In the near future, transportation systems will includeboth autonomous vehicles and human-operated vehicles sharing thesame traffic conditions. Human drivers may have difficulties in predictingthe actions of autonomous vehicles, and the latter will facechallenges due to complex decision-making algorithms and dynamicenvironments. The lack of standardized communication between autonomousvehicles and human drivers complicates safe decisionmaking.This paper proposes a centralized generative AI-based advisoryframework to enhance human driving skills in mixed-autonomytraffic, and also to improve the autonomous vehicles in a Human-AIteaming fashion. The framework includes visual aids, explanations,and a virtual reality environment for testing and training.

There is growing attention on the importance of building intelligent systems where humans and Artificial Intelligence-based systems (AIs) form teams exploiting the potentially synergistic relationships between humans and automation. In the last decade, the computational modeling of empathy has gained increasing attention. Empowering interactive agents with empathic capabilities leads, on the human’s side, to more trust, increases engagement, and thus interaction length, helps cope with stress. These findings suggest that agents endowed with empathy may enhance social interaction in educational applications, artificial companions, medical assistants, and gaming applications. This article focuses on modeling the empathic behavior of virtual agents interacting with humans. We propose a formal model that enables virtual agents to exhibit empathic, emotional behavior. Specifically, we extend the modeling of empathy via behavior trees with a new type of node allowing the specification of various.

Empowering interactive agents with empathetic capabilitiesleads, on the human side, to more trust and increased engagement. Thisarticle focuses on modeling the empathetic behavior of virtual agentsinteracting with humans employing behavior trees which we further enhancewith neuro-symbolic capabilities. This allows the specification ofvarious kinds of empathy for the agents to be deployed for user supportin critical fields such as digital forensics. This paper is a follow-up to ourwork in the COST Action DigForASP.

In this work, we propose a novel architecture for agents to be employed in Human-AI Teaming in various, evencritical, domains based upon affective computing, empathy, and Theory of Mind, and a description of the userprofile and the operational, professional, and ethical requirements of the domain in which the agent operates.In this paper, we outline the architecture’s building blocks and their interconnections. The architectural designagent encompasses a Knowledge Graph to enclose the above-mentioned kinds of knowledge and a Behavior Treeenhanced via a Neural component, where the latter elaborates sensor input from devices that monitor the userand input from the knowledge graph. The enhanced behavior tree actually interacts with the user, making actionsor providing suggestions, and returns feedback to feed to the knowledge graph as a novelty in the literature. Webriefly present a case study, on which to experiment once the implementation, which is presently at an initialstage, will be completed. We discuss in some detail the Prolog program implementing the behavior tree, anddiscuss why we chose Prolog.

In this work, we describe an agent to be employed in Human-AI Teaming in various, even critical, domains, based uponaffective computing, empathy, and Theory of Mind, and a description of the user profile and of the operational, professional,and ethical requirements of the domain in which the agent operates. The architecture of the proposed agent encompasses aKnowledge Graph, a Neural component and a Behaviour Tree. We briefly discuss a case study.

Care Robots are the future of healthcare giving for patients with chronic diseases and disabilities. For improving the quality of caregiving and the trustworthiness of those robots, they should be equipped with emotion recognition capabilities and empathetic behavior. In this work, we propose an framework for an empathy module to be incorporated in every care robot, and then demonstrate the effectiveness of our proposal by means of an example.

For the tasks of improving caregiving in medicine and other sectors (i.e., teaching) and of constructingeffective human-AI teams, agents should be endowed with an emotion recognition and managementmodule, capable of empathy, and of modelling aspects of the Theory of Mind, in the sense of being ableto reconstruct what what someone is thinking or feeling. In this paper, we propose an architecture forsuch a module, based upon an enhanced notion of Behavior Trees. We illustrate the effectiveness of theproposed architecture on a significant example, and on a wider case study.

Aims. We study the effect a guiding magnetic field has on the formation and structure of a pair jet that propagates through a collisionless electron–proton plasma at rest.

Methods. We model with a particle-in-cell (PIC) simulation a pair cloud with a temperature of 400 keV and a mean speed of 0.9c (c - light speed). Pair particles are continuously injected at the boundary. The cloud propagates through a spatially uniform, magnetized, and cool ambient electron–proton plasma at rest. The mean velocity vector of the pair cloud is aligned with the uniform background magnetic field. The pair cloud has a lateral extent of a few ion skin depths.

Results. A jet forms in time. Its outer cocoon consists of jet-accelerated ambient plasma and is separated from the inner cocoon by an electromagnetic piston with a thickness that is comparable to the local thermal gyroradius of jet particles. The inner cocoon consists of pair plasma, which lost its directed flow energy while it swept out the background magnetic field and compressed it into the electromagnetic piston. A beam of electrons and positrons moves along the jet spine at its initial speed. Its electrons are slowed down and some positrons are accelerated as they cross the head of the jet. The latter escape upstream along the magnetic field, which yields an excess of megaelectronvolt positrons ahead of the jet. A filamentation instability between positrons and protons accelerates some of the protons, which were located behind the electromagnetic piston at the time it formed, to megaelectronvolt energies.

Conclusions. A microscopic pair jet in collisionless plasma has a structure that is similar to that predicted by a hydrodynamic model of relativistic astrophysical pair jets. It is a source of megaelectronvolt positrons. An electromagnetic piston acts as the contact discontinuity between the inner and outer cocoons. It would form on subsecond timescales in a plasma with a density that is comparable to that of the interstellar medium in the rest frame of the latter. A supercritical fast magnetosonic shock will form between the pristine ambient plasma and the jet-accelerated plasma on a timescale that exceeds our simulation time by an order of magnitude.

We present the results from a particle-in-cell (PIC) simulation that models the interaction between a spatially localized electron-positron cloud and an electron-ion plasma. The latter is permeated by a magnetic field that is initially spatially uniform and aligned with the mean velocity vector of the pair cloud. The pair cloud expels the magnetic field and piles it up into an electromagnetic piston. Its electromagnetic field is strong enough to separate the pair cloud from the ambient plasma in the direction that is perpendicular to the cloud propagation direction. The piston propagates away from the spine of the injected pair cloud and it accelerates the protons to a high nonrelativistic speed. The accelerated protons form an outer cocoon that will eventually become separated from the unperturbed ambient plasma by a fast magnetosonic shock. No electromagnetic piston forms at the front of the cloud and a shock is mediated here by the filamentation instability. The final plasma distribution resembles that of a hydrodynamic jet. Collisionless plasma jets may form in the coronal plasma of accreting black holes and the interaction between the strong magnetic field of the piston and the hot pair cloud may contribute to radio emissions by such objects.

Active living in older adults reduces disabilities and increases quality of life. Adherence to physical activity is low in older adults, therefore new possibilities to motivate to exercise must be explored. One of this new possibilities is to use exergaming. In this paper, we present an assistive tool for monitoring daily, physical activities in older adults with access to exergaming in their home environments. The proposed system employs the Kinect device and allows one to analyse the body movements. From a pilot study, we proved that the system can detect movements through exergaming. In the future we plan to implement the developed monitoring tool as well as exergaming in nursing homes.