Leandro Soriano Marcolino

Traffic control for a swarm of robots: Avoiding target congestion

One of the main problems in the navigation of robotic swarms is when several robots try to reach the same target at the same time, causing congestion situations that may compromise performance. In this paper, we propose a distributed coordination algorithm to alleviate this type of congestion. Using local sensing and communication, and controlling their actions using a probabilistic finite state machine, robots are able to coordinate themselves to avoid these situations. Simulations and real experiments were executed to study the performance and effectiveness of the proposed algorithm. Results show that the algorithm allows the swarm to have a more efficient and smoother navigation and is suitable for large groups of robots.

Traffic control for a swarm of robots: Avoiding group conflicts

A very common problem in the navigation of robotic swarms is when groups of robots move into opposite directions, causing congestion situations that may compromise performance. In this paper, we propose a distributed coordination algorithm to alleviate this type of congestion. By working collaboratively, and warning their teammates about a congestion risk, robots are able to coordinate themselves to avoid these situations. We executed simulations and real experiments to study the performance and effectiveness of the proposed algorithm. Results show that the algorithm allows the swarm to navigate in a smoother and more efficient fashion, and is suitable for large groups of robots.

Avoiding target congestion on the navigation of robotic swarms

Robotic swarms are decentralized systems formed by a large number of robots. A common problem encountered in a swarm is congestion, as a great number of robots often must move towards the same region. This happens when robots have a common target, for example during foraging or waypoint navigation. We propose three algorithms to alleviate congestion: in the first, some robots stop moving towards the target for a random number of iterations; in the second, we divide the scenario in two regions: one for the robots that are moving towards the target, and another for the robots that are leaving the target; in the third, we combine the two previous algorithms. We evaluate our algorithms in simulation, where we show that all of them effectively improve navigation. Moreover, we perform an experimental analysis in the real world with ten robots, and show that all our approaches improve navigation with statistical significance.

Multi-agent team formation for design problems

Design imposes a novel social choice problem: using a team of voting agents, maximize the number of optimal solutions; allowing a user to then take an aesthetical choice. In an open system of design agents, team formation is fundamental. We present the first model of agent teams for design. For maximum applicability, we envision agents that are queried for a single opinion, and multiple solutions are obtained by multiple iterations. We show that diverse teams composed of agents with different preferences maximize the number of optimal solutions, while uniform teams composed of multiple copies of the best agent are in general suboptimal. Our experiments study the model in bounded time; and we also study a real system, where agents vote to design buildings.

A Detailed Analysis of a Multi-agent Diverse Team

In an open system we can have many different kinds of agents. However, it is a challenge to decide which agents to pick when forming multi-agent teams. In some scenarios, agents coordinate by voting continuously. When forming such teams, should we focus on the diversity of the team or on the strength of each member? Can a team of diverse (and weak) agents outperform a uniform team of strong agents? We propose a new model to address these questions. Our key contributions include: (i) we show that a diverse team can overcome a uniform team and we give the necessary conditions for it to happen; (ii) we present optimal voting rules for a diverse team; (iii) we perform synthetic experiments that demonstrate that both diversity and strength contribute to the performance of a team; (iv) we show experiments that demonstrate the usefulness of our model in one of the most difficult challenges for Artificial Intelligence: Computer Go.

Genome Visualization in Space

Phylogeny is an important field to understand evolution and the organization of life. However, most methods depend highly on manual study and analysis, making the construction of phylogeny error prone. Linear Algebra methods are known to be efficient to deal with the semantic relationships between a large number of elements in spaces of high dimensionality. Therefore, they can be useful to help the construction of phylogenetic trees. The ability to visualize the relationships between genomes is crucial in this process. In this paper, a linear algebra method, followed by optimization, is used to generate a visualization of a set of complete genomes. Using the proposed method we were able to visualize the relationships of 64 complete mitochondrial genomes, organized as six different groups, and of 31 complete mitochondrial genomes of mammals, organized as nine different groups. The prespecified groups could be seen clustered together in the visualization, and similar species were represented close together. Besides, there seems to be an evolutionary influence in the organization of the graph.

Every team deserves a second chance: an extended study on predicting team performance

Voting among different agents is a powerful tool in problem solving, and it has been widely applied to improve the performance in finding the correct answer to complex problems. We present a novel benefit of voting, that has not been observed before: we can use the voting patterns to assess the performance of a team and predict their final outcome. This prediction can be executed at any moment during problem-solving and it is completely domain independent. Hence, it can be used to identify when a team is failing, allowing an operator to take remedial procedures (such as changing team members, the voting rule, or increasing the allocation of resources). We present three main theoretical results: (1) we show a theoretical explanation of why our prediction method works; (2) contrary to what would be expected based on a simpler explanation using classical voting models, we show that we can make accurate predictions irrespective of the strength (i.e., performance) of the teams, and that in fact, the prediction can work better for diverse teams composed of different agents than uniform teams made of copies of the best agent; (3) we show that the quality of our prediction increases with the size of the action space. We perform extensive experimentation in two different domains: Computer Go and Ensemble Learning. In Computer Go, we obtain high quality predictions about the final outcome of games. We analyze the prediction accuracy for three different teams with different levels of diversity and strength, and show that the prediction works significantly better for a diverse team. Additionally, we show that our method still works well when trained with games against one adversary, but tested with games against another, showing the generality of the learned functions. Moreover, we evaluate four different board sizes, and experimentally confirm better predictions in larger board sizes. We analyze in detail the learned prediction functions, and how they change according to each team and action space size. In order to show that our method is domain independent, we also present results in Ensemble Learning, where we make online predictions about the performance of a team of classifiers, while they are voting to classify sets of items. We study a set of classical classification algorithms from machine learning, in a data-set of hand-written digits, and we are able to make high-quality predictions about the final performance of two different teams. Since our approach is domain independent, it can be easily applied to a variety of other domains.

Algorithms or Actions? A Study in Large-Scale Reinforcement Learning

Large state and action spaces are very challenging to reinforcement learning. However, in many domains there is a set of algorithms available, which estimate the best action given a state. Hence, agents can either directly learn a performance-maximizing mapping from states to actions, or from states to algorithms. We investigate several aspects of this dilemma, showing sufficient conditions for learning over algorithms to outperform over actions for a finite number of training iterations. We present synthetic experiments to further study such systems. Finally, we propose a function approximation approach, demonstrating the effectiveness of learning over algorithms in real-time strategy games.

The Power of Teams that Disagree: Team Formation in Large Action Spaces

Recent work has shown that diverse teams can outperform a uniform team made of copies of the best agent. However, there are fundamental questions that were never asked before. When should we use diverse or uniform teams? How does the performance change as the action space or the teams get larger? Hence, we present a new model of diversity, where we prove that the performance of a diverse team improves as the size of the action space increases. Moreover, we show that the performance converges exponentially fast to the optimal one as we increase the number of agents. We present synthetic experiments that give further insights: even though a diverse team outperforms a uniform team when the size of the action space increases, the uniform team will eventually again play better than the diverse team for a large enough action space. We verify our predictions in a system of Go playing agents, where a diverse team improves in performance as the board size increases, and eventually overcomes a uniform team.

Experiments in the Coordination of Large Groups of Robots

The use of large groups of robots, generally called swarms, has gained increased attention in recent years. In this paper, we present and experimentally validate an algorithm that allows a swarm of robots to navigate in an environment containing unknown obstacles. A coordination mechanism based on dynamic role assignment and local communication is used to help robots that may get stuck in regions of local minima. Experiments were performed using both a realistic simulator and a group of real robots and the obtained results showed the feasibility of the proposed approach.