Committing to the wrong artificial delegate in a collective-risk dilemma is better than directly committing mistakes.

While autonomous artificial agents are assumed to perfectly execute the strategies they are programmed with, humans who design them may make mistakes. These mistakes may lead to a misalignment between the humans' intended goals and their agents' observed behavior, a problem of value alignment. Such an alignment problem may have particularly strong consequences when these autonomous systems are used in social contexts that involve some form of collective risk. By means of an evolutionary game theoretical model, we investigate whether errors in the configuration of artificial agents change the outcome of a collective-risk dilemma, in comparison to a scenario with no delegation. Delegation is here distinguished from no-delegation simply by the moment at which a mistake occurs: either when programming/choosing the agent (in case of delegation) or when executing the actions at each round of the game (in case of no-delegation). We find that, while errors decrease success rate, it is better to delegate and commit to a somewhat flawed strategy, perfectly executed by an autonomous agent, than to commit execution errors directly. Our model also shows that in the long-term, delegation strategies should be favored over no-delegation, if given the choice.

The art of compensation: How hybrid teams solve collective-risk dilemmas.

It is widely known how the human ability to cooperate has influenced the thriving of our species. However, as we move towards a hybrid human-machine future, it is still unclear how the introduction of artificial agents in our social interactions affect this cooperative capacity. In a one-shot collective risk dilemma, where enough members of a group must cooperate in order to avoid a collective disaster, we study the evolutionary dynamics of cooperation in a hybrid population. In our model, we consider a hybrid population composed of both adaptive and fixed behavior agents. The latter serve as proxies for the machine-like behavior of artificially intelligent agents who implement stochastic strategies previously learned offline. We observe that the adaptive individuals adjust their behavior in function of the presence of artificial agents in their groups to compensate their cooperative (or lack of thereof) efforts. We also find that risk plays a determinant role when assessing whether or not we should form hybrid teams to tackle a collective risk dilemma. When the risk of collective disaster is high, cooperation in the adaptive population falls dramatically in the presence of cooperative artificial agents. A story of compensation, rather than cooperation, where adaptive agents have to secure group success when the artificial agents are not cooperative enough, but will rather not cooperate if the others do so. On the contrary, when risk of collective disaster is low, success is highly improved while cooperation levels within the adaptive population remain the same. Artificial agents can improve the collective success of hybrid teams. However, their application requires a true risk assessment of the situation in order to actually benefit the adaptive population (i.e. the humans) in the long-term.

The duplication of genomes and genetic networks and its potential for evolutionary adaptation and survival during environmental turmoil.

The importance of whole-genome duplication (WGD) for evolution is controversial. Whereas some view WGD mainly as detrimental and an evolutionary dead end, there is growing evidence that polyploidization can help overcome environmental change, stressful conditions, or periods of extinction. However, despite much research, the mechanistic underpinnings of why and how polyploids might be able to outcompete or outlive nonpolyploids at times of environmental upheaval remain elusive, especially for autopolyploids, in which heterosis effects are limited. On the longer term, WGD might increase both mutational and environmental robustness due to redundancy and increased genetic variation, but on the short-or even immediate-term, selective advantages of WGDs are harder to explain. Here, by duplicating artificially generated Gene Regulatory Networks (GRNs), we show that duplicated GRNs-and thus duplicated genomes-show higher signal output variation than nonduplicated GRNs. This increased variation leads to niche expansion and can provide polyploid populations with substantial advantages to survive environmental turmoil. In contrast, under stable environments, GRNs might be maladaptive to changes, a phenomenon that is exacerbated in duplicated GRNs. We believe that these results provide insights into how genome duplication and (auto)polyploidy might help organisms to adapt quickly to novel conditions and to survive ecological uproar or even cataclysmic events.

Steering herds away from dangers in dynamic environments.

Shepherding, the task of guiding a herd of autonomous individuals in a desired direction, is an essential skill to herd animals, enable crowd control and rescue from danger. Equipping robots with the capability of shepherding would allow performing such tasks with increased efficiency and reduced labour costs. So far, only single-robot or centralized multi-robot solutions have been proposed. The former is unable to observe dangers at any place surrounding the herd, and the latter does not generalize to unconstrained environments. Therefore, we propose a decentralized control algorithm for multi-robot shepherding, where the robots maintain a caging pattern around the herd to detect potential nearby dangers. When danger is detected, part of the robot swarm positions itself in order to repel the herd towards a safer region. We study the performance of our algorithm for different collective motion models of the herd. We task the robots to shepherd a herd to safety in two dynamic scenarios: (i) to avoid dangerous patches appearing over time and (ii) to remain inside a safe circular enclosure. Simulations show that the robots are always successful in shepherding when the herd remains cohesive, and enough robots are deployed.

Iterative Online 3D Reconstruction from RGB Images.

3D reconstruction is the computer vision task of reconstructing the 3D shape of an object from multiple 2D images. Most existing algorithms for this task are designed for offline settings, producing a single reconstruction from a batch of images taken from diverse viewpoints. Alongside reconstruction accuracy, additional considerations arise when 3D reconstructions are used in real-time processing pipelines for applications such as robot navigation or manipulation. In these cases, an accurate 3D reconstruction is already required while the data gathering is still in progress. In this paper, we demonstrate how existing batch-based reconstruction algorithms lead to suboptimal reconstruction quality when used for online, iterative 3D reconstruction and propose appropriate modifications to the existing Pix2Vox++ architecture. When additional viewpoints become available at a high rate, e.g., from a camera mounted on a drone, selecting the most informative viewpoints is important in order to mitigate long term memory loss and to reduce the computational footprint. We present qualitative and quantitative results on the optimal selection of viewpoints and show that state-of-the-art reconstruction quality is already obtained with elementary selection algorithms.

Foraging behaviour and patch size distribution jointly determine population dynamics in fragmented landscapes.

Increased fragmentation caused by habitat loss represents a major threat to the persistence of animal populations. How fragmentation affects populations depends on the rate at which individuals move between spatially separated patches. Whereas negative effects of habitat loss on biodiversity are well known, the effects of fragmentation per se on population dynamics and ecosystem stability remain less well understood. Here, we use a spatially explicit predator-prey model to investigate how the interplay between fragmentation and optimal foraging behaviour affects predator-prey interactions and, subsequently, ecosystem stability. We study systems wherein prey occupies isolated patches and are consumed by predators that disperse following Lévy random walks. Our results show that the Lévy exponent and the degree of fragmentation jointly determine coexistence probabilities. In highly fragmented landscapes, Brownian and ballistic predators go extinct and only scale-free predators can coexist with prey. Furthermore, our results confirm that predation causes irreversible habitat loss in fragmented landscapes owing to overexploitation of smaller patches of prey. Moreover, we show that predator dispersal can reduce, but not prevent or minimize, the amount of lost habitat. Our results suggest that integrating optimal foraging theory into population and landscape ecology is crucial to assessing the impact of fragmentation on biodiversity and ecosystem stability.

Data-Efficient Sensor Upgrade Path Using Knowledge Distillation.

Deep neural networks have achieved state-of-the-art performance in image classification. Due to this success, deep learning is now also being applied to other data modalities such as multispectral images, lidar and radar data. However, successfully training a deep neural network requires a large reddataset. Therefore, transitioning to a new sensor modality (e.g., from regular camera images to multispectral camera images) might result in a drop in performance, due to the limited availability of data in the new modality. This might hinder the adoption rate and time to market for new sensor technologies. In this paper, we present an approach to leverage the knowledge of a teacher network, that was trained using the original data modality, to improve the performance of a student network on a new data modality: a technique known in literature as knowledge distillation. By applying knowledge distillation to the problem of sensor transition, we can greatly speed up this process. We validate this approach using a multimodal version of the MNIST dataset. Especially when little data is available in the new modality (i.e., 10 images), training with additional teacher supervision results in increased performance, with the student network scoring a test set accuracy of 0.77, compared to an accuracy of 0.37 for the baseline. We also explore two extensions to the default method of knowledge distillation, which we evaluate on a multimodal version of the CIFAR-10 dataset: an annealing scheme for the hyperparameter α and selective knowledge distillation. Of these two, the first yields the best results. Choosing the optimal annealing scheme results in an increase in test set accuracy of 6%. Finally, we apply our method to the real-world use case of skin lesion classification.

An Artificial Intelligence-Based Collaboration Approach in Industrial IoT Manufacturing: Key Concepts, Architectural Extensions and Potential Applications.

The digitization of manufacturing industry has led to leaner and more efficient production, under the Industry 4.0 concept. Nowadays, datasets collected from shop floor assets and information technology (IT) systems are used in data-driven analytics efforts to support more informed business intelligence decisions. However, these results are currently only used in isolated and dispersed parts of the production process. At the same time, full integration of artificial intelligence (AI) in all parts of manufacturing systems is currently lacking. In this context, the goal of this manuscript is to present a more holistic integration of AI by promoting collaboration. To this end, collaboration is understood as a multi-dimensional conceptual term that covers all important enablers for AI adoption in manufacturing contexts and is promoted in terms of business intelligence optimization, human-in-the-loop and secure federation across manufacturing sites. To address these challenges, the proposed architectural approach builds on three technical pillars: (1) components that extend the functionality of the existing layers in the Reference Architectural Model for Industry 4.0; (2) definition of new layers for collaboration by means of human-in-the-loop and federation; (3) security concerns with AI-powered mechanisms. In addition, system implementation aspects are discussed and potential applications in industrial environments, as well as business impacts, are presented.

Hybrid foraging in patchy environments using spatial memory.

Efficient random searches are essential to the survival of foragers searching for sparsely distributed targets. Lévy walks have been found to optimize the search over a wide range of constraints. When targets are distributed within patches, generating a spatial memory over the detected targets can be beneficial towards optimizing the search efficiency. Because foragers have limited memory, storing each target location separately is unrealistic. Instead, we propose incrementally learning a spatial distribution in favour of memorizing target locations. We demonstrate that an ensemble of Gaussian mixture models is a suitable candidate for such a spatial distribution. Using this, a hybrid foraging strategy is proposed, which interchanges random searches with informed movement. Informed movement results in displacements towards target locations, and is more likely to occur if the learned spatial distribution is correct. We show that, depending on the strength of the memory effects, foragers optimize search efficiencies by continuous revisitation of non-destructive targets. However, this negatively affects both the target and patch diversity, indicating that memory does not necessarily optimize multi-objective searches. Hence, the benefits of memory depend on the specific goals of the forager. Furthermore, through analysis of the distribution over walking distances of the forager, we show that memory changes the underlying walk characteristics. Specifically, the forager resorts to Brownian motion instead of Lévy walks, due to truncation of the long straight line displacements resulting from memory effects. This study provides a framework that opens up new avenues for investigating memory effects on foraging in sparse environments.

Adaptive Foraging in Dynamic Environments Using Scale-Free Interaction Networks.

Group interactions are widely observed in nature to optimize a set of critical collective behaviors, most notably sensing and decision making in uncertain environments. Nevertheless, these interactions are commonly modeled using local (proximity) networks, in which individuals interact within a certain spatial range. Recently, other interaction topologies have been revealed to support the emergence of higher levels of scalability and rapid information exchange. One prominent example is scale-free networks. In this study, we aim to examine the impact of scale-free communication when implemented for a swarm foraging task in dynamic environments. We model dynamic (uncertain) environments in terms of changes in food density and analyze the collective response of a simulated swarm with communication topology given by either proximity or scale-free networks. Our results suggest that scale-free networks accelerate the process of building up a rapid collective response to cope with the environment changes. However, this comes at the cost of lower coherence of the collective decision. Moreover, our findings suggest that the use of scale-free networks can improve swarm performance due to two side-effects introduced by using long-range interactions and frequent network regeneration. The former is a topological consequence, while the latter is a necessity due to robot motion. These two effects lead to reduced spatial correlations of a robot's behavior with its neighborhood and to an enhanced opinion mixing, i.e., more diversified information sampling. These insights were obtained by comparing the swarm performance in presence of scale-free networks to scenarios with alternative network topologies, and proximity networks with and without packet loss.

Robot Assistance in Dynamic Smart Environments-A Hierarchical Continual Planning in the Now Framework.

By coupling a robot to a smart environment, the robot can sense state beyond the perception range of its onboard sensors and gain greater actuation capabilities. Nevertheless, incorporating the states and actions of Internet of Things (IoT) devices into the robot's onboard planner increases the computational load, and thus can delay the execution of a task. Moreover, tasks may be frequently replanned due to the unanticipated actions of humans. Our framework aims to mitigate these inadequacies. In this paper, we propose a continual planning framework, which incorporates the sensing and actuation capabilities of IoT devices into a robot's state estimation, task planing and task execution. The robot's onboard task planner queries a cloud-based framework for actuators, capable of the actions the robot cannot execute. Once generated, the plan is sent to the cloud back-end, which will inform the robot if any IoT device reports a state change affecting its plan. Moreover, a Hierarchical Continual Planning in the Now approach was developed in which tasks are split-up into subtasks. To delay the planning of actions that will not be promptly executed, and thus to reduce the frequency of replanning, the first subtask is planned and executed before the subsequent subtask is. Only information relevant to the current (sub)task is provided to the task planner. We apply our framework to a smart home and office scenario in which the robot is tasked with carrying out a human's requests. A prototype implementation in a smart home, and simulator-based evaluation results, are presented to demonstrate the effectiveness of our framework.

Action Graphs for Performing Goal Recognition Design on Human-Inhabited Environments.

Goal recognition is an important component of many context-aware and smart environment services; however, a person's goal often cannot be determined until their plan nears completion. Therefore, by modifying the state of the environment, our work aims to reduce the number of observations required to recognise a human's goal. These modifications result in either: Actions in the available plans being replaced with more distinctive actions; or removing the possibility of performing some actions, so humans are forced to take an alternative (more distinctive) plan. In our solution, a symbolic representation of actions and the world state is transformed into an Action Graph, which is then traversed to discover the non-distinctive plan prefixes. These prefixes are processed to determine which actions should be replaced or removed. For action replacement, we developed an exhaustive approach and an approach that shrinks the plans then reduces the non-distinctive plan prefixes, namely Shrink-Reduce. Exhaustive is guaranteed to find the minimal distinctiveness but is more computationally expensive than Shrink-Reduce. These approaches are compared using a test domain with varying amounts of goals, variables and values, and a realistic kitchen domain. Our action removal method is shown to increase the distinctiveness of various grid-based navigation problems, with a width/height ranging from 4 to 16 and between 2 and 14 randomly selected goals, by an average of 3.27 actions in an average time of 4.69 s, whereas a state-of-the-art approach often breaches a 10 min time limit.

The Neglected Pieces of Designing Collective Decision-Making Processes.

Autonomous decision-making is a fundamental requirement for the intelligent behavior of individual agents and systems. For artificial systems, one of the key design prerequisites is providing the system with the ability to make proper decisions. Current literature on collective artificial systems designs decision-making mechanisms inspired mostly by the successful natural systems. Nevertheless, most of the approaches focus on voting mechanisms and miss other fundamental aspects. In this paper, we aim to draw attention to the missed pieces for the design of efficient collective decision-making, mainly information processes in its two types of stimuli and options set.

Scale invariance in natural and artificial collective systems: a review.

Self-organized collective coordinated behaviour is an impressive phenomenon, observed in a variety of natural and artificial systems, in which coherent global structures or dynamics emerge from local interactions between individual parts. If the degree of collective integration of a system does not depend on size, its level of robustness and adaptivity is typically increased and we refer to it as scale-invariant. In this review, we first identify three main types of self-organized scale-invariant systems: scale-invariant spatial structures, scale-invariant topologies and scale-invariant dynamics. We then provide examples of scale invariance from different domains in science, describe their origins and main features and discuss potential challenges and approaches for designing and engineering artificial systems with scale-invariant properties.