Body-machine interfaces for robotic teleoperation have been shown to improve user experience and performance. However, such interfaces must be tailored for each robot type and may require personalization to accommodate user’s preferences. Here, we present a novel method to adaptively generate personalized body-machine interfaces from an operator’s preferred body movements. The method captures individual motor synergies that are correlated to robot actions and translates them into control commands. The proposed method is validated on a set of users with varied behavioral patterns for teleoperating robots with diverse morphologies and degrees of freedom, such as a fixed-wing drone, a quadrotor, and a robotic manipulator.

The design and control of winged aircraft and drones is an iterative process aimed at identifying a compromise of mission-specific costs and constraints. When agility is required, shape-shifting (morphing) drones represent an efficient solution. However, morphing drones require the addition of actuated joints that increase the topology and control coupling, making the design process more complex. We propose a co-design optimisation method that assists the engineers by proposing a morphing drone’s conceptual design that includes topology, actuation, morphing strategy, and controller parameters. The method consists of applying multi-objective constraint-based optimisation to a multi-body winged drone with trajectory optimisation to solve the motion intelligence problem under diverse flight mission requirements, such as energy consumption and mission completion time. We show that co-designed morphing drones outperform fixed-winged drones in terms of energy efficiency and mission time, suggesting that the proposed co-design method could be a useful addition to the aircraft engineering toolbox.

Coordinated flight of multiple drones allows to achieve tasks faster such as search and rescue and infrastructure inspection. Thus, pushing the State-of-the-Art of aerial swarms in navigation speed and robustness is of tremendous benefit. In particular, being able to account for unexplored/unknown environments when planning trajectories allows for safer flight. In this work, we propose the first high-speed, decentralized, and synchronous motion planning framework (HDSM) for an aerial swarm that explicitly takes into account the unknown/undiscovered parts of the environment. The proposed approach generates an optimized trajectory for each planning agent that avoids obstacles and other planning agents while moving and exploring the environment. The only global information that each agent has is the target location. The generated trajectory is high-speed, safe from unexplored spaces, and brings the agent closer to its goal. The proposed method outperforms four recent state-of-the-art methods in success rate (100% success in reaching the target location), flight speed (97% faster), and flight time (50% lower). Finally, the method is validated on a set of Crazyflie nano-drones as a proof of concept.

Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking performance, but require high computing power. Conversely, learning-based offline optimization approaches, such as Reinforcement Learning (RL), allow fast and efficient execution on the robot but hardly match the accuracy of MPC in trajectory tracking tasks. In systems with limited compute, such as aerial vehicles, an accurate controller that is efficient at execution time is imperative. We propose an Analytic Policy Gradient (APG) method to tackle this problem. APG exploits the availability of differentiable simulators by training a controller offline with gradient descent on the tracking error. We address training instabilities that frequently occur with APG through curriculum learning and experiment on a widely used controls benchmark, the CartPole, and two common aerial robots, a quadrotor and a fixed-wing drone. Our proposed method outperforms both model-based and model-free RL methods in terms of tracking error. Concurrently, it achieves similar performance to MPC while requiring more than an order of magnitude less computation time. Our work provides insights into the potential of APG as a promising control method for robotics. To facilitate the exploration of APG, we open-source our code and make it available atgithub.com/lis-epfl/apg_trajectory_tracking.

Displaced communication, whereby individuals communicate regarding a subject that is not immediately present (spatially or temporally), is one of the key features of human language. It also occurs in a few animal species, most notably the honeybee, where the waggle dance is used to communicate the location and quality of a patch of flowers. However, it is difficult to study how it emerged given the paucity of species displaying this capacity and the fact that it often occurs via complex multimodal signals. To address this issue, we developed a novel paradigm in which we conducted experimental evolution with foraging agents endowed with neural networks that regulate their movement and the production of signals. Displaced communication readily evolved but, surprisingly, agents did not use signal amplitude to convey information on food location. Instead, they used signal onset-delay and duration-based mode of communication, which depends on the motion of the agent within a communication area. When agents were experimentally prevented from using these modes of communication, they evolved to use signal amplitude instead. Interestingly, this mode of communication was more efficient and led to higher performance. Subsequent controlled experiments suggested that this more efficient mode of communication failed to evolve because it took more generations to emerge than communication grounded on the onset-delay and length of signaling. These results reveal that displaced communication is likely to initially evolve from non-communicative behavioral cues providing incidental information with evolution later leading to more efficient communication systems through a ritualization process.

Animal locomotion results from a combination of power modulation and cyclic appendage trajectories, but combining these two properties in small-sized robots is difficult. Here, we introduce and characterize a new elastic actuation system based on an inverted cam that is capable of generating cyclic locomotion with controlled elastic energy charge and release for small-sized robots. We designed a leg linkage and attached to the inverted cam to develop a single legged hopping platform with one actuated degree of freedom. The hopping platform was able to continuously hop forward at 1.82 Hz. The average horizontal hopping distance was 18.7 cm, and the average forward speed was 0.34 m/s. This speed was corresponding to a Froude number of 0.14. The energy consumed for one hop was 2.09 J, and the corresponding energetic cost of transport was 6.43. The combination of inverted cam and cyclic trajectory generation has the potential to be used in other robotic applications, such as flapping wings in the air and tail fin waving in water.

Electro-adhesive clutches have become effective tools for variable stiffness functions in many robotic systems due to their light weight, high speed and strong brake force. In this paper, we present a novel, tubular design of an electro-adhesive clutch. Our clutch consists of flexible electrode sheets rolled into a tubular structure. This design allows encapsulating large electrode areas in a compact size for strong brake force. Additionally, the tubular structure acts as a guide for directional sliding without external guides. The structure also ensures that the electrode surfaces are encapsulated, preventing the accumulation of dust and thus leading to reliable performance. This structure is therefore an improvement over the commonly used planar designs. The characterization of the electro-adhesive tubular clutch shows that the frictional force increases with the increase of the electrode contact area, the decrease of the roll diameter and the dielectric layer thickness. A retractable tubular clutch is made by fixing an elastic cable along the clutch axis and achieves a stiffness change factor up to 260. Applications of this retractable clutch in robotics to achieve variable stiffness are demonstrated in two systems: a tensegrity structure and a wing skeleton. Changes in stiffness by 13.2 and 30.2 times are achieved for the two systems, respectively. The proposed tubular clutch is an effective means of achieving variable stiffness, particularly in the case of robotic systems that transmit forces through tensioned cables.

Robots using classical control have revolutionised assembly lines where the environment and manipulated objects are restricted and predictable. However, they have proven less effective when the manipulated objects are deformable due to their complex and unpredictable behaviour. The use of tactile sensors and continuous monitoring of tactile feedback is there-fore particularly important for pick-and-place tasks using these materials. This is in part due to the need to use multiple points of contact for the manipulation of deformable objects which can result in slippage with inadequate coordination between manipulators. In this paper, continuous monitoring of tactile feedback, using a liquid metal soft force sensor, for grasping deformable objects is presented. The trained data-driven model distinguishes between successful grasps, slippage and failure during a manipulation task for multiple deformable objects. Slippage could be anticipated before failure occurred using data acquired over a 30 ms period with a greater than 95% accuracy using a random forest classifier. The results were achieved using a single sensor that can be mounted on the fingertips of existing grippers and contributes to the development of an automated pick-and-place process for deformable objects.

Drones have shown to be useful aerial vehicles for unmanned transport missions such as food and medical supply delivery. This can be leveraged to deliver life-saving nutrition and medicine for people in emergency situations. However, commercial drones can generally only carry 10 %–30 % of their own mass as payload, which limits the amount of food delivery in a single flight. One novel solution to noticeably increase the food-carrying ratio of a drone, is recreating some structures of a drone, such as the wings, with edible materials. We thus propose a drone, which is no longer only a food-transporting aircraft, but itself is partially edible, increasing its food-carrying mass ratio to 50 %, owing to its edible wings. Furthermore, should the edible drone be left behind in the environment after performing its task in an emergency situation, it will be more biodegradable than its non-edible counterpart, leaving less waste in the environment. Here we describe the choice of materials and scalable design of edible wings, and validate the method in a flight-capable prototype that can provide 300 kcal and carry a payload of 80 g of water.

Fixed-wing drones must navigate to the desired location accurately for maneuvers such as picking up objects and perching. However, current GNSS receivers limit their navigation accuracy to several meters in outdoor environments, making such maneuvers impossible. RTK GNSS can improve flight accuracy, but it requires ground stations at the target location and additional communication modules on the drone. Here, we describe a fixed-wing platform with onboard computation that uses positional information from a GNSS receiver and vision from an onboard camera. The drone relies on a GNSS signal for flying towards a point of interest and switches to vision-based information to accurately reach the target. We conducted outdoor experiments to compare the flight accuracy of three navigation methods: GNSS, RTK GNSS, and the proposed GNSS-vision method. We also systematically assessed the robustness of vision-based control to compensate for GNSS errors and quantify the accuracy of the proposed method. Our results show that the accuracy of the proposed GNSS-vision system is on par with RTK GNSS. GNSS-vision reduces the average error of GNSS by over an order of magnitude, from 3.033 m to 0.283 m, and reduces the variance across repeated flights from 2.095 m to 0.309 m. We open-source the software-hardware architecture used in this paper to enable the research community to build on these results and expand the capabilities of fixed-wing drones.

Human-Robot Interfaces (HRIs) represent a crucial component in telerobotic systems. Body-Machine Interfaces (BoMIs) based on body motion can feel more intuitive than standard HRIs for naive users as they leverage humans’ natural control capability over their movements. Among the different methods used to map human gestures into robot commands, data-driven approaches select a set of body segments and transform their motion into commands for the robot based on the users’ spontaneous motion patterns. Despite being a versatile and generic method, there is no scientific evidence that implementing an interface based on spontaneous motion maximizes its effectiveness. In this study, we compare a set of BoMIs based on different body segments to investigate this aspect. We evaluate the interfaces in a teleoperation task of a fixed-wing drone and observe users’ performance and feedback. To this aim, we use a framework that allows a user to control the drone with a single Inertial Measurement Unit (IMU) and without prior instructions. All the interfaces are entirely data-driven and depend on the user’s spontaneous motion. We show through a user study that selecting the body segment for a BoMI based on spontaneous motion can lead to sub-optimal performance. Based on our findings, we suggest additional metrics based on biomechanical and behavioral factors that might improve data-driven methods for the design of HRIs.

In search and rescue missions, drone operations are challenging and cognitively demanding. High levels of cognitive workload can affect rescuers' performance, leading to failure with catastrophic outcomes. To face this problem, we propose a machine learning algorithm for real-time cognitive workload monitoring to understand if a search and rescue operator has to be replaced or if more resources are required. Our multimodal cognitive workload monitoring model combines the information of 25 features extracted from physiological signals, such as respiration, electrocardiogram, photoplethysmogram, and skin temperature, acquired in a noninvasive way. To reduce both subject and day inter-variability of the signals, we explore different feature normalization techniques, and introduce a novel weighted-learning method based on support vector machines suitable for subject-specific optimizations. On an unseen test set acquired from 34 volunteers, our proposed subject-specific model is able to distinguish between low and high cognitive workloads with an average accuracy of 87.3% and 91.2% while controlling a drone simulator using both a traditional controller and a new-generation controller, respectively.

Designing optimal soft modular robots is difficult, due to non-trivial interactions between morphology and controller. Evolutionary algorithms (EAs), combined with physical simulators, represent a valid tool to overcome this issue. In this work, we investigate algorithmic solutions to improve the Quality Diversity of co-evolved designs of Tensegrity Soft Modular Robots (TSMRs) for two robotic tasks, namely goal reaching and squeezing trough a narrow passage. To this aim, we use three different EAs, i.e., MAP-Elites and two custom algorithms: one based on Viability Evolution (ViE) and NEAT (ViE-NEAT), the other named Double Map MAP-Elites (DM-ME) and devised to seek diversity while co-evolving robot morphologies and neural network (NN)-based controllers. In detail, DM-ME extends MAP-Elites in that it uses two distinct feature maps, referring to morphologies and controllers respectively, and integrates a mechanism to automatically define the NN-related feature descriptor. Considering the fitness, in the goal-reaching task ViE-NEAT outperforms MAP-Elites and results equivalent to DM-ME. Instead, when considering diversity in terms of "illumination" of the feature space, DM-ME outperforms the other two algorithms on both tasks, providing a richer pool of possible robotic designs, whereas ViE-NEAT shows comparable performance to MAP-Elites on goal reaching, although it does not exploit any map.

The operation of telerobotic systems can be a challenging task, requiring intuitive and efficient interfaces to enable inexperienced users to attain a high level of proficiency. Body-Machine Interfaces (BoMI) represent a promising alternative to standard control devices, such as joysticks, because they leverage intuitive body motion and gestures. It has been shown that the use of Virtual Reality (VR) and first-person view perspectives can increase the user's sense of presence in avatars. However, it is unclear if these beneficial effects occur also in the teleoperation of non-anthropomorphic robots that display motion patterns different from those of humans. Here we describe experimental results on teleoperation of a non-anthropomorphic drone showing that VR correlates with a higher sense of spatial presence, whereas viewpoints moving coherently with the robot are associated with a higher sense of embodiment. Furthermore, the experimental results show that spontaneous body motion patterns are affected by VR and viewpoint conditions in terms of variability, amplitude, and robot correlates, suggesting that the design of BoMIs for drone teleoperation must take into account the use of Virtual Reality and the choice of the viewpoint.

Besides being part of the Internet of Things (IoT), drones can play a relevant role in it as enablers. The 3D mobility of UAVs can be exploited to improve node localization in IoT networks for, e.g., search and rescue or goods localization and tracking. One of the widespread IoT communication technologies is Long Range Wide Area Network (LoRaWAN), which allows achieving long communication distances with low power. In this work, we present a drone-aided localization system for LoRa networks in which a UAV is used to improve the estimation of a node's location initially provided by the network. We characterize the relevant parameters of the communication system and use them to develop and test a search algorithm in a realistic simulated scenario. We then move to the full implementation of a real system in which a drone is seamlessly integrated into Swisscom's LoRa network. The drone coordinates with the network with a two-way exchange of information which results in an accurate and fully autonomous localization system. The results obtained in our field tests show a ten-fold improvement in localization precision with respect to the estimation provided by the fixed network. Up to our knowledge, this is the first time a UAV is successfully integrated in a LoRa network to improve its localization accuracy.

Drone teleoperation is usually accomplished using remote radio controllers, devices that can be hard to master for inexperienced users. Moreover, the limited amount of information fed back to the user about the robot's state, often limited to vision, can represent a bottleneck for operation in several conditions. In this work, we present a wearable interface for drone teleoperation and its evaluation through a user study. The two main features of the proposed system are a data glove to allow the user to control the drone trajectory by hand motion and a haptic system used to augment their awareness of the environment surrounding the robot. This interface can be employed for the operation of robotic systems in line of sight (LoS) by inexperienced operators and allows them to safely perform tasks common in inspection and search-and-rescue missions such as approaching walls and crossing narrow passages with limited visibility conditions. In addition to the design and implementation of the wearable interface, we performed a systematic study to assess the effectiveness of the system through three user studies (n = 36) to evaluate the users' learning path and their ability to perform tasks with limited visibility. We validated our ideas in both a simulated and a real-world environment. Our results demonstrate that the proposed system can improve teleoperation performance in different cases compared to standard remote controllers, making it a viable alternative to standard Human-Robot Interfaces.

This paper presents a method to create fish-like robots with tensegrity systems and describes a prototype modeled on the body shape of the rainbow trout with a length of 400 mm and a mass of 102 g that is driven by a waterproof servomotor. The structure of the tensegrity robot consists of rigid body segments and elastic cables that represent bone/tissue and muscles of fish, respectively. This structural configuration employing the tensegrity class 2 is much simpler than other tensegrity-based underwater robots. It also allows the tuning of the mechanical stiffness, which is often said to be an important factor in fish swimming. In our robot, the body stiffness can be tuned by changing the cross-section of the cables and their pre-stretch ratio. We characterize the robot in terms of body stiffness, swimming speed, and thrust force while varying the body stiffness i.e., the cross-section of the elastic cables. The results show that the body stiffness of the robot can be designed to approximate that of the real fish and modulate its performance characteristics. The measured swimming speed of the robot is 0.23 m/s (0.58 BL/s), which is comparable to other fish robots of the same type. Strouhal number of the robot 0.54 is close to that of the natural counterpart, suggesting that the presented method is an effective engineering approach to realize the swimming characteristics of real fish.

Small unmanned aerial vehicles (UAV) have penetrated multiple domains over the past years. In GNSS-denied or indoor environments, aerial robots require a robust and stable localization system, often with external feedback, in order to fly safely. Motion capture systems are typically utilized indoors when accurate localization is needed. However, these systems are expensive and most require a fixed setup. In this paper, we study and characterize an ultra-wideband (UWB) system for navigation and localization of aerial robots indoors based on Decawave's DWM1001 UWB node. The system is portable, inexpensive and can be battery powered in its totality. We show the viability of this system for autonomous flight of UAVs, and provide open-source methods and data that enable its widespread application even with movable anchor systems. We characterize the accuracy based on the position of the UAV with respect to the anchors, its altitude and speed, and the distribution of the anchors in space. Finally, we analyze the accuracy of the self-calibration of the anchors' positions.

Among the available solutions for drone swarm simulations, we identified a lack of simulation frameworks that allow easy algorithms prototyping, tuning, debugging and performance analysis. Moreover, users who want to dive in the research field of drone swarms often need to interface with multiple programming languages. We present SwarmLab, a software entirely written in MATLAB, that aims at the creation of standardized processes and metrics to quantify the performance and robustness of swarm algorithms, and in particular, it focuses on drones. We showcase the functionalities of SwarmLab by comparing two decentralized algorithms from the state of the art for the navigation of aerial swarms in cluttered environments, Olfati-Saber's and Vasarhelyi's. We analyze the variability of the inter-agent distances and agents' speeds during flight. We also study some of the performance metrics presented, i.e. order, inter- and extra-agent safety, union, and connectivity. While Olfati-Saber's approach results in a faster crossing of the obstacle field, Vasarhelyi's approach allows the agents to fly smoother trajectories, without oscillations. We believe that SwarmLab is relevant for both the biological and robotics research communities, and for education, since it allows fast algorithm development, the automatic collection of simulated data, the systematic analysis of swarming behaviors with performance metrics inherited from the state of the art.

A swarm of randomly moving miniature robots is an effective solution for the exploration of unknown terrains. However, the deployment of a swarm of miniature robots poses two challenges: finding an adequate locomotion strategy for fast exploration and obstacles negotiation; and implementing simple design and control solutions suited for mass manufacturing. Here, we tackle these challenges by developing a new soft robot with a minimalistic design and a simple control strategy that can randomly propel itself above obstacles and roll on the ground upon landing. The robot is equipped with two propellers that are periodically activated to jump, a soft cage that protects the robot from impacts and allows to passively roll on the ground, and a passive self-righting mechanism for repetitive jumps. The minimalistic control and design reduce the complexity of the mechanics and electronics and are instrumental to the production of a large number of robots. In the paper, the key design aspects of the robot are discussed, the locomotion of a single prototype is experimentally characterized, and improvements of the system for future swarm operations are discussed.

Remote magnetic navigation of catheters is a technique used to perform radiofrequency ablation of heart tissue in order to treat cardiac arrhythmias. The flexible magnetic catheters used in this context are in some cases not sufficiently dexterous to navigate the complex and patient-specific anatomy of the heart. To overcome such limitations, this paper proposes a new approach that relies on the integration of variable stiffness segments into a magnetic catheter. The magnetic variable stiffness (VS) catheter presented here is based on silicone and a low melting point alloy (LMPA) that transforms from a solid to liquid phase upon joule heating. This dramatically changes the bending stiffness of the segment in which it is integrated, improving dexterity. Compared to standard catheters, a VS catheter can partially (just one segment) or completely lock its shape (shape fixity) in order to explore a larger 3D volume inside a magnetic navigation system, thus extending regions of the heart that can be reached for performing ablation procedures.

Multicopters stand to revolutionize parcel delivery because of their capability to operate in areas with unsuitable road infrastructure and precisely maneuver in cluttered environments. However, current multicopters for delivery can be dangerous for people, and are difficult to store and transport. Safety issues arise because users are exposed to unshielded spinning propellers. Transportation to the place of deployment and storage is often impaired by the large size that is required for heavy lifting. This paper addresses these limitations by proposing the integration of a quadcopter into a foldable protective cage. The cage provides an all-round protective structure that physically separates the propellers from the environment, ensuring the safety of people. The drone and the cage can be easily folded with a single movement, significantly reducing its size for ease of storage and transportation. This design has been validated with a quadcopter that can lift parcels up to 500 g and reduce its storage volume by 92% when folded.

Bio-inspired underwater robots have several benefits compared to traditional underwater vehicles such as agility, efficiency, and environmentally friendly body. However, bio-inspired underwater robots developed so far have a single swimming mode, which may limit their capability to perform different tasks. This paper presents a re-configurable bio-inspired underwater robot that can change the morphology to enable multiple swimming modes: octopus-mode and fish-mode. The robot is 60 cm long and 50 cm wide, weighing 2.1 kg, and consists of a re-configurable body and 8 compliant arms that are actuated independently by waterproof servomotors. In the robot, the octopus-mode is expected to perform unique tasks such as object manipulation and ground locomotion as demonstrated in literature, while the fish-mode is promising to swim faster and efficiently to travel long distance. With this platform, we investigate the effectiveness of adaptive morphology in bio-inspired underwater robots. For this purpose, we evaluated the robot in terms of the cost of transport and the swimming efficiency of both the morphologies. The fish-mode exhibited a lower cost of transport of 2.2 and higher efficiency of 1.2 % compared to the octopus-mode, illustrating the effect of the multiple swimming modes by adaptive morphology.

We present a fully edible pneumatic actuator based on gelatin-glycerol material. The actuator is monolithic, fabricated via a molding process, and measures 90 mm in length, 20 mm in width, and 17 mm in thickness. Thanks to the material mechanical characteristics similar to those of silicone elastomers, the actuator exhibits a bending angle of 170.3 ° and a blocked force of 0.34 N at the applied pressure of 25 kPa. These values are comparable to elastomer based pneumatic actuators. As a validation example, two actuators are integrated to form a gripper capable of handling various objects, highlighting the high performance and applicability of the edible actuator. These edible actuators, combined with other recent edible materials and electronics, could lay the foundation for a new type of edible robots.

Evolutionary algorithms are increasingly being applied to problems that are too computationally expensive to run on a single personal computer due to costly fitness function evaluations and/or large numbers of fitness evaluations. Here, we introduce the Seamless Peer And Cloud Evolution (SPACE) framework, which leverages bleeding edge web technologies to allow the computational resources necessary for running large scale evolutionary experiments to be made available to amateur and professional researchers alike, in a scalable and cost-effective manner, directly from their web browsers. The SPACE framework accomplishes this by distributing fitness evaluations across a heterogeneous pool of cloud compute nodes and peer computers. As a proof of concept, this framework has been attached to the \hbox{RoboGen\texttrademark} open-source platform for the co-evolution of robot bodies and brains, but importantly the framework has been built in a modular fashion such that it can be easily coupled with other evolutionary computation systems.

Flying robots are increasingly adopted in search and rescue missions because of their capability to quickly collect and stream information from remote and dangerous areas. To further enhance their use, we are investigating the development of a new class of drones, foldable sensorized hubs that can quickly take off from rescuers' hands as soon as they are taken out of a pocket or a backpack. With this aim, this paper presents the development of a foldable wing inspired by insects. The wing can be packaged for transportation or deployed for flight in half a second with a simple action from the user. The wing is manufactured as a thick origami structure with a foldable multi-layer material. The prototype of the foldable wing is experimentally characterized and validated in flight on a mini-drone.

Dielectric elastomer actuators (DEAs), a soft actuator technology, hold great promise for biomimetic underwater robots. The high-voltages required to drive DEAs can however make them challenging to use in water. This paper demonstrates a method to create DEA-based biomimetic swimming robots that operate reliably even in conductive liquids. We ensure the insulation of the high-voltage DEA electrodes without degrading actuation performance by laminating silicone layers. A fish and a jellyfish were fabricated and tested in water. The fish robot has a length of 120 mm and a mass of 3.8 g. The jellyfish robot has a 61 mm diameter for a mass of 2.6 g. The measured swimming speeds for a periodic 3 kV drive voltage were ~8 mm/s for the fish robot, and ~1.5 mm/s for the jellyfish robot.

The performance of evolutionary algorithms can be heavily undermined when constraints limit the feasible areas of the search space. For instance, while covariance matrix adaptation evolution strategy (CMA-ES) is one of the most efficient algorithms for unconstrained optimization problems, it cannot be readily applied to constrained ones. Here, we used concepts from memetic computing, i.e., the harmonious combination of multiple units of algorithmic information, and viability evolution, an alternative abstraction of artificial evolution, to devise a novel approach for solving optimization problems with inequality constraints. Viability evolution emphasizes the elimination of solutions that do not satisfy viability criteria, which are defined as boundaries on objectives and constraints. These boundaries are adapted during the search to drive a population of local search units, based on CMA-ES, toward feasible regions. These units can be recombined by means of differential evolution operators. Of crucial importance for the performance of our method, an adaptive scheduler toggles between exploitation and exploration by selecting to advance one of the local search units and/or recombine them. The proposed algorithm can outperform several state-of-the-art methods on a diverse set of benchmark and engineering problems, both for quality of solutions and computational resources needed.

Aerial robots provide valuable support in several high-risk scenarios thanks to their capability to quickly fly to locations dangerous or even inaccessible to humans. In order to fully benefit from these features, aerial robots should be easy to transport and rapid to deploy. With this aim, this paper focuses on the development of a novel pocket sized quadrotor with foldable arms. The quadrotor can be packaged for transportation by folding its arms around the main frame. Before flight, the quadrotor's arms self-deploy in 0.3 seconds thanks to the torque generated by the propellers. The paper describes the design strategies used for developing lightweight, stiff and self-deployable foldable arms for miniature quadrotors. The arms are manufactured according to an origami technique with a foldable multi-layer material. A prototype of the quadrotor is presented as a proof of concept and performance of the system is assessed.

A novel variable stiffness actuator composed of a dielectric elastomer actuator (DEA) and a low-melting-point-alloy (LMPA) embedded silicone substrate is demonstrated. The device which we call variable stiffness dielectric elastomer actuator (VSDEA) enables functional soft robots with a simplified structure, where the DEA generates a bending actuation and the LMPA provides controllable stiffness between soft and rigid states by Joule heating. The entire structure of VSDEA is made of soft silicones with an elastic modulus of less than 1 MPa providing a high compliance when the LMPA is active. The device has the dimension of 40 mm length × 10 mm width × 1 mm thickness, with mass of ~1 g. We characterize VSDEA in terms of the actuation stroke angle, the blocked force, and the reaction force against a forced displacement. The results show the controllable actuation angle and the blocked force up to 23.7 ° and 2.4 mN in the soft state, and 0.6 ° and 2.1 mN in the rigid state. Compared to an actuator without the LMPA, VSDEA exhibits ~90× higher rigidity. We develop a VSDEA gripper where the mass of active parts is ~2 g, which is able to successfully hold an object mass of 11 g, exhibiting the high performance of the actuator.

Teams of fixed wing micro-aerial vehicles (MAVs) could provide a wide area coverage and relay data in wireless ad-hoc networks. In such applications fixed wing MAVs have to be able to regulate an inter-robot distance. Fixed wing MAVs have reduced maneuverability, that is, they cannot perform sharp turns or hover on the spot. This kinematic property presents the main challenge to design a formation algorithm that will regulate inter-MAV distance and cover the desired area. In this paper we present a distributed control strategy that is based on attraction and repulsion between MAVs and relies only on local information. We show in simulation and in field experiments with a team of fixed wing MAVs that using our strategy MAVs can cover an area by creating an equilateral triangular lattice and regulate communication link quality between neighboring MAVs.

The neural mechanisms determining the timing of even simple actions, such as when to walk or rest, are largely mysterious. One intriguing, but untested, hypothesis posits a role for ongoing activity fluctuations in neurons of central action selection circuits that drive animal behavior from moment to moment. To examine how fluctuating activity can contribute to action timing, we paired high-resolution measurements of freely walking Drosophila melanogaster with data-driven neural network modeling and dynamical systems analysis. We generated fluctuation-driven network models whose outputs-locomotor bouts-matched those measured from sensory-deprived Drosophila. From these models, we identified those that could also reproduce a second, unrelated dataset: the complex time-course of odor-evoked walking for genetically diverse Drosophila strains. Dynamical models that best reproduced both Drosophila basal and odor-evoked locomotor patterns exhibited specific characteristics. First, ongoing fluctuations were required. In a stochastic resonance-like manner, these fluctuations allowed neural activity to escape stable equilibria and to exceed a threshold for locomotion. Second, odor-induced shifts of equilibria in these models caused a depression in locomotor frequency following olfactory stimulation. Our models predict that activity fluctuations in action selection circuits cause behavioral output to more closely match sensory drive and may therefore enhance navigation in complex sensory environments. Together these data reveal how simple neural dynamics, when coupled with activity fluctuations, can give rise to complex patterns of animal behavior.

Science instructors from a wide range of disciplines agree that hands-on laboratory components of courses are pedagogically necessary (Freedman, 1997). However, certain shortcomings of current laboratory exercises have been pointed out by several authors (Mataric, 2004; Hofstein and Lunetta, 2004). The overarching theme of these analyses is that hands-on components of courses tend to be formulaic, closed-ended, and at times outdated. To address these issues, we envision a novel platform that is not only a didactic tool but is also an experimental testbed for users to play with different ideas in evolutionary robotics (Nolfi and Floreano, 2000), neural networks, physical simulation, 3D printing, mechanical assembly, and embedded processing. Here, we introduce RoboGen™: an open-source software and hardware platform designed for the joint evolution of robot morphologies and controllers a la Sims (1994); Lipson and Pollack (2000); Bongard and Pfeifer (2003). Robo- Gen has been designed specifically to allow evolved robots to be easily manufactured via widely available desktop 3D-printers, and the use of simple, open-source, low-cost, offthe- shelf electronic components. RoboGen features an evolution engine complete with a physics simulator, as well as utilities both for generating design files of body components for 3D printing, and for compiling neural-network controllers to run on an Arduino microcontroller board.

Recently, the notion that the brain is fundamentally a pre-diction machine has gained traction within the cognitive sci-ence community. Consequently, the ability to learn accu-rate predictors from experience is crucial to creating intel-ligent robots. However, in order to make accurate predic-tions it is necessary to find appropriate data representations from which to learn. Finding such data representations or features is a fundamental challenge for machine learning. Of-ten domain knowledge is employed to design useful features for specific problems, but learning representations in a do-main independent manner is highly desirable. While many approaches for automatic feature extraction exist, they are of-ten either computationally expensive or of marginal utility. On the other hand, methods such as Extreme Learning Ma-chines (ELMs) have recently gained popularity as efficient and accurate model learners by employing large collections of fixed, random features. The computational efficiency of these approaches becomes particularly relevant when learn-ing is done fully online, such as is the case for robots learn-ing via their interactions with the world. Selectionist meth-ods, which replace features offering low utility with random replacements, have been shown to produce efficient feature learning in one class of ELM. In this paper we demonstrate that a Darwinian neurodynamic approach of feature replica-tion can improve performance beyond selection alone, and may offer a path towards effective learning of predictive mod-els in robotic agents.

Localization is one of the key challenges that needs to be considered beforehand to design truly autonomous MAV teams. In this paper, we present a cooperative method to address the localization problem for a team of MAVs, where individuals obtain their position through perceiving a sound-emitting beacon MAV that is flying relative to a reference point in the environment. For this purpose, an on-board audio-based localization system is proposed that allows individuals to measure the relative bearing to the beacon robot and furthermore to localize themselves and the beacon robot simultaneously, without the need for a communication network. Our method is based on coherence testing among signals of a small on-board microphone array, to obtain the relative bearing measurements, and an estimator, to fuse these measurements with sensory information about the motion of the robot throughout time, to estimate robustly the MAV positions. The proposed method is evaluated both in simulation and in real world experiments.

With the ongoing rise of soft robots there emerges a need for new technologies that can cope with hyper-flexibility and stretchability. In this paper, we describe a new method for enabling controllable adhesion, namely electroadhesion, for use in soft robots. We present a method to manufacture stretchable electroadhesive pads and characterize their performance when stretching the pad more than double its original length. Our results suggest that the normal detachment force per area slightly decreases with the stretching, while the shear detachment force per area increases with the stretch ratio. These results imply that stretchable electroadhesive pads have higher adaptivity than non-stretchable pads because their mechanical stiffness and adhesive forces can be controlled through stretching.

This paper proposes an optical motion sensor aimed towards small robotic platforms. It incorporates a 20×20 pixel continuous-time CMOS silicon retina vision sensor with pixels that have local gain control and adapt to background lighting and a DSP microcontroller which computes the global optical flow from the sampled sensor output. The system allows the user to validate various motion algorithms suitable for the platform. Measurements are presented that show that the system can compute global 2D translational motion from complex natural scenes using the image interpolation algorithm at a sample rate of 1 kHz and for speeds up to ±1000 pixels/s using <5k instruction cycles per frame.

Robots capable of hover flight in constrained indoor environments have many applications, however their range is constrained by the high energetic cost of airborne locomotion. Perching allows flying robots to scan their environment without the need to remain aloft. This paper presents the design of a mechanism that allows indoor flying robots to attach to vertical surfaces. To date, solutions that enable flying robot with perching capabilities either require high precision control of the dynamics of the robot, or a mechanism robust to high energy impacts. In this article, we propose a perching mechanism comprising a compliant deployable pad and a passive self-alignment system, that does not require any active control during the attachment procedure. More specifically, a perching mechanism using fibre-based dry adhesives was implemented on a 300 g flying platform. An adhesive pad was first modeled and optimized in shape for maximum attachment force at the low pre-load forces inherent to hovering platforms. It was then mounted on a deployable mechanism that stays within the structure of the robot during flight and can be deployed when a perching manoeuvre is initiated. Finally, the perching mechanism is integrated onto a real flying robot and successful perching manoeuvres are demonstrated as a proof of concept.

Autonomous navigation in obstacle-dense indoor environments is very challenging for flying robots due to the high risk of collisions, which may lead to mechanical damage of the platform and eventual failure of the mission. While conventional approaches in autonomous navigation favor obstacle avoidance strategies, recent work showed that collision-robust flying robots could hit obstacles without breaking and even self-recover after a crash to the ground. This approach is particularly interesting for autonomous navigation in complex environments where collisions are unavoidable, or for reducing the sensing and control complexity involved in obstacle avoidance. This paper aims at showing that collision-robust platforms can go a step further and exploit contacts with the environment to achieve useful navigation tasks based on the sense of touch. This approach is typically useful when weight restrictions prevent the use of heavier sensors, or as a low-level detection mechanism supplementing other sensing modalities. In this paper, a solution based on force and inertial sensors used to detect obstacles all around the robot is presented. Eight miniature force sensors, weighting 0.9g each, are integrated in the structure of a collision-robust flying platform without affecting its robustness. A proof-of-concept experiment demonstrates the use of contact sensing for exploring autonomously a room in 3D, showing significant advantages compared to a previous strategy. To our knowledge this is the first fully autonomous flying robot using touch sensors as only exteroceptive sensors.

Most existing robots are designed to exploit only one single locomotion mode, such as rolling, walking, flying, swimming, or jumping, which limits their flexibility and adaptability to different environments where specific and different locomotion capabilities could be more effective. Here we introduce the concept and the design of a flying robot with Adaptive Morphology for Multi-Modal Locomotion. We present a prototype that can use its wings to walk on the ground and fly forward. The wings are used as whegs to move on rough terrains. This solution allows to minimize the structural mass of the robot by reusing the same structure (here the wings) for different modes of locomotion. Furthermore, the morphology of the robot is analysed and optimized for ground speed.

This paper addresses the problem of adequately protecting flying robots from damage resulting from collisions that may occur when exploring constrained and cluttered environments. A method for designing protective structures to meet the specific constraints of flying systems is presented and applied to the protection of a small coaxial hovering platform. Protective structures in the form of Euler springs in a tetrahedral configuration are designed and optimised to elastically absorb the energy of an impact while simultaneously minimizing the forces acting on the robot's stiff inner frame. These protective structures are integrated into a 282 g hovering platform and shown to consistently withstand dozens of collisions undamaged.

Optimizing collective behavior in multiagent systems requires algorithms to find not only appropriate individual behaviors but also a suitable composition of agents within a team. Over the last two decades, evolutionary methods have emerged as a promising approach for the design of agents and their compositions into teams. The choice of a crossover operator that facilitates the evolution of optimal team composition is recognized to be crucial, but so far, it has never been thoroughly quantified. Here, we highlight the limitations of two different crossover operators that exchange entire agents between teams: restricted agent swapping (RAS) that exchanges only corresponding agents between teams and free agent swapping (FAS) that allows an arbitrary exchange of agents. Our results show that RAS suffers from premature convergence, whereas FAS entails insufficient convergence. Consequently, in both cases, the exploration and exploitation aspects of the evolutionary algorithm are not well balanced resulting in the evolution of suboptimal team compositions. To overcome this problem, we propose combining the two methods. Our approach first applies FAS to explore the search space and then RAS to exploit it. This mixed approach is a much more efficient strategy for the evolution of team compositions compared to either strategy on its own. Our results suggest that such a mixed agent-swapping algorithm should always be preferred whenever the optimal composition of individuals in a multiagent system is unknown.

Because of their low weight, cost and energy consumption, optic-flow sensors attract growing interest in robotics for tasks such as self-motion estimation or depth measurement. Most applications require a large number of these sensors, which involves a fair amount of calibration work for each setup. In particular, the viewing direction of each sensor has to be measured for proper operation. This task is often cumbersome and prone to errors, and has to be carried out every time the setup is slightly modified. This paper proposes an algorithm for viewing direction calibration relying on rate gyroscope readings and a recursive weighted linear least square estimation of the rotation matrix elements. The method only requires the user to realize random rotational motions of its setup by hand. The algorithm provides hints about the current precision of the estimation and what motions should be performed to improve it. To assess the validity of the method, tests were performed on an experimental setup and the results compared to a precise manual calibration. The repeatability of the gyroscope-based calibration process reached ±1.7° per axis.

Swarms of flying robots are promising in many applications due to rapid terrain coverage. However, there are numerous challenges in realising autonomous operation in unknown indoor environments. A new autonomous flight methodology is presented using relative positioning sensors in reference to nearby static robots. The entirely decentralised approach relies solely on local sensing without requiring absolute positioning, environment maps, powerful computation or long-range communication. The swarm deploys as a robotic network facilitating navigation and goal directed flight. Initial validation tests with quadrotors demonstrated autonomous flight within a confined indoor environment, indicating that they could traverse a large network of static robots across expansive environments.

In search and rescue missions, Micro Air Vehicles (MAV's) can assist rescuers to faster locate victims inside a large search area and to coordinate their efforts. Acoustic signals play an important role in outdoor rescue operations. Emergency whistles, as found on most aircraft life vests, are commonly carried by people engaging in outdoor activities, and are also used by rescue teams, as they allow to signal reliably over long distances and far beyond visibility. For a MAV involved in such missions, the ability to locate the source of a distress sound signal, such as an emergency whistle blown by a person in need of help, is therefore significantly important and would allow the localization of victims and rescuers during night time, through foliage and in adverse conditions such as dust, fog and smoke. In this paper we present a sound source localization system for a MAV to locate narrowband sound sources on the ground, such as the sound of a whistle or personal alarm siren. We propose a method based on a particle filter to combine information from the cross correlation between signals of four spatially separated microphones mounted on the MAV, the dynamics of the aerial platform, and the doppler shift in frequency of the sound due to the motion of the MAV. Furthermore, we evaluate our proposed method in a real world experiment where a flying micro air vehicle is used to locate and track the position of a narrowband sound source on the ground.

Typical deflection sensors like strain gauges or devices based on optical fibers require physical contact with the deflected substrate during the measurement process. Such contact, however, impacts on the softness of the substrate and may falsify the measurements. In order to overcome this drawback, a novel method of contactless deflection sensing was proposed in a recent work. It was verified that the deflection angle between two planes can be extracted using only a photosensor and a light source bearing a bell-shape angular emission profile. Yet, the range of operation was limited to concave shapes. In this paper, we introduce an alternative configuration of this light-based deflection sensing method to extend its functionality to convex surfaces. Here, a spheroidal mirror bearing a customized profile is introduced above the light source. This mirror redirects part of the emitted light towards the photosensor occluded by the bending surface during convex deflections.We make use of a ray tracing simulation method to design the mirror profiles, which are accurately reproduced in the manufactured prototypes by tuning the fabrication variables of the manufacturing process. Using a shape-sensing prototype, it is verified that the use of the mirror extends the range of detectable deflections by 55° to convex bendings, yielding a deviation of only 8.3% from simulated results. Our deflection sensing solution is a promising method to be used as a shape sensor in numerous applications, such as soft robotics platforms or prosthetic devices.

Flying robots have unique advantages in the exploration of cluttered environments such as caves or collapsed buildings. Current systems, however, have difficulty in dealing with the large amount of obstacles inherent to such environments. Collisions with obstacles generally result in crashes from which the platform can no longer recover. This paper presents a method to design active uprighting mechanisms for protected rotorcraft-type flying robots that allow them to become upright and subsequently take off again after an otherwise mission-ending collision. This method is demonstrated on a tailsitter flying robot, which is capable of consistently uprighting after falling on its side using a spring-based “leg” and returning to the air to continue its mission.

In the emerging field of soft robotics, there is an interest in developing new kinds of sensors whose characteristics do not affect the intrinsic compliance of soft robot components. Additionally, non-invasive shape and deflection sensors may provoke improved solutions to assist in the control of mechanical parts in these robots. Herein, we introduce a novel method for deflection sensing where an LED element and a photodiode are placed on to two substrates connected physically or virtually at a deflection point. The deflection angle between the two planes can be extracted from the LED light intensity detected at the photodiode due to the bell-shaped angular intensity profile of the emitted light. The main advantage of this system is that the components are not in physical contact with the deflection region as in the case of strain gauges and similar sensing methods. The sensor is characterized in a range of deflections of 105-180 degrees, showing a near 1 degree resolution. The experimental data are compared to simulations, modeled by ray tracing. The light intensity vs. deflection angle measurements in our setup display a maximum difference of 9% and an average difference of approximately 5% with respect to the model. Finally, a shape monitoring system has been developed using the proposed concept for a flexible PCB. The system is composed of 12 deflection sensors that operate at frame rate of 33 Hz. This device could be applied to monitor the body shape of a soft robot.

The success of swarm behaviors often depends on the range at which robots can communicate and the speed at which they change their behavior. Challenges arise when the communication range is too small with respect to the dynamics of the robot, preventing interactions from lasting long enough to achieve coherent swarming. To alleviate this dependency, most swarm experiments done in laboratory environments rely on communication hardware that is relatively long range and wheeled robotic platforms that have omnidirectional motion. Instead, we focus on deploying a swarm of small fixed-wing flying robots. Such platforms have limited payload, resulting in the use of short-range communication hardware. Furthermore, they are required to maintain forward motion to avoid stalling and typically adopt low turn rates because of physical or energy constraints. The tradeoff between communication range and flight dynamics is exhaustively studied in simulation in the scope of Reynolds flocking and demonstrated with up to 10 robots in outdoor experiments.

MOTIVATION: Over the last decade, numerous methods have been developed for inference of regulatory networks from gene expression data. However, accurate and systematic evaluation of these methods is hampered by the difficulty of constructing adequate benchmarks and the lack of tools for a differentiated analysis of network predictions on such benchmarks. RESULTS: Here, we describe a novel and comprehensive method for in silico benchmark generation and performance profiling of network inference methods available to the community as an open-source software called GeneNetWeaver (GNW). In addition to the generation of detailed dynamical models of gene regulatory networks to be used as benchmarks, GNW provides a network motif analysis that reveals systematic prediction errors, thereby indicating potential ways of improving inference methods. The accuracy of network inference methods is evaluated using standard metrics such as precision-recall and receiver operating characteristic curves. We show how GNW can be used to assess the performance and identify the strengths and weaknesses of six inference methods. Furthermore, we used GNW to provide the international Dialogue for Reverse Engineering Assessments and Methods (DREAM) competition with three network inference challenges (DREAM3, DREAM4 and DREAM5). AVAILABILITY: GNW is available at http://gnw.sourceforge.net along with its Java source code, user manual and supporting data. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. CONTACT: [email protected].

Aerial robots are often required to remain within the communication range of a base station on the ground to exchange commands, sensor data or as a safety mechanism. For this purpose, we propose a minimal control strategy for steering flying robots using only communication hardware (e.g. WiFi module or radio modem) instead of GPS or cameras. To avoid being dependent on the specifics of the communication hardware or its driver, we propose to measure the number of messages the robot receives from the base as a control input. Leashing is then performed by having the robot react to low message rates by moving towards the base in order to improve the communication. Results show both in theory and reality that this strategy can leash the robot to the base in scenarios with limited wind or base mobility.

This paper presents a new paradigm in the design of indoor flying robots that replaces collision avoidance with collision robustness. Indoor flying robots must operate within constrained and cluttered environments where even nature's most sophisticated flyers such as insects cannot avoid all obstacles and should thus be able to withstand collisions and recover from them autonomously. A prototype platform specifically designed to withstand collisions and recover without human intervention is presented. Its dimensions are optimized to fulfill the varying constraints of aerodynamics, robustness and self-recovery, and new construction techniques focusing on shock absorption are presented. Finally, the platform is tested both in-flight and during collisions to characterize its collision robustness and self-recovery capability.

The ability to fly at low altitude while actively avoiding collisions with the terrain and other objects is a great challenge for small unmanned aircraft. This paper builds on top of a control strategy called optiPilot whereby a series of optic-flow detectors pointed at divergent viewing directions around the aircraft main axis are linearly combined into roll and pitch commands using two sets of weights. This control strategy already proved successful at controlling flight and avoiding collisions in reactive navigation experiments. This paper shows how optiPilot can be coupled with a GPS in order to provide goal-directed, nap-of-the-earth flight control in presence of static obstacles. Two fully autonomous flights of 25 minutes each are described where a 400-gram unmanned aircraft is flying at approx. 9 m above the terrain on a circular path including two copses of trees requiring efficient collision avoidance actions.

It is generally challenging to design decentralized controllers for swarms of robots because there is often no obvious relation between the individual robot behaviors and the final behavior of the swarm. As a solution, we use artificial evolution to automatically discover neural controllers for swarming robots. Artificial evolution has the potential to find simple and efficient strategies which might otherwise have been overlooked by a human designer. However, evolved controllers are often unadapted when used in scenarios that differ even slightly from those encountered during the evolutionary process. By reverse-engineering evolved controllers we aim towards hand-designed controllers which capture the simplicity and efficiency of evolved neural controllers while being easy to optimize for a variety of scenarios.

In nature, many animals are able to jump, upright themselves after landing and jump again. This allows them to move in unstructured and rough terrain. As a further development of our previously presented 7 g jumping robot, we consider various mechanisms enabling it to recover and upright after landing and jump again. After a weighted evaluation of these different solutions, we present a spherical system with a mass of 9.8 g and a diameter of 12 cm that is able to jump, upright itself after landing and jump again. In order to do so autonomously, it has a control unit and sensors to detect its orientation and spring charging state. With its current configuration it can overcome obstacles of 76 cm at a take-off angle of 75°.

Scanning laser range sensors (ladars) are frequently used in mobile robotics applications because their ability to accurately measure the environment in 3D makes them well-suited for perception tasks like terrain modeling and obstacle detection. The choice of ladar sensor and the manner in which it is configured and integrated into a robot platform is usually determined subjectively based on the experience of the project team members. This paper develops a method for evaluating ladar sensors and sensor configurations that objectively measures the quality of a sensor/configuration choice in terms of density and uniformity of measurements within a region of interest. The method is applicable to static sensors and environments as well as scenarios with moving objects and mobile sensors. It can be used to compare different sensors, to evaluate specific sensor configurations and search for the optimal one, and to aid in designing new ladar sensors tailored to specific applications. We find that popular ladar configurations are often not the best configuration choice, and that alternative configurations not commonly used would offer better data density and uniformity.

Most autopilots of existing miniature unmanned air vehicles (MUAVs) rely on control architectures that typically use a large number of sensors (gyros, accelerometers, magnetometers, GPS) and a computationally demanding estimation of flight states. As a consequence, they tend to be complex, require a significant amount of processing power and are usually expensive. Many research projects that aim at experiments with one, or even several, MUAVs would benefit from a simpler, potentially smaller, lighter and less expensive autopilot for their flying platforms. In this paper, we present a minimalist control strategy for fixed-wing MUAVs that provides the three basic functionalities of airspeed, altitude and heading turnrate control while only using two pressure sensors and a single-axis rate gyro. To achieve this, we use reactive control loops, which rely on direct feedback from the sensors instead of full state information. In order to characterize the control strategy, it was implemented on a custom-made autopilot. With data recorded during flight experiments, we carried out a statistical analysis of step responses to altitude and turnrate commands as well as responses to artificial perturbations.

In the growing field of collective robotics, spatial co-ordination between robots is often critical and usually achieved via local relative positioning sensors. We believe that range and bearing sensing, based on infrared technology, has the potential to fulfil the strict requirements of real-world collective robots. These requirements include: small size, light weight, large range, high refresh rate, immunity against tilting and misalignment, immunity against ambient light changes, and good range and bearing accuracy. Currently, there are no range and bearing systems that have been designed to cope with such strict requirements. This paper presents a custom range and bearing system, based on a novel cascaded filtering technology, complemented by hybrid infrared/Radio Frequency (RF) communication, which has been designed specifically to meet all these expectations. The system has been characterised and tested, proving its viability.

In cooperative multiagent systems, agents interact to solve tasks. Global dynamics of multiagent teams result from local agent interactions, and are complex and difficult to predict. Evolutionary computation has proven a promising approach to the design of such teams. The majority of current studies use teams composed of agents with identical control rules (ldquogenetically homogeneous teamsrdquo) and select behavior at the team level (ldquoteam-level selectionrdquo). Here we extend current approaches to include four combinations of genetic team composition and level of selection. We compare the performance of genetically homogeneous teams evolved with individual-level selection, genetically homogeneous teams evolved with team-level selection, genetically heterogeneous teams evolved with individual-level selection, and genetically heterogeneous teams evolved with team-level selection. We use a simulated foraging task to show that the optimal combination depends on the amount of cooperation required by the task. Accordingly, we distinguish between three types of cooperative tasks and suggest guidelines for the optimal choice of genetic team composition and level of selection.

Jumping can be a very efficient mode of locomotion for small robots to overcome large obstacles and travel in natural, rough terrain. In this paper we present the development and characterization of a novel 5 cm, 7g jumping robot. It can jump obstacles more than 27 times its own size and outperforms existing jumping robots by one order of magnitude with respect to jump height per weight and jump height per size. It employs elastic elements in a four bar linkage leg system to allow for very powerful jumps and adjustment of the jumping force, take-off angle and force profile during the acceleration phase.

Flying has an advantage when compared to ground based locomotion, as it simplifies the task of overcoming obstacles and allows for rapid coverage of an area while also providing a birds-eye-view of the environment. One of the key challenges that has prevented engineers from coming up with convincing aerial solutions for indoor exploration is the energetic cost of flying. This paper presents a way of mitigating the energy problem regarding aerial exploration within indoor environments. This is achieved by means of a model to estimate the endurance of a hover-capable flying robot and by using ceiling attachment as a means of preserving energy while maintaining a birds-eye-view. The proposed model for endurance estimation has been extensively tested using a custom-developed quadrotor and autonomous ceiling attachment system.

Environments with varying reward contingencies constitute a challenge to many living creatures. In such conditions, animals capable of adaptation and learning derive an advantage. Recent studies suggest that neuromodulatory dynamics are a key factor in regulating learning and adaptivity when reward conditions are subject to variability. In biological neural networks, specific circuits generate modulatory signals, particularly in situations that involve learning cues such as a reward or novel stimuli. Modulatory signals are then broadcast and applied onto target synapses to activate or regulate synaptic plasticity. Artificial neural models that include modulatory dynamics could prove their potential in uncertain environments when online learning is required. However, a topology that synthesises and delivers modulatory signals to target synapses must be devised. So far, only handcrafted architectures of such kind have been attempted. Here we show that modulatory topologies can be designed autonomously by artificial evolution and achieve superior learning capabilities than traditional fixed-weight or Hebbian networks. In our experiments, we show that simulated bees autonomously evolved a modulatory network to maximise the reward in a reinforcement learning-like environment.

In this paper we describe a new class of representations for real-valued parameters called Center of Mass Encoding (CoME). CoME is based on variable length strings, it is self-adaptive, and it permits the choice of the degree of redundancy of the genotype-to-phenotype map and the choice of the distribution of the redundancy over the space of phenotypes. We first describe CoME and then proceed to test its performance and compare it with other representations and with a state-of-the-art evolution strategy. We show that CoME performs well on a large set of test functions. Furthermore, we show how CoME adapts the granularity of its discretization on functions defined over nonuniformly scaled domains.

Fully autonomous control of ultra-light indoor airplanes has not yet been achieved because of the strong limitations on the kind of sensors that can be embedded making it difficult to obtain good estimations of altitude. We propose to revisit altitude control by considering it as an obstacle avoidance problem and introduce a novel control scheme where the ground and ceiling is avoided based on translatory optic flow, in a way similar to existing vision-based wall avoidance strategies. We show that this strategy is successful at controlling a simulated microflyer without any explicit altitude estimation and using only simple sensors and processing that have already been embedded in an existing 10-gram microflyer. This result is thus a significant step toward autonomous control of indoor flying robots.

Unpowered flight can be used in microrobotics to overcome ground obstacles and to increase the traveling distance per energy unit. In order to explore the potential of goal-directed gliding in the domain of miniature robotics, we developed a 22cm microglider weighing a mere 1.5g and flying at around 1.5m/s. It is equipped with sensors and electronics to achieve phototaxis, which can be seen as a minimal level of control autonomy. A novel 0.2g Shape Memory Alloy (SMA) actuator for steering control has been specifically designed and integrated to keep the overall weight as low as possible. In order to characterize autonomous operation of this robot, we developed an experimental setup consisting of a launching device and a light source positioned 1m below and 4m away with varying angles with respect to the launching direction. Statistical analysis of 36 autonomous flights demonstrate its flight and phototaxis efficiency.

This paper describes a new kind of genetic representation called analog genetic encoding (AGE). The representation is aimed at the evolutionary synthesis and reverse engineering of circuits and networks such as analog electronic circuits, neural networks, and genetic regulatory networks. AGE permits the simultaneous evolution of the topology and sizing of the networks. The establishment of the links between the devices that form the network is based on an implicit definition of the interaction between different parts of the genome. This reduces the amount of information that must be carried by the genome, relatively to a direct encoding of the links. The application of AGE is illustrated with examples of analog electronic circuit and neural network synthesis. The performance of the representation and the quality of the results obtained with AGE are compared with those produced by genetic programming.

Autonomous control of ultra-light indoor microflyers is a difficult and largely unsolved task because of the strong limitations on the kind of sensors that can be embedded. We propose a new approach for altitude control of a 10-gram microflyer, where altitude as well as pitch angle are estimated using a set of visual, airspeed and gyroscopic sensors that weight about 1 (g) in total. This approach does not rely on an explicit estimation of optic flow, but rather takes as input the raw images as provided by the vision sensor. We show that altitude and pitch angle of a simulated agent can be successfully estimated. This result is thus a first step toward autonomous altitude control of indoor flying robots

We aim at developing ultralight autonomous microflyers capable of navigating within houses or small built environments. Our latest prototype is a fixed-wing aircraft weighing a mere 10 g, flying below 2 m/s and carrying the necessary electronics for airspeed regulation and obstacle avoidance. This microflyer is equipped with two tiny camera modules, two rate gyroscopes, an anemometer, a small microcontroller, and a Bluetooth radio module. In-flight tests are carried out in a new experimentation room specifically designed for easy changing of surrounding textures.

We aim at developing ultralight autonomous microflyers capable of navigating within houses or small built environments. Our latest prototype is a fixed-wing aircraft weighing a mere 10 g, flying around 1.5 m/s and carrying the necessary electronics for airspeed regulation and collision avoidance. This microflyer is equipped with two tiny camera modules, two rate gyroscopes, an anemometer, a small microcontroller, and a Bluetooth radio module. In-flight tests are carried out in a new experimentation room specifically designed for easy changing of surrounding textures

We describe evolution of spiking neural architectures to control navigation of autonomous mobile robots. Experimental results with simple fitness functions indicate that evolution can rapidly generate spiking circuits capable of navigating in textured environments with simple genetic representations that encode only the presence or absence of synaptic connections. Building on those results, we then describe a low-level implementation of evolutionary spiking circuits in tiny microcontrollers that capitalizes on compact genetic encoding and digital aspects of spiking neurons. The implementation is validated on a sugar-cube robot capable of developing functional spiking circuits for collision-free navigation. © 2006 Wiley Periodicals, Inc. Int J Int Syst 21: 1005–1024, 2006.

We aim at developing autonomous microflyers capable of navigating within houses or small indoor environments using vision as the principal source of information. Due to severe weight and energy constraints, inspiration is taken from the fly for the selection of sensors, for signal processing, and for the control strategy. The current 30-g prototype is capable of autonomous steering in a 16/spl times/16 m textured environment. This paper describes models and algorithms which allow for efficient course stabilization and collision avoidance using optic flow and inertial information.

We aim at developing autonomous micro-flyers capable of navigating within houses or small built environments. The severe weight and energy constraints of indoor flying platforms led us to take inspiration from flying insects for the selection of sensors, signal processing, and behaviors. This paper presents the control strategies enabling obstacle avoidance and altitude control using only optic flow and gyroscopic information. For experimental convenience, the control strategies are first implemented and tested separately on a small wheeled robot featuring the same hardware as the targeted aircraft. The obstacle avoidance system is then transferred to a 30-gram aircraft, which demonstrates autonomous steering within a square textured arena.

We explore the role of active body movement in the developmental process of the visual system. Receptive fields of an evolved mobile robot are developed during active or passive movement with the generalized Hebbian algorithm by Sanger, T.D., (1989). In accordance to experimental observations of kitten, we show that the receptive fields and behavior of the robot developed under active condition significantly differ from those developed under passive condition. A possible explanation of this difference is derived by correlating receptive field formation and behavioral performance in the two conditions.

We give an overview of the EPFL indoor flying project, whose goal is to evolve neural controllers for autonomous, adaptive, indoor micro-flyers. Indoor flight is still a challenge because it requires miniaturization, energy efficiency, and control of nonlinear flight dynamics. This ongoing project consists of developing a flying, vision-based micro-robot, a bio-inspired controller composed of adaptive spiking neurons directly mapped into digital microcontrollers, and a method to evolve such a neural controller without human intervention. This article describes the motivation and methodology used to reach our goal as well as the results of a number of preliminary experiments on vision-based wheeled and flying robots.

In this paper, we describe the artificial evolution of adaptive neural controllers for an outdoor mobile robot equipped with a mobile camera. The robot can dynamically select the gazing direction by moving the body and/or the camera. The neural control system, which maps visual information to motor commands, is evolved online by means of a genetic algorithm, but the synaptic connections (receptive fields) from visual photoreceptors to internal neurons can also be modified by Hebbian plasticity while the robot moves in the environment. We show that robots evolved in physics-based simulations with Hebbian visual plasticity display more robust adaptive behavior when transferred to real outdoor environments as compared to robots evolved without visual plasticity. We also show that the formation of visual receptive fields is significantly and consistently affected by active vision as compared to the formation of receptive fields with grid sample images in the environment of the robot. Finally, we show that the interplay between active vision and receptive field formation amounts to the selection and exploitation of a small and constant subset of visual features available to the robot.

In this paper we address the problem of defining a measure of diversity for a population of individuals whose genome can be subjected to major reorganizations during the evolutionary process. To this end, we introduce a measure of diversity for populations of strings of variable length defined on a finite alphabet, and from this measure we derive a semi-metric distance between pairs of strings. The definitions are based on counting the number of substrings of the strings, considered first separately and then collectively. This approach is related to the concept of linguistic complexity, whose definition we generalize from single strings to populations. Using the substring count approach we also define a new kind of Tanimoto distance between strings. We show how to extend the approach to representations that are not based on strings and, in particular, to the tree-based representations used in the field of genetic programming. We describe how suffix trees can allow these measures and distances to be implemented with a computational cost that is linear in both space and time relative to the length of the strings and the size of the population. The definitions were devised to assess the diversity of populations having genomes of variable length and variable structure during evolutionary computation runs, but applications in quantitative genomics, proteomics, and pattern recognition can be also envisaged.

This paper presents a new robotic concept, called SWARM-BOT, based on a swarm of autonomous mobile robots with self-assembling capabilities. SWARM-BOT takes advantage from collective and distributed approaches to ensure robustness to failures and to hard environment conditions in tasks such as navigation, search and transportation in rough terrain. One SWARM-BOT is composed of a number of simpler robots, called s-bots, physically interconnected. The SWARM-BOT is provided with self-assembling and self-reconfiguring capabilities whereby s-bots can connect and disconnect forming large flexible structures. This paper introduces the SWARM-BOT concept and describes its implementation from a mechatronic perspective.

We describe an incremental approach towards the development of autonomous indoor flyers that use only vision to navigate in textured environments. In order to cope with the severe weight and energy constraints of such systems, we use spiking neural controllers that can be implemented in tiny micro-controllers and map visual information into motor commands. The network morphology is evolved by means of an evolutionary process on the physical robots. This methodology is tested in three robots of increasing complexity, from a wheeled robot to a dirigible to a winged robot. The paper describes the approach, the robots, their degrees of complexity, and summarizes results. In addition, three compatible electronic boards and a choice of vision sensors suitable for these robots are described in more details. These boards allow a comparative and gradual development of spiking neural controllers for flying robots.

We describe an evolutionary vision system capable of autonomously scanning through an image while zooming in and out and changing filtering strategy in order to perform shape discrimination. The system consists of a small artificial retina controlled by an evolutionary recurrent neural network without hidden units. We show that such a simple active-vision system can successfully recognize different shapes independently of their position and size by dynamically exploring relevant parts of the image. We also show that a standard feedforward neural network trained with the backpropagation algorithm cannot perform the task, not even with hidden units added to the architecture. Given its compactness, computational requirements, and versatility, this evolutionary active vision system is a suitable solution for small-size and embedded vision systems with stringent energetic and computational requirements, such as micro-robotic systems. In addition, this approach provides a framework for studying emergent active-vision behavior in autonomous systems.

This paper is concerned with adaptation capabilities of evolved neural controllers. We propose to evolve mechanisms for parameter self-organization instead of evolving the parameters themselves. The method consists of encoding a set of local adaptation rules that synapses follow while the robot freely moves in the environment. In the experiments presented here, the performance of the robot is measured in environments that are different in significant ways from those used during evolution. The results show that evolutionary adaptive controllers solve the task much faster and better than evolutionary standard fixed-weight controllers, that the method scales up well to large architectures, and that evolutionary adaptive controllers can adapt to environmental changes that involve new sensory characteristics (including transfer from simulation to reality and across different robotic platforms) and new spatial relationships.

This paper presents an adaptive method that allows mobile robots to learn cognitive maps of indoor environments incrementally and online. Our approach models the environment. By means of a variable-resolution partitioning that discretizes the world in perceptually homogeneous regions. The resulting model incorporates both a compact geometrical representation of the environment and a topological map of the spatial relationships between its obstacle-free areas. The efficiency of the learning process is based on the use of local memory-based techniques for partitioning and of active learning techniques for selecting the most appropriate region to be explored next. In addition, a feedforward neural network is used to interpret sensor readings. We present experimental results obtained with two different mobile robots, the Nomad 200 and Khepera. The current implementation of the method relies on the assumption that obstacles are parallel or perpendicular to each other. This results in variable-resolution partitioning consisting of simple rectangular partitions and reduces the complexity of treating the underlying geometrical properties.

Coevolution (i.e., the evolution of two or more competing populations with coupled fitness) has several features that may potentially enhance the power of adaptation of artificial evolution. In particular, as discussed by Dawkins and Krebs [3], competing populations may reciprocally drive one another to increasing levels of complexity by producing an evolutionary "arms race." In this article we will investigate the role of coevolution in the context of evolutionary robotics. In particular, we will try to understand in what conditions coevolution can lead to "arms races." Moreover, we will show that in some cases artificial coevolution has a higher adaptive power than simple evolution. Finally, by analyzing the dynamics of coevolved populations, we will show that in some circumstances well-adapted individuals would be better advised to adopt simple but easily modifiable strategies suited for the current competitor strategies rather than incorporate complex and general strategies that may be effective against a wide range of opposing counter-strategies.

We propose a modular architecture for autonomous robots which allows for the implementation of basic behavioral modules by both programming and training, and accommodates for an evolutionary development of the interconnections among modules. This architecture can implement highly complex controllers and allows for incremental shaping of the robot behavior. Our proposal is exemplified and evaluated experimentally through a number of mobile robotic tasks involving exploration, battery recharging and object manipulation.

In this paper we describe the evolution of a discrete-time recurrent neural network to control a real mobile robot. In all our experiments the evolutionary procedure is carried out entirely on the physical robot without human intervention. We show that the autonomous development of a set of behaviors for locating a battery charger and periodically returning to it can be achieved by lifting constraints in the design of the robot/environment interactions that were employed in a preliminary experiment. The emergent homing behavior is based on the autonomous development of an internal neural topographic map (which is not pre-designed) that allows the robot to choose the appropriate trajectory as function of location and remaining energy.