuja, Hassan Fouad, Giovanni Beltrame

With inspiration from arthropods' exoskeletons, we designed a simple, easily manufactured, semi-rigid structure with flexible joints that can passively damp impact energy. This exoskeleton fuses the protective shell to the main robot structure, thereby minimizing its loss in payload capacity. Our design is simple to build and customize using cheap components and consumer-grade 3D printers. Our results show we can build a sub-250g, autonomous quadcopter with visual navigation that can survive multiple collisions, shows a five-fold increase in the passive energy absorption, that is also suitable for automated battery swapping, and with enough computing power to run deep neural network models. This structure makes for an ideal platform for high-risk activities (such as flying in a cluttered environment or reinforcement learning training) without damage to the hardware or the environment.

Vivek Shankar Vardharajan, Karthik Soma, Giovanni Beltrame

We propose a decentralized algorithm to collaboratively transport arbitrarily shaped objects using a swarm of robots. Our approach starts with a task allocation phase that sequentially distributes locations around the object to be transported starting from a seed robot that makes first contact with the object. Our approach does not require previous knowledge of the shape of the object to ensure caging. To push the object to a goal location, we estimate the robots required to apply force on the object based on the angular difference between the target and the object. During transport, the robots follow a sequence of intermediate goal locations specifying the required pose of the object at that location. We evaluate our approach in a physics-based simulator with up to 100 robots, using three generic paths. Experiments using a group of KheperaIV robots demonstrate the effectiveness of our approach in a real setting. Keywords: Collaborative transport, Task Allocation, Caging, Robot Swarms

Beatrice Capelli, Hassan Fouad, Giovanni Beltrame et al.

Connectivity maintenance is crucial for the real world deployment of multi-robot systems, as it ultimately allows the robots to communicate, coordinate and perform tasks in a collaborative way. A connectivity maintenance controller must keep the multi-robot system connected independently from the system's mission and in the presence of undesired real world effects such as communication delays, model errors, and computational time delays, among others. In this paper we present the implementation, on a real robotic setup, of a connectivity maintenance control strategy based on Control Barrier Functions. During experimentation, we found that the presence of communication delays has a significant impact on the performance of the controlled system, with respect to the ideal case. We propose a heuristic to counteract the effects of communication delays, and we verify its efficacy both in simulation and with physical robot experiments.

Ali Agha, Kyohei Otsu, Benjamin Morrell et al.

This paper presents and discusses algorithms, hardware, and software architecture developed by the TEAM CoSTAR (Collaborative SubTerranean Autonomous Robots), competing in the DARPA Subterranean Challenge. Specifically, it presents the techniques utilized within the Tunnel (2019) and Urban (2020) competitions, where CoSTAR achieved 2nd and 1st place, respectively. We also discuss CoSTAR's demonstrations in Martian-analog surface and subsurface (lava tubes) exploration. The paper introduces our autonomy solution, referred to as NeBula (Networked Belief-aware Perceptual Autonomy). NeBula is an uncertainty-aware framework that aims at enabling resilient and modular autonomy solutions by performing reasoning and decision making in the belief space (space of probability distributions over the robot and world states). We discuss various components of the NeBula framework, including: (i) geometric and semantic environment mapping; (ii) a multi-modal positioning system; (iii) traversability analysis and local planning; (iv) global motion planning and exploration behavior; (i) risk-aware mission planning; (vi) networking and decentralized reasoning; and (vii) learning-enabled adaptation. We discuss the performance of NeBula on several robot types (e.g. wheeled, legged, flying), in various environments. We discuss the specific results and lessons learned from fielding this solution in the challenging courses of the DARPA Subterranean Challenge competition.

Hassan Fouad, Giovanni Beltrame

One aspect of the ever-growing need for long term autonomy of multi-robot systems, is ensuring energy sufficiency. In particular, in scenarios where charging facilities are limited, battery-powered robots need to coordinate to share access. In this work we extend previous results by considering robots that carry out a generic mission while sharing a single charging station, while being affected by air drag and wind fields. Our mission-agnostic framework based on control barrier functions (CBFs) ensures energy sufficiency (i.e., maintaining all robots above a certain voltage threshold) and proper coordination (i.e., ensuring mutually exclusive use of the available charging station). Moreover, we investigate the feasibility requirements of the system in relation to individual robots' properties, as well as air drag and wind effects. We show simulation results that demonstrate the effectiveness of the proposed framework.

Benjamin Ramtoula, Adam Caccavale, Giovanni Beltrame et al.

Determining the relative position and orientation of objects in an environment is a fundamental building block for a wide range of robotics applications. To accomplish this task efficiently in practical settings, a method must be fast, use common sensors, and generalize easily to new objects and environments. We present MSL-RAPTOR, a two-stage algorithm for tracking a rigid body with a monocular camera. The image is first processed by an efficient neural network-based front-end to detect new objects and track 2D bounding boxes between frames. The class label and bounding box is passed to the back-end that updates the object's pose using an unscented Kalman filter (UKF). The measurement posterior is fed back to the 2D tracker to improve robustness. The object's class is identified so a class-specific UKF can be used if custom dynamics and constraints are known. Adapting to track the pose of new classes only requires providing a trained 2D object detector or labeled 2D bounding box data, as well as the approximate size of the objects. The performance of MSL-RAPTOR is first verified on the NOCS-REAL275 dataset, achieving results comparable to RGB-D approaches despite not using depth measurements. When tracking a flying drone from onboard another drone, it outperforms the fastest comparable method in speed by a factor of 3, while giving lower translation and rotation median errors by 66% and 23% respectively.

Simon Ramstedt, Yann Bouteiller, Giovanni Beltrame et al.

Action and observation delays commonly occur in many Reinforcement Learning applications, such as remote control scenarios. We study the anatomy of randomly delayed environments, and show that partially resampling trajectory fragments in hindsight allows for off-policy multi-step value estimation. We apply this principle to derive Delay-Correcting Actor-Critic (DCAC), an algorithm based on Soft Actor-Critic with significantly better performance in environments with delays. This is shown theoretically and also demonstrated practically on a delay-augmented version of the MuJoCo continuous control benchmark.

Yanjun Cao, Giovanni Beltrame

Monocular cameras coupled with inertial measurements generally give high performance visual inertial odometry. However, drift can be significant with long trajectories, especially when the environment is visually challenging. In this paper, we propose a system that leverages ultra-wideband ranging with one static anchor placed in the environment to correct the accumulated error whenever the anchor is visible. We also use this setup for collaborative SLAM: different robots use mutual ranging (when available) and the common anchor to estimate the transformation between each other, facilitating map fusion Our system consists of two modules: a double layer ranging, visual, and inertial odometry for single robots, and a transformation estimation module for collaborative SLAM. We test our system on public datasets by simulating an ultra-wideband sensor as well as on real robots. Experiments show our method can outperform state-of-the-art visual-inertial odometry by more than 20%. For visually challenging environments, our method works even the visual-inertial odometry has significant drift Furthermore, we can compute the collaborative SLAM transformation matrix at almost no extra computation cost.

Yanjun Cao, Chenhao Yang, Rui Li et al.

Accurate localization and tracking are a fundamental requirement for robotic applications. Localization systems like GPS, optical tracking, simultaneous localization and mapping (SLAM) are used for daily life activities, research, and commercial applications. Ultra-wideband (UWB) technology provides another venue to accurately locate devices both indoors and outdoors. In this paper, we study a localization solution with a single UWB anchor, instead of the traditional multi-anchor setup. Besides the challenge of a single UWB ranging source, the only other sensor we require is a low-cost 9 DoF inertial measurement unit (IMU). Under such a configuration, we propose continuous monitoring of UWB range changes to estimate the robot speed when moving on a line. Combining speed estimation with orientation estimation from the IMU sensor, the system becomes temporally observable. We use an Extended Kalman Filter (EKF) to estimate the pose of a robot. With our solution, we can effectively correct the accumulated error and maintain accurate tracking of a moving robot.

Benjamin Ramtoula, Ricardo de Azambuja, Giovanni Beltrame

Using multiple robots for exploring and mapping environments can provide improved robustness and performance, but it can be difficult to implement. In particular, limited communication bandwidth is a considerable constraint when a robot needs to determine if it has visited a location that was previously explored by another robot, as it requires for robots to share descriptions of places they have visited. One way to compress this description is to use constellations, groups of 3D points that correspond to the estimate of a set of relative object positions. Constellations maintain the same pattern from different viewpoints and can be robust to illumination changes or dynamic elements. We present a method to extract from these constellations compact spatial and semantic descriptors of the objects in a scene. We use this representation in a 2-step decentralized loop closure verification: first, we distribute the compact semantic descriptors to determine which other robots might have seen scenes with similar objects; then we query matching robots with the full constellation to validate the match using geometric information. The proposed method requires less memory, is more interpretable than global image descriptors, and could be useful for other tasks and interactions with the environment. We validate our system's performance on a TUM RGB-D SLAM sequence and show its benefits in terms of bandwidth requirements.

Vivek Shankar Varadharajan, David St-Onge, Bram Adams et al.

The coordination of robot swarms - large decentralized teams of robots - generally relies on robust and efficient inter-robot communication. Maintaining communication between robots is particularly challenging in field deployments. Unstructured environments, limited computational resources, low bandwidth, and robot failures all contribute to the complexity of connectivity maintenance. In this paper, we propose a novel lightweight algorithm to navigate a group of robots in complex environments while maintaining connectivity by building a chain of robots. The algorithm is robust to single robot failures and can heal broken communication links. The algorithm works in 3D environments: when a region is unreachable by wheeled robots, the chain is extended with flying robots. We test the performance of the algorithm using up to 100 robots in a physics-based simulator with three mazes and different robot failure scenarios. We then validate the algorithm with physical platforms: 7 wheeled robots and 6 flying ones, in homogeneous and heterogeneous scenarios.

Hehui Zheng, Jacopo Panerati, Giovanni Beltrame et al.

Privacy is an important facet of defence against adversaries. In this letter, we introduce the problem of private flocking. We consider a team of mobile robots flocking in the presence of an adversary, who is able to observe all robots' trajectories, and who is interested in identifying the leader. We present a method that generates private flocking controllers that hide the identity of the leader robot. Our approach towards privacy leverages a data-driven adversarial co-optimization scheme. We design a mechanism that optimizes flocking control parameters, such that leader inference is hindered. As the flocking performance improves, we successively train an adversarial discriminator that tries to infer the identity of the leader robot. To evaluate the performance of our co-optimization scheme, we investigate different classes of reference trajectories. Although it is reasonable to assume that there is an inherent trade-off between flocking performance and privacy, our results demonstrate that we are able to achieve high flocking performance and simultaneously reduce the risk of revealing the leader.

Jacopo Panerati, Benjamin Ramtoula, David St-Onge et al.

Redundancy and parallelism make decentralized multi-robot systems appealing solutions for the exploration of extreme environments. However, effective cooperation often requires team-wide connectivity and a carefully designed communication strategy. Several recently proposed decentralized connectivity maintenance approaches exploit elegant algebraic results drawn from spectral graph theory. Yet, these proposals are rarely taken beyond simulations or laboratory implementations. In this work, we present two major contributions: (i) we describe the full-stack implementation---from hardware to software---of a decentralized control law for robust connectivity maintenance; and (ii) we assess, in the field, our setup's ability to correctly exchange all the necessary information required to maintain connectivity in a team of quadcopters.

Vivek Shankar Varadharajan, Bram Adams, Giovanni Beltrame

Connectivity maintenance plays a key role in achieving a desired global behavior among a swarm of robots. However, connectivity maintenance in realistic environments is hampered by lack of computation resources, low communication bandwidth, robot failures, and unstable links. In this paper, we propose a novel decentralized connectivity-preserving algorithm that can be deployed on top of other behaviors to enforce connectivity constraints. The algorithm takes a set of targets to be reached while keeping a minimum number of redundant links between robots, with the goal of guaranteeing bandwidth and reliability. Robots then incrementally build and maintain a communication backbone with the specified number of links. We empirically study the performance of the algorithm, analyzing its time to convergence, as well as robustness to faults injected into the backbone robots. Our results statistically demonstrate the algorithm's ability to preserve the desired connectivity constraints and to reach the targets with up to 70 percent of individual robot failures in the communication backbone.

Yanjun Cao, David St-Onge, Andreas Zell et al.

Localization and tracking are two very active areas of research for robotics, automation, and the Internet-of-Things. Accurate tracking for a large number of devices usually requires deployment of substantial infrastructure (infrared tracking systems, cameras, wireless antennas, etc.), which is not ideal for inaccessible or protected environments. This paper stems from the challenge posed such environments: cover a large number of units spread over a large number of small rooms, with minimal required localization infrastructure. The idea is to accurately track the position of handheld devices or mobile robots, without interfering with its architecture. Using Ultra-Wide Band (UWB) devices, we leveraged our expertise in distributed and collaborative robotic systems to develop an novel solution requiring a minimal number of fixed anchors. We discuss a strategy to share the UWB network together with an Extended Kalman filter derivation to collaboratively locate and track UWB-equipped devices, and show results from our experimental campaign tracking visitors in the Chambord castle in France.

Fang Wu, Vivek Shankar Varadharajan, Giovanni Beltrame

We propose a novel formulation of the collision-aware task assignment (CATA) problem and a decentralized auction-based algorithm to solve the problem with optimality bound. Using a collision cone, we predict potential collisions and introduce a binary decision variable into the local reward function for task bidding. We further improve CATA by implementing a receding collision horizon to address the stopping robot scenario, i.e. when robots are confined to their task location and become static obstacles to other moving robots. The auction-based algorithm encourages the robots to bid for tasks with collision mitigation considerations. We validate the improved task assignment solution with both simulation and experimental results, which show significant reduction of overlapping paths as well as deadlocks.

Pierre-Yves Lajoie, Siyi Hu, Giovanni Beltrame et al.

Perceptual aliasing is one of the main causes of failure for Simultaneous Localization and Mapping (SLAM) systems operating in the wild. Perceptual aliasing is the phenomenon where different places generate a similar visual (or, in general, perceptual) footprint. This causes spurious measurements to be fed to the SLAM estimator, which typically results in incorrect localization and mapping results. The problem is exacerbated by the fact that those outliers are highly correlated, in the sense that perceptual aliasing creates a large number of mutually-consistent outliers. Another issue stems from the fact that most state-of-the-art techniques rely on a given trajectory guess (e.g., from odometry) to discern between inliers and outliers and this makes the resulting pipeline brittle, since the accumulation of error may result in incorrect choices and recovery from failures is far from trivial. This work provides a unified framework to model perceptual aliasing in SLAM and provides practical algorithms that can cope with outliers without relying on any initial guess. We present two main contributions. The first is a Discrete-Continuous Graphical Model (DC-GM) for SLAM: the continuous portion of the DC-GM captures the standard SLAM problem, while the discrete portion describes the selection of the outliers and models their correlation. The second contribution is a semidefinite relaxation to perform inference in the DC-GM that returns estimates with provable sub-optimality guarantees. Experimental results on standard benchmarking datasets show that the proposed technique compares favorably with state-of-the-art methods while not relying on an initial guess for optimization.

Ryan Cotsakis, David St-Onge, Giovanni Beltrame

Small unmanned aerial vehicles (UAVs) have generally little capacity to carry payloads. Through collaboration, the UAVs can increase their joint payload capacity and carry more significant loads. For maximum flexibility to dynamic and unstructured environments and task demands, we propose a fully decentralized control infrastructure based on a swarm-specific scripting language, Buzz. In this paper, we describe the control infrastructure and use it to compare two algorithms for collaborative transport: field potentials and spring-damper. We test the performance of our approach with a fleet of micro-UAVs, demonstrating the potential of decentralized control for collaborative transport.

Marco Minelli, Marcel Kaufmann, Jacopo Panerati et al.

Efficient networking of many-robot systems is considered one of the grand challenges of robotics. In this article, we address the problem of achieving resilient, dynamic interconnection topologies in multi-robot systems. In scenarios in which the overall network topology is constantly changing, we aim at avoiding the onset of single points of failure, particularly situations in which the failure of a single robot causes the loss of connectivity for the overall network. We propose a method based on the combination of multiple control objectives and we introduce an online distributed optimization strategy that computes the optimal choice of control parameters for each robot. This ensures that the connectivity of the multi-robot system is not only preserved but also made more resilient to failures, as the network topology evolves. We provide simulation results, as well as experiments with real robots to validate theoretical findings and demonstrate the portability to robotic hardware.

Nathalie Majcherczyk, Adhavan Jayabalan, Giovanni Beltrame et al.

We present a decentralized and scalable approach for deployment of a robot swarm. Our approach tackles scenarios in which the swarm must reach multiple spatially distributed targets, and enforce the constraint that the robot network cannot be split. The basic idea behind our work is to construct a logical tree topology over the physical network formed by the robots. The logical tree acts as a backbone used by robots to enforce connectivity constraints. We study and compare two algorithms to form the logical tree: outwards and inwards. These algorithms differ in the order in which the robots join the tree: the outwards algorithm starts at the tree root and grows towards the targets, while the inwards algorithm proceeds in the opposite manner. Both algorithms perform periodic reconfiguration, to prevent suboptimal topologies from halting the growth of the tree. Our contributions are (i) The formulation of the two algorithms; (ii) A comparison of the algorithms in extensive physics-based simulations; (iii) A validation of our findings through real-robot experiments.

David St-Onge, Vivek Shankar Varadharajan, Guannan Li et al.

This paper address the challenges encountered by developers when deploying a distributed decision-making behavior on heterogeneous robotic systems. Many applications benefit from the use of multiple robots, but their scalability and applicability are fundamentally limited if relying on a central control station. Getting beyond the centralized approach can increase the complexity of the embedded intelligence, the sensitivity to the network topology, and render the deployment on physical robots tedious and error-prone. By integrating the swarm-oriented programming language Buzz with the standard environment of ROS, this work demonstrates that behaviors requiring distributed consensus can be successfully deployed in practice. From simulation to the field, the behavioral script stays untouched and applicable to heterogeneous robot teams. We present the software structure of our solution as well as the swarm-oriented paradigms required from Buzz to implement a robust generic consensus strategy. We show the applicability of our solution with simulations and experiments with heterogeneous ground-and-air robotic teams.

Carlo Pinciroli, Adam Lee-Brown, Giovanni Beltrame

We present Buzz, a novel programming language for heterogeneous robot swarms. Buzz advocates a compositional approach, offering primitives to define swarm behaviors both from the perspective of the single robot and of the overall swarm. Single-robot primitives include robot-specific instructions and manipulation of neighborhood data. Swarm-based primitives allow for the dynamic management of robot teams, and for sharing information globally across the swarm. Self-organization stems from the completely decentralized mechanisms upon which the Buzz run-time platform is based. The language can be extended to add new primitives (thus supporting heterogeneous robot swarms), and its run-time platform is designed to be laid on top of other frameworks, such as Robot Operating System. We showcase the capabilities of Buzz by providing code examples, and analyze scalability and robustness of the run-time platform through realistic simulated experiments with representative swarm algorithms.