This paper presents an effective, cooperative, and probabilistically-complete multi-robot motion planner that enables each robot to move to a desired location while avoiding collisions with obstacles and other robots. The approach takes into account not only the geometric constraints arising from collision avoidance, but also the differential constraints imposed by the motion dynamics of each robot. This makes it possible to generate collision-free and dynamically-feasible trajectories that can be executed in the physical world.The salient aspect of the approach is the coupling of sampling-based motion planning to handle the complexity arising from the obstacles and robot dynamics with multi-agent search to find solutions over a suitable discrete abstraction. The discrete abstraction is obtained by constructing roadmaps to solve a relaxed problem that accounts for the obstacles but not the dynamics. Sampling-based motion planning expands a motion tree in the composite state space of all the robots by adding collision-free and dynamically-feasible trajectories as branches. Efficiency is obtained by using multi-agent search to find non-conflicting routes over the discrete abstraction which serve as heuristics to guide the motion-tree expansion. When little or no progress is made, the routes are penalized and the multi-agent search is invoked again to find alternative routes. This synergistic coupling makes it possible to effectively plan collision-free and dynamically-feasible motions that enable each robot to reach its goal. Experiments using vehicle models with nonlinear dynamics operating in complex environments, where cooperation among robots is required, show significant speedups over related work.

Machine learning techniques have deeply rooted in our everyday life. However, since it is knowledge- and labor-intensive to pursuit good learning performance, human experts are heavily engaged in every aspect of machine learning. In order to make machine learning techniques easier to apply and reduce the demand for experienced human experts, automatic machine learning~(AutoML) has emerged as a hot topic of both in industry and academy. In this paper, we provide a survey on existing AutoML works. First, we introduce and define the AutoML problem, with inspiration from both realms of automation and machine learning. Then, we propose a general AutoML framework that not only covers almost all existing approaches but also guides the design for new methods. Afterward, we categorize and review the existing works from two aspects, i.e., the problem setup and the employed techniques. Finally, we provide a detailed analysis of AutoML approaches and explain the reasons underneath their successful applications. We hope this survey can serve as not only an insightful guideline for AutoML beginners but also an inspiration for future researches.

In this paper, we show that even if artificial intelligence (AI) or machine learning (ML) systems are individually well-aligned with a goal, specific classes of over-optimization failures can create dynamics in multiparty systems that lead to new failure modes. Even specification of noncompetitive or cooperative goals does not necessarily provide any guarantee for the behavior of systems. By outlining how and why these multi-agent failures can occur, the paper hopes to spur system designers to explicitly consider these failure modes in designing systems, and to find approaches for mitigating them. When complex systems are optimized by a single agent, the representation of the system and of the goal used for optimization often lead to failures that can be surprising to the agent's designers. These various failure modes have been referred to as Goodhart's law [1, 2], Campbell's law [3], faulty reward functions [4], distributional shift [4], reward hacking [5], Proxyeconomics[6], and presumably many other terms. Such failure modes are the focus of a significant body of work in AI safety, and progress has been made.

Flocking refers to collective behavior of a large number of interacting entities, where the interactions between discrete individuals produce collective motion on the large scale. We employ an agent-based model to describe the microscopic dynamics of each individual in a flock, and use a fractional PDE to model the evolution of macroscopic quantities of interest. The macroscopic models with phenomenological interaction functions are derived by applying the continuum hypothesis to the microscopic model. Instead of specifying the fPDEs with an ad hoc fractional order for nonlocal flocking dynamics, we learn the effective nonlocal influence function in fPDEs directly from particle trajectories generated by the agent-based simulations. We demonstrate how the learning framework is used to connect the discrete agent-based model to the continuum fPDEs in 1D and 2D nonlocal flocking dynamics. In particular, a Cucker-Smale particle model is employed to describe the microscale dynamics of each individual, while Euler equations with nonlocal interaction terms are used to compute the evolution of macroscale quantities. The trajectories generated by the particle simulations mimic the field data of tracking logs that can be obtained experimentally. They can be used to learn the fractional order of the influence function using a Gaussian process regression model implemented with the Bayesian optimization. We show that the numerical solution of the learned Euler equations solved by the finite volume scheme can yield correct density distributions consistent with the collective behavior of the agent-based system. The proposed method offers new insights on how to scale the discrete agent-based models to the continuum-based PDE models, and could serve as a paradigm on extracting effective governing equations for nonlocal flocking dynamics directly from particle trajectories.

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically naturalistic simulated environment in which an agent can move and interact with objects it sees, we propose a "world-model" network that learns to predict the dynamic consequences of the agent's actions. Simultaneously, we train a separate explicit "self-model" that allows the agent to track the error map of its own world-model, and then uses the self-model to adversarially challenge the developing world-model. We demonstrate that this policy causes the agent to explore novel and informative interactions with its environment, leading to the generation of a spectrum of complex behaviors, including ego-motion prediction, object attention, and object gathering. Moreover, the world-model that the agent learns supports improved performance on object dynamics prediction, detection, localization and recognition tasks. Taken together, our results are initial steps toward creating flexible autonomous agents that self-supervise in complex novel physical environments.

Abstract--Internet of vehicles is a promising area related to D2D communication and internet of things. We present a novel perspective for vehicular communications, social vehicle swarms, to study and analyze socially aware internet of vehicles with the assistance of an agent-based model intended to reveal hidden patterns behind superficial data. After discussing its components, namely its agents, environments, and rules, we introduce supportive technology and methods, deep reinforcement learning, privacy preserving data mining and sub-cloud computing, in order to detect the most significant and interesting information for each individual effectively, which is the key desire. Finally, several relevant research topics and challenges are discussed. NETNET of vehicles (IoV) is a particular case, with vehicles being basic units, of internet of things (IoT) [1], which allows objects or devices to interact and communicate, indicating that an intrinsic component of IoT or IoV is device-to-device (D2D) communication [2]. IoV aims to build an intelligent system to improve the quality of driving or living; formally, to increase the quality of experience (QoE) or quality of service (QoS) [3]. Further study of IoV could lead to integration with smart cities, where each building, house, or even each individual device is capable of communication via wired or wireless access. On the other hand, online social networks (OSNs) have gained a growing amount of attention during recent years, and their use has almost become a daily necessity. This work has been supported by the National Natural Science Foundation of China (Nos.61271173 and 61372068), the Research Fund for the Doctoral Program of Higher Education of China (No.20130203110005), the Fundamental Research Funds for the Central Universities (No.K5051301033), the 111 Project(No. B08038), and also supported by the ISN State Key Laboratory. Y. Zhang, F. Tian and B. Song are with the State Key Laboratory of Integrated Services Networks, Xidian University, 710071, China (email: y.zhang@stu.xidian.edu.cn,

What will it be like when machines make and execute decisions without any human intervention? Why would we make such systems and what are their implications for the future of human judgment and free will? Hundreds, if not thousands, of science fiction stories tell us it's a bad idea to build automated systems without "Human-in-the-loop" (HITL) processes for keeping them in check. In real life, the need for human intervention before executing an automated process is most obvious when it has serious, irreversible consequences: like killing a person with a drone. In high stakes situations like drone strikes, humans make the difficult judgment call before the weapon's deadly automation kicks in.

Abstract--Differential evolution is the conventional algorithm with the fastest convergence speed, but it may be trapped local optimal solution easily, so many researchers devote themselves into improve DE. Whale swarm algorithm (WSA) is a new algorithm with niching strategy we proposed previously, it's featured with simple mutation strategy and powerful global search capability, but for functions with high dimensions, it converges slower than conventional algorithms. Based on this fact, we proposed a new DE algorithm, called DE with nearest & better option (NbDE). In order to evaluate the performance of NbDE, we compare NbDE with several meta-heuristic algorithms in nine classical benchmark functions with different dimensions. The result have shown that NbDE outperforms other algorithms in convergence speed and accuracy.

Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts. Here, we introduce the BabyAI research platform to support investigations towards including humans in the loop for grounded language learning. The BabyAI platform comprises an extensible suite of 19 levels of increasing difficulty. The levels gradually lead the agent towards acquiring a combinatorially rich synthetic language which is a proper subset of English. The platform also provides a heuristic expert agent for the purpose of simulating a human teacher. We report baseline results and estimate the amount of human involvement that would be required to train a neural network-based agent on some of the BabyAI levels. We put forward strong evidence that current deep learning methods are not yet sufficiently sample efficient when it comes to learning a language with compositional properties. How can a human train an intelligent agent to understand natural language instructions? We believe that this research question is important from both technological and scientific perspectives. No matter how advanced AI technology becomes, human users may want to customize their intelligent helpers to be able to better understand their desires and needs.

Customer care powered by artificial intelligence gives insurers the opportunity to save 30% of their service costs. How can insurers meet increased customer expectations at a lower cost? AI-powered care delivers on a future vision of customer service with an opportunity for savings of 30% by, for example, driving customers to digital experiences. In this post, I will explore how to apply AI using an intelligent customer engagement (ICE) framework. In this blog series, I'm exploring the myriad ways in which AI adds value to financial services in general and the insurance value chain in particular. In my previous post, I defined the term AIQ and revealed and discussed three key ingredients to building a strong AIQ: technology, data and people.