Vasco Costa

Evolution of Collective Behaviors for a Real Swarm of Aquatic Surface Robots.

Swarm robotics is a promising approach for the coordination of large numbers of robots. While previous studies have shown that evolutionary robotics techniques can be applied to obtain robust and efficient self-organized behaviors for robot swarms, most studies have been conducted in simulation, and the few that have been conducted on real robots have been confined to laboratory environments. In this paper, we demonstrate for the first time a swarm robotics system with evolved control successfully operating in a real and uncontrolled environment. We evolve neural network-based controllers in simulation for canonical swarm robotics tasks, namely homing, dispersion, clustering, and monitoring. We then assess the performance of the controllers on a real swarm of up to ten aquatic surface robots. Our results show that the evolved controllers transfer successfully to real robots and achieve a performance similar to the performance obtained in simulation. We validate that the evolved controllers display key properties of swarm intelligence-based control, namely scalability, flexibility, and robustness on the real swarm. We conclude with a proof-of-concept experiment in which the swarm performs a complete environmental monitoring task by combining multiple evolved controllers.

Hybrid Control for a Real Swarm Robotics System in an Intruder Detection Task

Control design is one of the prominent challenges in the field of swarm robotics. Evolutionary robotics is a promising approach to the synthesis of self-organized behaviors for robotic swarms but it has, so far, only produced been shown in relatively simple collective behaviors. In this paper, we explore the use of a hybrid control synthesis approach to produce control for a swarm of aquatic surface robots that must perform an intruder detection task. The robots have to go to a predefined area, monitor it, detect and follow intruders, and manage their energy levels by regularly recharging at a base station. The hybrid controllers used in our experiments rely on evolved behavior primitives that are combined through a manually programmed high-level behavior arbitrator. In simulation, we show how simple modifications to the behavior arbitrator can result in different swarm behaviors that use the same underlying behavior primitives, and we show that the composed behaviors are scalable with respect to the swarm size. Finally, we demonstrate the synthesized controller in a real swarm of robots, and show that the behavior successfully transfers from simulation to reality.

Design of Communication and Control for Swarms of Aquatic Surface Drones

The availability of relatively capable and inexpensive hardware components has made it feasible to consider large-scale systems of autonomous aquatic drones for maritime tasks. In this paper, we present the CORATAM and HANCAD projects, which focus on the fundamental challenges related to communication and control in swarms of aquatic drones. We argue for: (i) the adoption of a heterogeneous approach to communication in which a small subset of the drones have long-range communication capabilities while the majority carry only short-range communication hardware, and (ii) the use of decentralized control to facilitate inherent robustness and scalability. A heterogeneous communication system and decentralized control allow for the average drone to be kept relatively simple and therefore inexpensive. To assess the proposed methodology, we are currently building 25 prototype drones from off-the-shelf components. We present the current hardware designs and discuss the results of simulation-based experiments involving swarms of up to 1,000 aquatic drones that successfully patrolled a 20 km-long strip for 24 hours.

Design and development of an inexpensive aquatic swarm robotics system

Swarm robotics is a promising approach characterized by large numbers of relatively small and inexpensive robots. Since such systems typically rely on decentralized control and local communication, they exhibit a number of interesting and useful properties, namely scalability, robustness to individual faults, and flexibility. In this paper, we detail the design and development process of a swarm robotics platform composed of autonomous surface robots, which was designed in order to study the use of robotic swarms in real-world environments. Our aquatic surface robots where manufactured using digital fabrication techniques, such as 3D printing and CNC milling, and all hardware and software has been made available as open-source, thus allowing third-parties to customize and further improve our platform.

Unleashing the Potential of Evolutionary Swarm Robotics in the Real World

We provide a summary of our real-world experiments with a swarm of aquatic surface robots with evolved control. Robotic control was synthesized in simulation, using of- fline evolutionary robotics techniques, and then successfully transferred to a real swarm. Our study presents one of the first demonstrations of evolved control in a swarm robotics system outside of controlled laboratory conditions. Original publication: M. Duarte, V. Costa, J. Gomes, T. Rodrigues, F. Silva, S. M. Oliveira, and A. L. Christensen. Evolution of collective behaviors for a real swarm of aquatic surface robots. PLoS ONE, 11(3):e0151834, 2016.

Overcoming Limited Onboard Sensing in Swarm Robotics Through Local Communication

In swarm robotics systems, the constituent robots are typically equipped with simple onboard sensors of limited quality and range. In this paper, we propose to use local communication to enable sharing of sensory information between neighboring robots to overcome the limitations of onboard sensors. Shared information is used to compute readings for virtual, collective sensors that, to a control program, are indistinguishable from a robot’s onboard sensors. We evaluate two implementations of collective sensors: one that relies on sharing of immediate sensory information within a local frame of reference, and another that relies on sharing of accumulated sensory information within a global frame of reference. We compare performance of swarms using collective sensors with: (i) swarms in which robots only use their onboard sensors, and (ii) swarms in which the robots have idealized sensors. Our experimental results show that collective sensors significantly improve the swarm’s performance by effectively extending the capabilities of the individual robots.