scholarly journals Cognitive prediction of obstacle's movement for reinforcement learning pedestrian interacting model

2022 ◽  
Vol 31 (1) ◽  
pp. 127-147
Author(s):  
Thanh-Trung Trinh ◽  
Masaomi Kimura
Keyword(s):  
Reinforcement Learning ◽  
Real Life ◽  
Complex Interaction ◽  
Cognitive Factors ◽  
Human Cognition ◽  
Human Likeness ◽  
Thinking Process ◽  
Path Lengths ◽  
Human Thinking ◽  
Pedestrian Simulation

Abstract Recent studies in pedestrian simulation have been able to construct a highly realistic navigation behaviour in many circumstances. However, when replicating the close interactions between pedestrians, the replicated behaviour is often unnatural and lacks human likeness. One of the possible reasons is that the current models often ignore the cognitive factors in the human thinking process. Another reason is that many models try to approach the problem by optimising certain objectives. On the other hand, in real life, humans do not always take the most optimised decisions, particularly when interacting with other people. To improve the navigation behaviour in this circumstance, we proposed a pedestrian interacting model using reinforcement learning. Additionally, a novel cognitive prediction model, inspired by the predictive system of human cognition, is also incorporated. This helps the pedestrian agent in our model to learn to interact and predict the movement in a similar practice as humans. In our experimental results, when compared to other models, the path taken by our model’s agent is not the most optimised in certain aspects like path lengths, time taken and collisions. However, our model is able to demonstrate a more natural and human-like navigation behaviour, particularly in complex interaction settings.

scholarly journals Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems

2021 ◽  
Author(s):  
Amarildo Likmeta ◽  
Alberto Maria Metelli ◽  
Giorgia Ramponi ◽  
Andrea Tirinzoni ◽  
Matteo Giuliani ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Real Life ◽  
User Preferences ◽  
Inverse Reinforcement Learning ◽  
Water Release ◽  
Reward Function ◽  
Model Free ◽  
Conflicting Objectives ◽  
Multiple Experts

AbstractIn real-world applications, inferring the intentions of expert agents (e.g., human operators) can be fundamental to understand how possibly conflicting objectives are managed, helping to interpret the demonstrated behavior. In this paper, we discuss how inverse reinforcement learning (IRL) can be employed to retrieve the reward function implicitly optimized by expert agents acting in real applications. Scaling IRL to real-world cases has proved challenging as typically only a fixed dataset of demonstrations is available and further interactions with the environment are not allowed. For this reason, we resort to a class of truly batch model-free IRL algorithms and we present three application scenarios: (1) the high-level decision-making problem in the highway driving scenario, and (2) inferring the user preferences in a social network (Twitter), and (3) the management of the water release in the Como Lake. For each of these scenarios, we provide formalization, experiments and a discussion to interpret the obtained results.

scholarly journals Drone Deep Reinforcement Learning: A Review

Electronics ◽  
2021 ◽  
Vol 10 (9) ◽  
pp. 999
Author(s):  
Ahmad Taher Azar ◽  
Anis Koubaa ◽  
Nada Ali Mohamed ◽  
Habiba A. Ibrahim ◽  
Zahra Fathy Ibrahim ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Real Life ◽  
Environment Monitoring ◽  
Simulated Environments ◽  
Infrastructure Inspection ◽  
Remote Sensing Mapping ◽  
And Control ◽  
The Military ◽  
Uav Navigation

Unmanned Aerial Vehicles (UAVs) are increasingly being used in many challenging and diversified applications. These applications belong to the civilian and the military fields. To name a few; infrastructure inspection, traffic patrolling, remote sensing, mapping, surveillance, rescuing humans and animals, environment monitoring, and Intelligence, Surveillance, Target Acquisition, and Reconnaissance (ISTAR) operations. However, the use of UAVs in these applications needs a substantial level of autonomy. In other words, UAVs should have the ability to accomplish planned missions in unexpected situations without requiring human intervention. To ensure this level of autonomy, many artificial intelligence algorithms were designed. These algorithms targeted the guidance, navigation, and control (GNC) of UAVs. In this paper, we described the state of the art of one subset of these algorithms: the deep reinforcement learning (DRL) techniques. We made a detailed description of them, and we deduced the current limitations in this area. We noted that most of these DRL methods were designed to ensure stable and smooth UAV navigation by training computer-simulated environments. We realized that further research efforts are needed to address the challenges that restrain their deployment in real-life scenarios.

scholarly journals Comparison Between the Facial Flow Lines of Androids and Humans

2021 ◽  
Vol 8 ◽  
Author(s):  
Hisashi Ishihara ◽  
Saneyuki Iwanaga ◽  
Minoru Asada
Keyword(s):  
Three Dimensional ◽  
Real Life ◽  
Comparative Approach ◽  
Adult Males ◽  
Flow Lines ◽  
Deformation Features ◽  
Human Likeness ◽  
Upper Face ◽  
Android Robot ◽  
Main Deformation

The behavior of an android robot face is difficult to predict because of the complicated interactions between many and various attributes (size, weight, and shape) of system components. Therefore, the system behavior should be analyzed after these components are assembled to improve their performance. In this study, the three-dimensional displacement distributions for the facial surfaces of two android robots were measured for the analysis. The faces of three adult males were also analyzed for comparison. The visualized displacement distributions indicated that the androids lacked two main deformation features observed in the human upper face: curved flow lines and surface undulation, where the upstream areas of the flow lines elevate. These features potentially characterize the human-likeness. These findings suggest that innovative composite motion mechanisms to control both the flow lines and surface undulations are required to develop advanced androids capable of exhibiting more realistic facial expressions. Our comparative approach between androids and humans will improve androids’ impressions in future real-life application scenes, e.g., receptionists in hotels and banks, and clerks in shops.

scholarly journals Get A&Wdicted! di Restoran Khas Amerika: Pengaruh Cognitive Learning dan Message Reception and Processing Terhadap Perubahan Sikap Konsumen

Humaniora ◽  
2012 ◽  
Vol 3 (1) ◽  
pp. 145
Author(s):  
Elsye Rumondang Damanik
Keyword(s):  
Marketing Strategy ◽  
Cognitive Learning ◽  
Processing System ◽  
Message Processing ◽  
Literature Study ◽  
Cognitive Response ◽  
Thinking Process ◽  
Human Thinking ◽  
The Right ◽  
Message Reception

Article clarified a research on cognitive response effect on cognition, attitude, and purpose. The purpose of this study was to analyze the influence of cognitive learning and a set of message processing system to persuade consumers. Researcher obtained the data and information from literature study, media, and direct observation to A & W Restaurants located at Rawamangun, Kelapa Gading Mall, and Bina Nusantara University. The result shows that human thinking process relates to ego involvement which includes culture and living habit is influential to the way people process the message. Finally, it is concluded that it is important to understand how consumers do message processing in order to make marketers able to determine the right marketing strategy to influence their consumers’ attitudes. 

The complex interaction of cognitive factors in influencing time theft behaviors

2021 ◽  
Vol 2021 (1) ◽  
pp. 16078
Author(s):  
Chandrashekhar Lakshman ◽  
Kubilay Gok ◽  
Linh Chi Vo ◽  
John J. Sumanth
Keyword(s):  
Complex Interaction ◽  
Cognitive Factors ◽  
Time Theft

Cognition

2019 ◽  
pp. 7-22
Author(s):  
Cym Anthony Ryle
Keyword(s):  
Mental Models ◽  
Driving Force ◽  
Complex Interaction ◽  
Human Cognition ◽  
Stable Sets ◽  
Conscious Effort ◽  
The World

This chapter considers the fundamental characteristics of human cognition. It suggests that the capacity to make sense of the world involves a complex interaction between external realities and mental models. It considers that there are two complementary types of model—holistic representations, and models consisting of abstract componentsorganized in categories and hierarchies. It suggests that knowledge can be described as stable sets of models and their connections. It notes that reasoning is usually described as having two modes: Intuition operates rapidly and unconsciously; analysis requires sustained conscious effort. It argues that an absolute distinction between the two modes is artificial; intuition is usually the driving force, but effective reasoning depends on the synergy of both modes. It introduces the concept of bias and suggests that bias and intuition are inseparable.

scholarly journals A variable neighborhood search algorithm with reinforcement learning for a real-life periodic vehicle routing problem with time windows and open routes

2020 ◽  
Vol 54 (5) ◽  
pp. 1467-1494
Author(s):  
Binhui Chen ◽  
Rong Qu ◽  
Ruibin Bai ◽  
Wasakorn Laesanklang
Keyword(s):  
Reinforcement Learning ◽  
Large Scale ◽  
Search Algorithm ◽  
Real Life ◽  
Planning Horizon ◽  
Neighborhood Search ◽  
Variable Neighbourhood Search ◽  
Container Transportation ◽  
Solution Quality ◽  
Routing Problem

This paper studies a real-life container transportation problem with a wide planning horizon divided into multiple shifts. The trucks in this problem do not return to depot after every single shift but at the end of every two shifts. The mathematical model of the problem is first established, but it is unrealistic to solve this large scale problem with exact search methods. Thus, a Variable Neighbourhood Search algorithm with Reinforcement Learning (VNS-RLS) is thus developed. An urgency level-based insertion heuristic is proposed to construct the initial solution. Reinforcement learning is then used to guide the search in the local search improvement phase. Our study shows that the Sampling scheme in single solution-based algorithms does not significantly improve the solution quality but can greatly reduce the rate of infeasible solutions explored during the search. Compared to the exact search and the state-of-the-art algorithms, the proposed VNS-RLS produces promising results.

scholarly journals Sextual Intercourse: Considering Social–Cognitive Predictors and Subsequent Outcomes of Sexting Behavior in Adulthood

2019 ◽  
Vol 48 (8) ◽  
pp. 2367-2379 ◽  
Author(s):  
Zara P. Brodie ◽  
Claire Wilson ◽  
Graham G. Scott
Keyword(s):  
Sexual Satisfaction ◽  
Sexual Behaviors ◽  
Risky Sexual Behavior ◽  
Perceived Risk ◽  
Romantic Relationship ◽  
Differential Reinforcement ◽  
Social Cognitive ◽  
Real Life ◽  
Cognitive Factors ◽  
Context Specific

Abstract The purpose of this study was to identify specific social–cognitive factors that may influence the likelihood of engaging in sexting, and potential positive and negative outcomes of such behaviors, in adults. We asked 244 adult participants (64.5% women) to complete a set of online measures reflecting sexting engagement, social–cognitive factors (definitions, differential association, differential reinforcement, and imitation), and outcomes of sexting behavior (risky sexual behavior appraisal, sexual satisfaction, and relationship satisfaction). Results showed that 77.6% of our sample had sexted. Sexting in the context of a romantic relationship was predicted by differential reinforcement and friend imitation, while positive definitions of sexting alone predicted sexting someone outside the context of a romantic relationship. This indicates that motivations for sexting engagement may be context specific in adulthood. Those who had sexted demonstrated significantly higher sexual satisfaction than those who had never sexted. However, sexting outside of a romantic relationship predicted reduced perceived risk and heightened perceived benefit of engaging in real-life risky sexual behaviors. This suggests there may be both positive and negative implications of sexting engagement in adulthood.

Design thinking: breaking fixation for new relationships between organizations

2017 ◽  
Vol 38 (6) ◽  
pp. 20-30 ◽  
Author(s):  
Mark Lewis ◽  
Scott Hayward ◽  
Rob Hornyak
Keyword(s):  
Value Creation ◽  
Design Thinking ◽  
Single Case ◽  
Interorganizational Relationships ◽  
Real Life ◽  
Human Cognition ◽  
Social Implications ◽  
Brick Wall ◽  
Content Type

Purpose The purpose of this paper is to show how design thinking can be a useful approach for helping interorganizational partnerships create higher levels of value creation for both parties. By integrating concepts related to human cognition, contracts and performance, the authors show how interorganizational relationships often hit a brick wall. The authors show how they can break through such obstacles in a systematic way using design thinking. Design/methodology/approach The authors anchor their conceptual and prescriptive advice in a real-life case study between a large logistics company and a global technology firm. The case study was conducted over a multiyear period with many sources of data collected: interview data, observational, participant observation, archival presentations, etc. Findings The authors show the factors that lead to rigidity in interorganizational relationships over time, and the cycle of confirmation and exploitation that truly squeezes the life out of relationships if firms are not careful. They offer a prescriptive approach for addressing this issue that should be valuable for many firms across the globe. Research limitations/implications The study is based on a single-case study, so generalizability is always an issue. However, we think that most practicing managers who have been involved (in any way) with managing an interorganizational relationship will attest to the fact that they often experience the patterns that the authors illuminate in their study. Practical implications By applying the design thinking methodology within the context of interorganizational relationships, managers will help their firms break fixation and enter entirely new plateaus of value creation for both firms. Social implications The world of work occurs through partnerships and relationships, companies rarely “go it alone”. Thus, developing the capacities in managers to continuously assess relationship efficacy, break from inertia and discover new ways of creating value will lead to positive social implications. Additionally, the design thinking methodology is based on developing empathy for others, and the authors would argue that such capabilities are sorely needed in this world. Originality/value There is a lot of work on interorganizational partnerships, but an absence of help for practicing managers on how to make such relationships great. Grounded in a real-life case study, this paper provides practical contributions to those currently managing such relationships.

A Research Roadmap Toward a Holistic and Structured Top-Down Concept Selection Methodology

2008 ◽  
Author(s):  
Shun Takai
Keyword(s):  
Human Cognition ◽  
Evaluation Methodology ◽  
Concept Selection ◽  
Top Down ◽  
Evaluation Approach ◽  
System Concept ◽  
Concept Evaluation ◽  
System Components ◽  
Thinking Process ◽  
Selection Methodology

In the field of human cognition, thinking consists of problem-solving and decision-making. In cognitive thinking, top-down processing is an approach used by experts that enables them to solve problems and make decisions efficiently. This paper attempts to apply cognitive top-down thinking process to the concept evaluation of systems and their components. In the top-down concept evaluation approach, engineers first evaluate system concepts. Once a system concept is selected, engineers then identify system components (modules) that they can design independently for the chosen system concept. Engineers generate concepts for system modules and select one concept for each module. The objective of this paper is first to identify characteristics needed for a holistic and structured top-down concept evaluation methodology for a system and its components, and second to propose a research roadmap for establishing the proposed framework.

Sign in / Sign up

Export Citation Format

Share Document