Explore the vast range of titles available.

We consider mobile service robots that carry out tasks with, for, and around humans in their environments. Speech combined with on-screen display are common mechanisms for autonomous robots to communicate with humans, but such communication modalities may fail for mobile robots due to spatio-temporal limitations. To enable a better human understanding of the robot given its mobility and autonomous task performance, we introduce the use of lights to reveal the dynamic robot state. We contribute expressive lights as a primary modality for the robot to communicate to humans useful robot state information. Such lights are persistent, non-invasive, and visible at a distance, unlike other existing modalities. Current programmable light arrays provide a very large animation space, which we address by introducing a finite set of parametrized signal shapes while still maintaining the needed animation design flexibility. We present a formalism for light animation control and an architecture to map the representation of robot state to the parametrized light animation space. The mapping generalizes to multiple light strips and even other expression modalities. We demonstrate our approach on CoBot, a mobile multi-floor service robot, and evaluate its validity through several user studies. Our results show that carefully designed expressive lights on a mobile robot help humans better understand robot states and actions and can have a desirable impact on a collaborative human–robot behavior.

Multi-agent path planning (MAPP) is increasingly being used to address resource allocation problems in highly dynamic, distributed environments that involve autonomous agents. Example domains include surveillance automation, traffic control and others. Most MAPP approaches assume hard collisions, e.g., agents cannot share resources, or co-exist at the same node or edge. This assumption unnecessarily restricts the solution space and does not apply to many real-world scenarios. To mitigate this limitation, this paper introduces a more general class of MAPP problems—MAPP in a soft-collision context. In soft-collision MAPP problems, agents can share resources or co-exist in the same location at the expense of reducing the quality of the solution. Hard constraints can still be modeled by imposing a very high cost for sharing. This paper motivates and defines the soft-collision MAPP problem, and generalizes the widely-used M* MAPP algorithm to support the concept of soft-collisions. Soft-collision M* (SC-M*) extends M* by changing the definition of a collision, so paths with collisions that have a quality penalty below a given threshold are acceptable. For each candidate path, SC-M* keeps track of the reduction in satisfaction level of each agent using a collision score, and it places agents whose collision scores exceed its threshold into a soft-collision set for reducing the score. Our evaluation shows that SC-M* is more flexible and more scalable than M*. It can also handle complex environments that include agents requesting different types of resources. Furthermore, we show the benefits of SC-M* compared with several baseline algorithms in terms of path cost, success rate and run time.

Faba bean (Vicia faba L.) is a facultative cross-pollinating legume crop with a great importance for food and feed due to its high protein content as well as the important role in soil fertility and nitrogen fixation. In this work we evaluated genetic diversity and population structure of faba bean accessions from the Western Mediterranean basin and wild related species. For that purpose we screened 53 V. faba, 2 V. johannis and 7 V. narbonensis accessions from Portugal, Spain and Morocco with 28 faba bean Single Sequence Repeats (SSR). SSR genotyping showed that the number of alleles detected per locus for the polymorphic markers ranged between 2 and 10, with Polymorphic Information Content (PIC) values between 0.662 and 0.071, and heterozygosity (HO) between 0-0.467. Heterozygosity and inbreeding coefficient levels indicate a higher level of inbreeding in wild related species than in cultivated Vicia. The analysis of molecular variance (AMOVA) showed a superior genetic diversity within accessions than between accessions even from distant regions. These results are in accordance to population structure analysis showing that individuals from the same accession can be genetically more similar to individuals from far away accessions, than from individuals from the same accession. In all three levels of analysis (whole panel of cultivated and wild accessions, cultivated faba bean accessions and Portuguese accessions) no population structure was observed based on geography or climatic factors. Differences between V. narbonensis and V. johannis are undetectable although these wild taxa are clearly distinct from V. faba accessions. Thus, a limited gene flow occurred between cultivated accessions and wild relatives. Contrastingly, the lack of population structure seems to indicate a high degree of gene flow between V. faba accessions, possibly explained by the partially allogamous habit in association with frequent seed exchange/introduction.

Along with population growth, global climate change represents a critical threat to agricultural production, compromising the goal of achieving food and nutrition security for all. It is urgent to create sustainable and resilient agri-food systems capable of feeding the world without debilitating the planet. The Food and Agriculture Organization of the United Nations (FAO) refers to pulses as a superfood, as one of the most nutritious crops with high health benefits. Considered to be low-cost, many can be produced in arid lands and have an extended shelf-life. Their cultivation helps reduce greenhouse gases and increases carbon sequestration, also improving soil fertility. Cowpea, Vigna unguiculata (L.) Walp. is particularly drought tolerant, with a wide diversity of landraces adapted to different environments. Considering the importance of knowing and valuing the genetic variability of this species in Portugal, this study assessed the impact of drought on four landraces of cowpea (L1 to L4) from different regions of the country and a national commercial variety (CV) as a reference. The development and evaluation of morphological characteristics were monitored in response to terminal drought (imposed during the reproductive phase), and its effects were evaluated on the yield and quality of the produced grain, namely the weight of 100 grains, color, protein content, and soluble sugars. Under drought conditions, the landraces L1 and L2 showed early maturation as a strategy to avoid water deficit. Morphological alteration of the aerial part of the plants was evident in all genotypes, with a rapid reduction in the number of leaves and a reduction in the number of flowers and pods by between 44 and 72%. The parameters of grain quality, the weight of 100 grains, color, protein, and soluble sugars did not vary significantly, except for sugars of the raffinose family that is associated with the adaptive mechanisms of plants to drought. The performance and maintenance of the evaluated characteristics reflect the adaptation acquired in the past by exposure to the Mediterranean climate, highlighting the potential agronomic and genetic value, still little exploited, that could contribute to production stability, preserved nutritional value, and food safety under water stress.

Many real-world robotic scenarios require performing task planning to decide courses of actions to be executed by (possibly heterogeneous) robots. A classical centralized planning approach has to find a solution inside a search space that contains every possible combination of robots and goals. This leads to inefficient solutions that do not scale well. Multi-Agent Planning (MAP) provides a new way to solve this kind of tasks efficiently. Previous works on MAP have proposed to factorize the problem to decrease the planning effort i.e. dividing the goals among the agents (robots). However, these techniques do not scale when the number of agents and goals grow. Also, in most real world scenarios with big maps, goals might not be reached by every robot so it has a computational cost associated. In this paper we propose a combination of robotics and planning techniques to alleviate and boost the computation of the goal assignment process. We use Actuation Maps (AMs). Given a map, AMs can determine the regions each agent can actuate on. Thus, specific information can be extracted to know which goals can be tackled by each agent, as well as cheaply estimating the cost of using each agent to achieve every goal. Experiments show that when information extracted from AMs is provided to a multi-agent planning algorithm, the goal assignment is significantly faster, speeding-up the planning process considerably. Experiments also show that this approach greatly outperforms classical centralized planning.

Learning from demonstration algorithms enable a robot to learn a new policy based on demonstrations provided by a teacher. In this article, we explore a novel research direction, multi-robot learning from demonstration , which extends demonstration based learning methods to collaborative multi-robot domains. Specifically, we study the problem of enabling a single person to teach individual policies to multiple robots at the same time. We present flexMLfD , a task and platform independent multi-robot demonstration learning framework that supports both independent and collaborative multi-robot behaviors. Building upon this framework, we contribute three approaches to teaching collaborative multi-robot behaviors based on different information sharing strategies, and evaluate these approaches by teaching two Sony QRIO humanoid robots to perform three collaborative ball sorting tasks. We then present scalability analysis of flexMLfD using up to seven Sony AIBO robots. We conclude the article by proposing a formalization for a broader multi-robot learning from demonstration research area.

RoboCup was created in 1996 by a group of Japanese, American, and European artificial intelligence and robotics researchers with a formidable, visionary long‐term challenge: By 2050 a team of robot soccer players will beat the human World Cup champion team. In this article, we focus on RoboCup robot soccer, and present its five current leagues, which address complementary scientific challenges through different robot and physical setups. Full details on the status of the RoboCup soccer leagues, including league history and past results, upcoming competitions, and detailed rules and specifications are available from the league homepages and wikis.

Cowpea (Vigna unguiculata) is a robust legume; nevertheless, yield is always affected by drought, especially when it occurs during reproductive growth and seed filling. Considered a key crop in the effort to attain food security, and a suitable crop for a scenario of climate change, modern disregard for cowpea landraces is particularly detrimental as it causes genetic variability loss, compromising breeding efforts. To contribute to the evaluation of the cowpea germplasm, four Portuguese landraces (L1, L2, L3, L4) were compared with a commercial variety (CV) to evaluate their physiological responses to terminal drought and their inter-variation on productivity, under semi-controlled conditions. Despite no differences in relative water content (RWC) between the CV and the landraces under water deficit (WD), differences in leaf water potential (Ψ) defined the CV as having an isohydric control of stomata in contrast with anisohydric control for landraces. There was an identical decrease in the photosynthetic rate for all plants under stress, caused by both stomatal and non-stomatal limitations, namely, damages at the level of photosystem II as indicated by fluorescence measurements. Instantaneous water use efficiency (iWUE) was improved with stress in L1 and L3. Maintenance of higher relative chlorophyll content for longer periods in the CV revealed a stay-green phenotype. The slim differences observed in terms of stomatal control, iWUE and progression of senescence between the CV and the landraces under WD led to quite important differences in terms of productivity, as inferred from improved yield (number of pods and number of grains per plant). This is a clear result of pragmatic on-farm selection. On one hand it shows that small differences in stomatal responses or water saving strategies under WD may lead to desirable outcomes and should therefore be considered during breeding. On the other hand, it suggests that other traits could be explored in view of drought adaptation. These results highlight the need to preserve and characterize as many genetic pools as possible within a species.

Four leading researchers share their concerns and solutions for reducing societal risks from intelligent machines.

Portugal contributed to the global diffusion of sweetpotato (Ipomoea batatas L. Lam.). Although it is of minor importance on the Portuguese mainland, it is one of the most common crops in the Azores and Madeira archipelagos and is highly relevant in the Portuguese ex-colonies Mozambique and Timor-Leste. We analyzed the genetic diversity and population structure of sweetpotato from these five geographic provenances using twelve nuclear simple sequence repeat (SSR) markers. We studied 45 accessions, 15 of which were collected from farmers’ fields in these five regions and 30 of which are held at “Banco de Germoplasma de Moçambique”. The SSR markers showed a high level of polymorphism and a high number of alleles per locus. Population structure analyses using Bayesian clustering (STRUCTURE) grouped accessions from farmers’ fields into two groups and divided samples of “Banco de Germoplasma de Moçambique” into three groups. A principal coordinate analysis (PCoA), based on the Bruvo distance, supported the population structure analysis. Concerning the genebank accessions, the two analyses indicated three clusters, all of them containing Mozambican landraces. From our results, it may be concluded that sweetpotato populations from the three countries do not share a common genetic background, despite the shared history of the countries.