Alcherio Martinoli

Distributed odor source localization

This paper presents an investigation of odor localization by groups of autonomous mobile robots. First, we describe a distributed algorithm by which groups of agents can solve the full odor localization task. Next, we establish that conducting polymer-based odor sensors possess the combination of speed and sensitivity necessary to enable real world odor plume tracing and we demonstrate that simple local position, odor, and flow information, tightly coupled with robot behavior, is sufficient to allow a robot to localize the source of an odor plume. Finally, we show that elementary communication among a group of agents can increase the efficiency of the odor localization system performance.

Social Integration of Robots into Groups of Cockroaches to Control Self-Organized Choices

Collective behavior based on self-organization has been shown in group-living animals from insects to vertebrates. These findings have stimulated engineers to investigate approaches for the coordination of autonomous multirobot systems based on self-organization. In this experimental study, we show collective decision-making by mixed groups of cockroaches and socially integrated autonomous robots, leading to shared shelter selection. Individuals, natural or artificial, are perceived as equivalent, and the collective decision emerges from nonlinear feedbacks based on local interactions. Even when in the minority, robots can modulate the collective decision-making process and produce a global pattern not observed in their absence. These results demonstrate the possibility of using intelligent autonomous devices to study and control self-organized behavioral patterns in group-living animals.

Modeling Swarm Robotic Systems: a Case Study in Collaborative Distributed Manipulation

In this paper, we present a time-discrete, incremental methodology for modeling, at the microscopic and macroscopic levels, the dynamics of distributed manipulation experiments using swarms of autonomous robots endowed with reactive controllers. The methodology is well suited for non-spatial metrics, as it does not take into account robot trajectories or the spatial distribution of objects in the environment. The strength of the methodology lies in the fact that it has been generated by considering incremental abstraction steps, fromreal robots to macroscopic models, each with well-defined mappings between successive implementation levels. Precise heuristic criteria based on geometrical considerations and systematic tests with one or two real robots prevent the introduction of free parameters in the calibration procedure of models. As a consequence, we are able to generate highly abstracted macroscopic models that can capture the dynamics of a swarm of robots at the behavioral level while still being closely anchored to the characteristics of the physical setup. Although this methodology has been and can be applied to other experiments in distributed manipulation (e.g. object aggregation and segregation, foraging), in this paper we focus on a strictly collaborative case study concerned with pulling sticks out of the ground, an action that requires the collaboration of two robots to be successful. Experiments were carried out with teams consisting of two to 600 individuals at different levels of implementation (real robots, embodied simulations, microscopic and macroscopic models). Results show that models can deliver both qualitatively and quantitatively correct predictions in time lapses that are at least four orders of magnitude smaller than those required by embodied simulations and that they represent a useful tool for generalizing the dynamics of these highly stochastic, asynchronous, nonlinear systems, often outperforming intuitive reasoning. Finally, in addition to discussing subtle numerical effects, small prediction discrepancies, and difficulties in generating the mapping between different abstractions levels, we conclude the paper by reviewing the intrinsic limitations of the current modeling methodology and by proposing a few suggestions for future work.

Towards multi-level modeling of self-assembling intelligent micro-systems

The development of enabling infrastructure for the next generation of multi-agent systems consisting of large numbers of agents and operating in open environments is one of the key challenges for the multi-agent community.Current infrastructure support does not materially assist in the development of sophisticated agent coordination strategies. It is the need for and the development of such a high-level support structure that will be the focus of this paper. A domain-independent (generic) agent architecture is proposed that wraps around an agents problem-solving component in order to make problem solving responsive to real-time constraints, available network resources, and the need to coordinate—both in the large and small—with problem-solving activities of other agents. This architecture contains five components, local agent scheduling, multi-agent coordination, organizational design, detection and diagnosis, and on-line learning, that are designed to interact so that a range of different situation-specific coordination strategies can be implemented and adapted as the situation evolves. The presentation of this architecture is followed by a more detailed discussion on the interaction among these components and the research questions that need to be answered to understand the appropriateness of this architecture for the next generation of multi-agent systems.We investigate and model the dynamics of two-dimensional stochastic self-assembly of intelligent micro-systems with minimal requirements in terms of sensing, actuation, and control. A microscopic agent-based model accounts for spatiality and serves as a baseline for assessing the accuracy of models at higher abstraction level. Spatiality is relaxed in Monte Carlo simulations, which still capture the binding energy of each individual aggregate. Finally, we introduce a macroscopic model that only keeps track of the average number of aggregates in each energy state. This model is able to quantitatively and qualitatively predict the dynamics observed at lower, more detailed modeling levels. Since we investigate an idealized system, thus making very few assumptions about the exact nature of the final target system, our framework is potentially applicable to a large body of self-assembling agents ranging from functional micro-robots endowed with simple sensors and actuators to elementary microfabricated parts. In particular, we show how our suite of models at different abstraction levels can be used for optimizing both the design of the building blocks and the control of the stochastic process.

Inspiring and Modeling Multi-Robot Search with Particle Swarm Optimization

Within the field of multi-robot systems, multi-robot search is one area which is currently receiving a lot of research attention. One major challenge within this area is to design effective algorithms that allow a team of robots to work together to find their targets. Techniques have been adopted for multi-robot search from the particle swarm optimization algorithm, which uses a virtual multi-agent search to find optima in a multi-dimensional function space. We present here a multi-search algorithm inspired by particle swarm optimization. Additionally, we exploit this inspiration by modifying the particle swarm optimization algorithm to mimic the multi-robot search process, thereby allowing us to model at an abstracted level the effects of changing aspects and parameters of the system such as number of robots and communication range

Understanding collective aggregation mechanisms: From probabilistic modelling to experiments with real robots

Abstract This paper presents an experiment of clustering implemented at three different levels: in a hardware implementation, in a sensor-based simulation and in a probabilistic model. The experiment consists of small reactive autonomous robots gathering and clustering randomly distributed objects. It is shown that, while the behaviour of the real robots can be faithfully reproduced in a sensor-based simulation, the evolution of the cluster sizes is perfectly described, both qualitatively and quantitatively, by a simple probabilistic model. Rather than simulating robots moving within an environment, the probabilistic model represents the clustering activity as a sequence of probabilistic events during which cluster sizes can be modified depending on simple geometrical considerations.

SwisTrack - a flexible open source tracking software for multi-agent systems

Vision-based tracking is used in nearly all robotic laboratories for monitoring and extracting of agent positions, orientations, and trajectories. However, there is currently no accepted standard software solution available, so many research groups resort to developing and using their own custom software. In this paper, we present version 4 of SwisTrack, an open source project for simultaneous tracking of multiple agents. While its broad range of pre-implemented algorithmic components allows it to be used in a variety of experimental applications, its novelty stands in its highly modular architecture. Advanced users can therefore also implement additional customized modules which extend the functionality of the existing components within the provided interface. This paper introduces SwisTrack and shows experiments with both marked and marker-less agents.

Swarm robotic odor localization

This paper presents an investigation of odor localization by groups of autonomous mobile robots using principles of swarm intelligence. We describe a distributed algorithm by which groups of agents can solve the full odor localization task more efficiently than a single agent. We then demonstrate that a group of real robots under fully distributed control can successfully traverse a real odor plume. Finally, we show that an embodied simulator can faithfully reproduce the real robots experiments and thus can be a useful tool for off-line study and optimization of odor localization in the real world.

Multi-robot learning with particle swarm optimization

We apply an adapted version of Particle Swarm Optimization to distributed unsupervised robotic learning in groups of robots with only local information. The performance of the learning technique for a simple task is compared across robot groups of various sizes, with the maximum group size allowing each robot to individually contain and manage a single PSO particle. Different PSO neighborhoods based on limitations of real robotic communication are tested in this scenario, and the effect of varying communication power is explored. The algorithms are then applied to a group learning scenario to explore their susceptibility to the credit assignment problem. Results are discussed and future work is proposed.

Swarm robotic odor localization: Off-line optimization and validation with real robots

This paper presents an investigation of odor localization by groups of autonomous mobile robots using principles of Swarm Intelligence. First, we describe a distributed algorithm by which groups of agents can solve the full odor localization task more efficiently than a single agent. Next, we demonstrate that a group of real robots under fully distributed control can successfully traverse a real odor plume, and that an embodied simulator can faithfully reproduce these real robots experiments. Finally, we use the embodied simulator combined with a reinforcement learning algorithm to optimize performance across group size, showing that it can be useful not only for improving real world odor localization, but also for quantitatively characterizing the influence of group size on task performance.