For a summary of our activities please download our press pack. Need more information? Contact our Communications Officer:
Looking for publications? You might want to consider searching on the EPFL Infoscience site which provides advanced publication search capabilities.
In this work we propose a novel fully distributed approach to endow robots in a swarm with awareness of their relative position with respect to the rest of the swarm. Such spatial awareness can be used to support spatially differentiated task allocation or for pattern formation. In particular, we aim to partition the robots in the swarm in two (or more) distinct and spatially segregated groups. The distributed approach we propose only relies on local wireless communications and is based on a combination of distributed consensus and load balancing. We propose two metrics to measure the effectiveness of the obtained partitioning and we test the performance and the scalability of our algorithm in extensive simulation experiments. We also validate it in a small set of experiments with real robots.
Evaluative techniques offer a tremendous potential for online controller design. However, when the optimization space is large and the performance metric is noisy, the overall adaptation process becomes extremely time consuming. Distributing the adaptation process reduces the required time and increases robustness to failure of individual agents. In this paper, we analyze the role of the four algorithmic parameters that determine the total evaluation time in a distributed implementation of a Particle Swarm Optimization (PSO) algorithm. For an obstacle avoidance case study using up to eight robots, we explore in simulation the lower boundaries of these parameters and propose a set of empirical guidelines for choosing their values. We then apply these guidelines to a real robot implementation and show that it is feasible to optimize 24 control parameters per robot within 2 h, a limited amount of time determined by the robots’ battery life. We also show that a hybrid simulate-and-transfer approach coupled with a noise-resistant PSO algorithm can be used to further reduce experimental time as compared to a pure real-robot implementation.
Large numbers of collaborating robots are advantageous for solving distributed problems. In order to efficiently solve the task at hand, the robots often need accurate localization. In this work, we address the localization problem by developing a solution that has low computational and sensing requirements, and that is easily deployed on large robot teams composed of cheap robots. We build upon a real-time, particle-filter based localization algorithm that is completely decentralized and scalable, and accommodates realistic robot assumptions including noisy sensors, and asynchronous and lossy communication. In order to further reduce this algorithm’s overall complexity, we propose a low-cost particle clustering method, which is particularly well suited to the collaborative localization problem. Our approach is experimentally validated on a team of ten real robots.
The ability to move in complex environments is a fundamental requirement for robots to be a part of our daily lives. While in simple environments it is usually straightforward for human designers to foresee the different conditions a robot will be exposed to, for more complex environments the human design of high-performing controllers becomes a challenging task, especially when the on-board resources of the robots are limited. In this article, we use a distributed implementation of Particle Swarm Optimization to design robotic controllers that are able to navigate around obstacles of different shape and size. We analyze how the behavior and performance of the controllers differ based on the environment where learning takes place, showing that different arenas lead to different avoidance behaviors. We also test the best controllers in environments not encountered during learning, both in simulation and with real robots, and show that no single learning environment is able to generate a behavior general and robust enough to succeed in all testing environments.