scholarly journals Activity, Plan, and Goal Recognition: A Review

2021 ◽  
Vol 8 ◽  
Author(s):  
Franz A. Van-Horenbeke ◽  
Angelika Peer

Recognizing the actions, plans, and goals of a person in an unconstrained environment is a key feature that future robotic systems will need in order to achieve a natural human-machine interaction. Indeed, we humans are constantly understanding and predicting the actions and goals of others, which allows us to interact in intuitive and safe ways. While action and plan recognition are tasks that humans perform naturally and with little effort, they are still an unresolved problem from the point of view of artificial intelligence. The immense variety of possible actions and plans that may be encountered in an unconstrained environment makes current approaches be far from human-like performance. In addition, while very different types of algorithms have been proposed to tackle the problem of activity, plan, and goal (intention) recognition, these tend to focus in only one part of the problem (e.g., action recognition), and techniques that address the problem as a whole have been not so thoroughly explored. This review is meant to provide a general view of the problem of activity, plan, and goal recognition as a whole. It presents a description of the problem, both from the human perspective and from the computational perspective, and proposes a classification of the main types of approaches that have been proposed to address it (logic-based, classical machine learning, deep learning, and brain-inspired), together with a description and comparison of the classes. This general view of the problem can help on the identification of research gaps, and may also provide inspiration for the development of new approaches that address the problem in a unified way.

2020 ◽  
Vol 7 ◽  
Author(s):  
Matteo Spezialetti ◽  
Giuseppe Placidi ◽  
Silvia Rossi

A fascinating challenge in the field of human–robot interaction is the possibility to endow robots with emotional intelligence in order to make the interaction more intuitive, genuine, and natural. To achieve this, a critical point is the capability of the robot to infer and interpret human emotions. Emotion recognition has been widely explored in the broader fields of human–machine interaction and affective computing. Here, we report recent advances in emotion recognition, with particular regard to the human–robot interaction context. Our aim is to review the state of the art of currently adopted emotional models, interaction modalities, and classification strategies and offer our point of view on future developments and critical issues. We focus on facial expressions, body poses and kinematics, voice, brain activity, and peripheral physiological responses, also providing a list of available datasets containing data from these modalities.


2013 ◽  
Vol 765-767 ◽  
pp. 591-594
Author(s):  
Chao Ying Zhang ◽  
Hu Liu

Using interactive virtual simulation methods and combining numerical calculation software, the 3D airline emergency evacuation simulation system is established in Virtools platform according to the received data. The system takes full account of the passengers' individual differences during the evacuation process, setting up different member parameters, which influence the passengers evacuation behavior. In order to fulfill the different types of evacuation requirements in various simulation, it can change evacuation path algorithm, cabin layout data and evacuees component parameters, to get the corresponding evacuation simulation results. Meanwhile, the system interface can change visual angle to realize human-machine interaction freely and reflect the evacuation of the evacuation process accurately. Also the reliability of the system simulation result is verified by compared with the results of actual certification trial.


2007 ◽  
Vol 5 (1) ◽  
Author(s):  
María C. Cañadas ◽  
Jordi Deulofeu ◽  
Lourdes Figueiras ◽  
David Reid ◽  
Oleksiy Yevdokimov

In this paper we analyze different types and stages of the conjecturing process. A classification of conjectures is discussed. A variety of problems that could lead to conjectures are considered from the didactical point of view. Results from a number of research studies are used to identify and investigate a number of questions related to the theoretical background of conjecturing as well as practical implications in the learning process.


2018 ◽  
Vol 2018 ◽  
pp. 1-16
Author(s):  
Alexandre Alapetite ◽  
Emilie Møllenbach ◽  
Anders Stockmarr ◽  
Katsumi Minakata

We contribute to a project introducing the use of a large single touch-screen as a concept for future airplane cockpits. Human-machine interaction in this new type of cockpit must be optimised to cope with the different types of normal use as well as during moments of turbulence (which can occur during flights varying degrees of severity). We propose an original experimental setup for reproducing turbulence (not limited to aviation) based on a touch-screen mounted on a rollercoaster. Participants had to repeatedly solve three basic touch interactions: a single click, a one-finger drag-and-drop, and a zoom operation involving a 2-finger pinching gesture. The completion times of the different tasks as well as the number of unnecessary interactions with the screen constitute the collected user data. We also propose a data analysis and statistical method to combine user performance with observed turbulence, including acceleration and jerk along the different axes. We then report some of the implications of severe turbulence on touch interaction and make recommendations as to how this can be accommodated in future design solutions.


Author(s):  
A. Slysarenko

The article considers the MMC (Machinery Maintenance Connect) equipment maintenance system, factors that affect the key competence, the ability to regularly audit vessels and the time before the audit of vessels, the analysis of the company's risks associated with the possibility of cyber security threats against the resources of the IT information network, the possibility of implementing and using modern technologies in achieving modern cyber security and safe business operations of the Commission, the constant protection of critical it infrastructure. establishing a specific AI system, the human-machine interaction (ergatic system) and machine-machine (machine-to-Machine, M2M) and their interdependence with the corresponding application schemes, careful attention to the study of these interactions. The influence of factors on the change and their display in different types of work efficiency, risk management DNV GL of the AI system was studied.


2018 ◽  
Vol 82 (3) ◽  
pp. 74-82
Author(s):  
S. V. Yevdokimenko

This research is one of the first attempts in the Ukrainian legal science in determining the essence and features of legal components of economic risks taking into account the latest achievements of science. It has been emphasized that theoretical basis for determining the concept of “risk” is widely researched in the scientific literature, but the problem of legal components of the economic risks has been insufficiently highlighted. The concept of “legal components of economic risks” has been defined; factors that actualized the problem of risks in Ukraine have been considered; and the features of the classification of economic risks according to legal components have been established. It has been noted that the negative consequences of economic risks are unforeseen losses. From the point of view of legal risks, such consequences should be defined as losses (according to the Civil Code of Ukraine) or as the amount of caused damages (according to the Criminal Code of Ukraine). Administrative liability is also established depending on the amount of caused damage for different types of activities. According to the author, the essence of legal components of economic risks is to determine the criteria for the delimitation of lawful and unlawful economic risk, the possibility of using the levers of legal influence in this regard, namely the establishment of the basis for a person’s liability for damage caused by a risky act. Legal components contain possible options of overcoming the consequences of risk situations, establish the threshold for criminal liability and punishment for economic crimes, depending on the caused damage. On the basis of the analysis of the current legislation of Ukraine and generalization of the main provisions of the works of scholars, the author has made theoretical synthesis and has found a new solution to the scientific problem – the definition of the essence and features of legal components of economic risks related to liability in accordance with the legislation of Ukraine in order to overcome the consequences of risk situations for different types of activities depending on the amount of caused damage.


Sign in / Sign up

Export Citation Format

Share Document