We develop a learning-based algorithm for the distributed formation control of networked multi-agent systems governed by unknown, nonlinear dynamics. Most existing algorithms either assume certain parametric forms for the unknown dynamic terms or resort to unnecessarily large control inputs in order to provide theoretical guarantees. The proposed algorithm avoids these drawbacks by integrating neural network-based learning with adaptive control in a two-step procedure. In the first step of the algorithm, each agent learns a controller, represented as a neural network, using training data that correspond to a collection of formation tasks and agent parameters. These parameters and tasks are derived by varying the nominal agent parameters and the formation specifications of the task in hand, respectively. In the second step of the algorithm, each agent incorporates the trained neural network into an online and adaptive control policy in such a way that the behavior of the multi-agent closed-loop system satisfies a user-defined formation task. Both the learning phase and the adaptive control policy are distributed, in the sense that each agent computes its own actions using only local information from its neighboring agents. The proposed algorithm does not use any a priori information on the agents' unknown dynamic terms or any approximation schemes. We provide formal theoretical guarantees on the achievement of the formation task.

Cognitive cooperative assistance in robot-assisted surgery holds the potential to increase quality of care in minimally invasive interventions. Automation of surgical tasks promises to reduce the mental exertion and fatigue of surgeons. In this work, multi-agent reinforcement learning is demonstrated to be robust to the distribution shift introduced by pairing a learned policy with a human team member. Multi-agent policies are trained directly from images in simulation to control multiple instruments in a sub task of the minimally invasive removal of the gallbladder. These agents are evaluated individually and in cooperation with humans to demonstrate their suitability as autonomous assistants. Compared to human teams, the hybrid teams with artificial agents perform better considering completion time (44.4% to 71.2% shorter) as well as number of collisions (44.7% to 98.0% fewer). Path lengths, however, increase under control of an artificial agent (11.4% to 33.5% longer). A multi-agent formulation of the learning problem was favored over a single-agent formulation on this surgical sub task, due to the sequential learning of the two instruments. This approach may be extended to other tasks that are difficult to formulate within the standard reinforcement learning framework. Multi-agent reinforcement learning may shift the paradigm of cognitive robotic surgery towards seamless cooperation between surgeons and assistive technologies.

A reflection of the Corona pandemic highlights the need for more sustainable production systems using automation. The goal is to retain automation of repetitive tasks while allowing complex parts to come together. We recognize the fragility and how hard it is to create traditional automation. We introduce a method which converts one really hard problem of producing sustainable production code into three simpler problems being data, patterns and working prototypes. We use developer seniority as a metric to measure whether the proposed method is easier. By using agent-based simulation and NanoVC repos for agent arbitration, we are able to create a simulated environment where patterns developed by people are used to transform working prototypes into templates that data can be fed through to create the robots that create the production code. Having two layers of robots allow early implementation choices to be replaced as we gather more feedback from the working system. Several benefits of this approach have been discovered, with the most notable being that the Robot of Robots encodes a legacy of the person that designed it in the form of the 3 ingredients (data, patterns and working prototypes). This method allows us to achieve our goal of reducing the fragility of the production code while removing the difficulty of getting there.

Multi-task optimization (MTO) studies how to simultaneously solve multiple optimization problems for the purpose of obtaining better performance on each problem. Over the past few years, evolutionary MTO (EMTO) was proposed to handle MTO problems via evolutionary algorithms. So far, many EMTO algorithms have been developed and demonstrated well performance on solving real-world problems. However, there remain many works to do in adapting knowledge transfer to task relatedness in EMTO. Different from the existing works, we develop a self-adaptive multi-task particle swarm optimization (SaMTPSO) through the developed knowledge transfer adaptation strategy, the focus search strategy and the knowledge incorporation strategy. In the knowledge transfer adaptation strategy, each task has a knowledge source pool that consists of all knowledge sources. Each source (task) outputs knowledge to the task. And knowledge transfer adapts to task relatedness via individuals' choice on different sources of a pool, where the chosen probabilities for different sources are computed respectively according to task's success rate in generating improved solutions via these sources. In the focus search strategy, if there is no knowledge source benefit the optimization of a task, then all knowledge sources in the task's pool are forbidden to be utilized except the task, which helps to improve the performance of the proposed algorithm. Note that the task itself is as a knowledge source of its own. In the knowledge incorporation strategy, two different forms are developed to help the SaMTPSO explore and exploit the transferred knowledge from a chosen source, each leading to a version of the SaMTPSO. Several experiments are conducted on two test suites. The results of the SaMTPSO are comparing to that of 3 popular EMTO algorithms and a particle swarm algorithm, which demonstrates the superiority of the SaMTPSO.

We propose a new formalization of legal competences, and in particular for the Hohfeldian categories of power and immunity, through a deontic reinterpretation of dynamic epistemic logic. We argue that this logic explicitly captures the norm-changing character of legal competences while providing a sophisticated reduction of the latter to static normative positions. The logic is completely axiomatizable, and we apply it to a concrete case in German contract law to illustrate that it can capture the distinction between legal ability and legal permissibility.

Artificial Intelligence (AI) logic formalizes the reasoning of intelligent agents. In this paper, we discuss how an argumentation-based AI logic could be used also to formalize important aspects of social reasoning. Besides reasoning about the knowledge and actions of individual agents, social AI logic can reason also about social dependencies among agents using the rights, obligations and permissions of the agents. We discuss four aspects of social AI logic. First, we discuss how rights represent relations between the obligations and permissions of intelligent agents. Second, we discuss how to argue about the right-to-know, a central issue in the recent discussion of privacy and ethics. Third, we discuss how a wide variety of conflicts among intelligent agents can be identified and (sometimes) resolved by comparing formal arguments. Importantly, to cover a wide range of arguments occurring in daily life, also fallacious arguments can be represented and reasoned about. Fourth, we discuss how to argue about the freedom to act for intelligent agents. Examples from social, legal and ethical reasoning highlight the challenges in developing social AI logic. The discussion of the four challenges leads to a research program for argumentation-based social AI logic, contributing towards the future development of AI logic.

Singapore, Singapore--(Newsfile Corp. - October 8, 2021) - PlatON, a next-generation Internet infrastructure protocol based on the fundamental properties of blockchain, recently combined blockchain, artificial intelligence and privacy computing technology to establish a decentralized collaborative privacy artificial intelligence network, which would take utilization of data to a new level. This network will serve as the infrastructure of autonomous artificial intelligence (AI) agents, who can facilitate advanced artificial intelligence and explore the road to Artificial General Intelligence. Based on blockchain network, PlatON developers designed a decentralized privacy computing network to connect data, algorithms and hashrate through privacy computing protocols. Autonomous AI agents can obtain the required resources at low cost, train artificial intelligence models and publish them on the network, and interact with other artificial intelligence services or agents to form a self-organizing and cooperative artificial intelligence network. On this network, anyone can obtain artificial intelligence technology or become a stakeholder in its development, and realize the autonomy of artificial intelligence.

Sensory and emotional experiences such as pain and empathy are relevant to mental and physical health. The current drive for automated pain recognition is motivated by a growing number of healthcare requirements and demands for social interaction make it increasingly essential. Despite being a trending area, they have not been explored in great detail. Over the past decades, behavioral science and neuroscience have uncovered mechanisms that explain the manifestations of pain. Recently, also artificial intelligence research has allowed empathic machine learning methods to be approachable. Generally, the purpose of this paper is to review the current developments for computational pain recognition and artificial empathy implementation. Our discussion covers the following topics: How can AI recognize pain from unimodality and multimodality? Is it necessary for AI to be empathic? How can we create an AI agent with proactive and reactive empathy? This article explores the challenges and opportunities of real-world multimodal pain recognition from a psychological, neuroscientific, and artificial intelligence perspective. Finally, we identify possible future implementations of artificial empathy and analyze how humans might benefit from an AI agent equipped with empathy.

We present a literature survey on non-interactive computational story generation. The article starts with the presentation of requirements for creative systems, three types of models of creativity (computational, socio-cultural, and individual), and models of human creative writing. Then it reviews each class of story generation approach depending on the used technology: story-schemas, analogy, rules, planning, evolutionary algorithms, implicit knowledge learning, and explicit knowledge learning. Before the concluding section, the article analyses the contributions of the reviewed work to improve the quality of the generated stories. This analysis addresses the description of the story characters, the use of narrative knowledge including about character believability, and the possible lack of more comprehensive or more detailed knowledge or creativity models. Finally, the article presents concluding remarks in the form of suggestions of research topics that might have a significant impact on the advancement of the state of the art on autonomous non-interactive story generation systems. The article concludes that the autonomous generation and adoption of the main idea to be conveyed and the autonomous design of the creativity ensuring criteria are possibly two of most important topics for future research.

Explainable AI techniques that describe agent reward functions can enhance human-robot collaboration in a variety of settings. One context where human understanding of agent reward functions is particularly beneficial is in the value alignment setting. In the value alignment context, an agent aims to infer a human's reward function through interaction so that it can assist the human with their tasks. If the human can understand where gaps exist in the agent's reward understanding, they will be able to teach more efficiently and effectively, leading to quicker human-agent team performance improvements. In order to support human collaborators in the value alignment setting and similar contexts, it is first important to understand the effectiveness of different reward explanation techniques in a variety of domains. In this paper, we introduce a categorization of information modalities for reward explanation techniques, suggest a suite of assessment techniques for human reward understanding, and introduce four axes of domain complexity. We then propose an experiment to study the relative efficacy of a broad set of reward explanation techniques covering multiple modalities of information in a set of domains of varying complexity.