RESUMO
Political discourse is the soul of democracy, but misunderstanding and conflict can fester in divisive conversations. The widespread shift to online discourse exacerbates many of these problems and corrodes the capacity of diverse societies to cooperate in solving social problems. Scholars and civil society groups promote interventions that make conversations less divisive or more productive, but scaling these efforts to online discourse is challenging. We conduct a large-scale experiment that demonstrates how online conversations about divisive topics can be improved with AI tools. Specifically, we employ a large language model to make real-time, evidence-based recommendations intended to improve participants' perception of feeling understood. These interventions improve reported conversation quality, promote democratic reciprocity, and improve the tone, without systematically changing the content of the conversation or moving people's policy attitudes.
Assuntos
Idioma , Políticas , HumanosRESUMO
Human teams are able to easily perform collaborative manipulation tasks. However, simultaneously manipulating a large extended object for a robot and human is a difficult task due to the inherent ambiguity in the desired motion. Our approach in this paper is to leverage data from human-human dyad experiments to determine motion intent for a physical human-robot co-manipulation task. We do this by showing that the human-human dyad data exhibits distinct torque triggers for a lateral movement. As an alternative intent estimation method, we also develop a deep neural network based on motion data from human-human trials to predict future trajectories based on past object motion. We then show how force and motion data can be used to determine robot control in a human-robot dyad. Finally, we compare human-human dyad performance to the performance of two controllers that we developed for human-robot co-manipulation. We evaluate these controllers in three-degree-of-freedom planar motion where determining if the task involves rotation or translation is ambiguous.
RESUMO
Various approaches have used neural networks as probabilistic models for the design of protein sequences. These "inverse folding" models employ different objective functions, which come with trade-offs that have not been assessed in detail before. This study introduces probabilistic definitions of protein stability and conformational specificity and demonstrates the relationship between these chemical properties and the [Formula: see text] Boltzmann probability objective. This links the Boltzmann probability objective function to experimentally verifiable outcomes. We propose a novel sequence decoding algorithm, referred to as "BayesDesign", that leverages Bayes' Rule to maximize the [Formula: see text] objective instead of the [Formula: see text] objective common in inverse folding models. The efficacy of BayesDesign is evaluated in the context of two protein model systems, the NanoLuc enzyme and the WW structural motif. Both BayesDesign and the baseline ProteinMPNN algorithm increase the thermostability of NanoLuc and increase the conformational specificity of WW. The possible sources of error in the model are analyzed.
Assuntos
Algoritmos , Teorema de Bayes , Estabilidade Proteica , Sequência de Aminoácidos , Funções VerossimilhançaRESUMO
Model-based optimal control of soft robots may enable compliant, underdamped platforms to operate in a repeatable fashion and effectively accomplish tasks that are otherwise impossible for soft robots. Unfortunately, developing accurate analytical dynamic models for soft robots is time-consuming, difficult, and error-prone. Deep learning presents an alternative modeling approach that only requires a time history of system inputs and system states, which can be easily measured or estimated. However, fully relying on empirical or learned models involves collecting large amounts of representative data from a soft robot in order to model the complex state space-a task which may not be feasible in many situations. Furthermore, the exclusive use of empirical models for model-based control can be dangerous if the model does not generalize well. To address these challenges, we propose a hybrid modeling approach that combines machine learning methods with an existing first-principles model in order to improve overall performance for a sampling-based non-linear model predictive controller. We validate this approach on a soft robot platform and demonstrate that performance improves by 52% on average when employing the combined model.
RESUMO
Soft robots have the potential to significantly change the way that robots interact with the environment and with humans. However, accurately modeling soft robot and soft actuator dynamics in order to perform model-based control can be extremely difficult. Deep neural networks are a powerful tool for modeling systems with complex dynamics such as the pneumatic, continuum joint, six degree-of-freedom robot shown in this paper. Unfortunately it is also difficult to apply standard model-based control techniques using a neural net. In this work, we show that the gradients used within a neural net to relate system states and inputs to outputs can be used to formulate a linearized discrete state space representation of the system. Using the state space representation, model predictive control (MPC) was developed with a six degree of freedom pneumatic robot with compliant plastic joints and rigid links. Using this neural net model, we were able to achieve an average steady state error across all joints of approximately 1 and 2° with and without integral control respectively. We also implemented a first-principles based model for MPC and the learned model performed better in terms of steady state error, rise time, and overshoot. Overall, our results show the potential of combining empirical modeling approaches with model-based control for soft robots and soft actuators.
RESUMO
Invasive alien species are a major threat to native insular species. Eradicating invasive mammals from islands is a feasible and proven approach to prevent biodiversity loss. We developed a conceptual framework to identify globally important islands for invasive mammal eradications to prevent imminent extinctions of highly threatened species using biogeographic and technical factors, plus a novel approach to consider socio-political feasibility. We applied this framework using a comprehensive dataset describing the distribution of 1,184 highly threatened native vertebrate species (i.e. those listed as Critically Endangered or Endangered on the IUCN Red List) and 184 non-native mammals on 1,279 islands worldwide. Based on extinction risk, irreplaceability, severity of impact from invasive species, and technical feasibility of eradication, we identified and ranked 292 of the most important islands where eradicating invasive mammals would benefit highly threatened vertebrates. When socio-political feasibility was considered, we identified 169 of these islands where eradication planning or operation could be initiated by 2020 or 2030 and would improve the survival prospects of 9.4% of the Earth's most highly threatened terrestrial insular vertebrates (111 of 1,184 species). Of these, 107 islands were in 34 countries and territories and could have eradication projects initiated by 2020. Concentrating efforts to eradicate invasive mammals on these 107 islands would benefit 151 populations of 80 highly threatened vertebrates and make a major contribution towards achieving global conservation targets adopted by the world's nations.
Assuntos
Conservação dos Recursos Naturais/métodos , Espécies Introduzidas/tendências , Animais , Biodiversidade , Espécies em Perigo de Extinção , Extinção Biológica , Ilhas , MamíferosRESUMO
Humans have greatly altered the natural distribution of species, making it difficult to distinguish between natural and introduced populations. This is a problem for conservation efforts because native or introduced status can determine whether a species is afforded protection or persecuted as an invasive pest. Holocene colonization events are especially difficult to discern, particularly when the species in question is a naturally good disperser and widely transported by people. In this study, we test the origin of such a species, the diamondback terrapin (Malaclemys terrapin), on Bermuda using a combination of palaeontologic (fossil, radiometric and palaeoenvironmental) and genetic data. These lines of evidence support the hypothesis that terrapins are relatively recent (between 3000 and 400 years ago) natural colonizers of Bermuda. The tiny population of Bermudian terrapins represents the second naturally occurring non-marine reptile that still survives on one of the most densely populated and heavily developed oceanic islands in the world. We recommend that they should be given protection as a native species.