scholarly journals A Framework for Multi-Agent UAV Exploration and Target-Finding in GPS-Denied and Partially Observable Environments

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4739
Author(s):  
Ory Walker ◽  
Fernando Vanegas ◽  
Felipe Gonzalez
Keyword(s):  
Remote Sensing ◽  
Reinforcement Learning ◽  
Search Problem ◽  
Planning Problem ◽  
Planning And Control ◽  
Points Of Interest ◽  
Multi Agent ◽  
The Individual ◽  
Partially Observable ◽  
And Control

The problem of multi-agent remote sensing for the purposes of finding survivors or surveying points of interest in GPS-denied and partially observable environments remains a challenge. This paper presents a framework for multi-agent target-finding using a combination of online POMDP based planning and Deep Reinforcement Learning based control. The framework is implemented considering planning and control as two separate problems. The planning problem is defined as a decentralised multi-agent graph search problem and is solved using a modern online POMDP solver. The control problem is defined as a local continuous-environment exploration problem and is solved using modern Deep Reinforcement Learning techniques. The proposed framework combines the solution to both of these problems and testing shows that it enables multiple agents to find a target within large, simulated test environments in the presence of unknown obstacles and obstructions. The proposed approach could also be extended or adapted to a number of time sensitive remote-sensing problems, from searching for multiple survivors during a disaster to surveying points of interest in a hazardous environment by adjusting the individual model definitions.

scholarly journals Determinantal Reinforcement Learning

2019 ◽  
Vol 33 ◽  
pp. 4659-4666
Author(s):  
Takayuki Osogami ◽  
Rudy Raymond
Keyword(s):  
Reinforcement Learning ◽  
Value Function ◽  
Positive Semidefinite ◽  
Positive Semidefinite Matrix ◽  
The Matrix ◽  
Multi Agent ◽  
Action Value ◽  
The Individual ◽  
Partially Observable ◽  
Semidefinite Matrix

We study reinforcement learning for controlling multiple agents in a collaborative manner. In some of those tasks, it is insufficient for the individual agents to take relevant actions, but those actions should also have diversity. We propose the approach of using the determinant of a positive semidefinite matrix to approximate the action-value function in reinforcement learning, where we learn the matrix in a way that it represents the relevance and diversity of the actions. Experimental results show that the proposed approach allows the agents to learn a nearly optimal policy approximately ten times faster than baseline approaches in benchmark tasks of multi-agent reinforcement learning. The proposed approach is also shown to achieve the performance that cannot be achieved with conventional approaches in partially observable environment with exponentially large action space.

EVA 2.0: Emotional and rational multimodal argumentation between virtual agents

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Niklas Rach ◽  
Klaus Weber ◽  
Yuchi Yang ◽  
Stefan Ultes ◽  
Elisabeth André ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
User Feedback ◽  
Virtual Agents ◽  
Multi Agent System ◽  
Dialogue Game ◽  
Multi Agent ◽  
The Individual ◽  
Minimal Bias ◽  
Intuitive Interface ◽  
Emotional Level

Abstract Persuasive argumentation depends on multiple aspects, which include not only the content of the individual arguments, but also the way they are presented. The presentation of arguments is crucial – in particular in the context of dialogical argumentation. However, the effects of different discussion styles on the listener are hard to isolate in human dialogues. In order to demonstrate and investigate various styles of argumentation, we propose a multi-agent system in which different aspects of persuasion can be modelled and investigated separately. Our system utilizes argument structures extracted from text-based reviews for which a minimal bias of the user can be assumed. The persuasive dialogue is modelled as a dialogue game for argumentation that was motivated by the objective to enable both natural and flexible interactions between the agents. In order to support a comparison of factual against affective persuasion approaches, we implemented two fundamentally different strategies for both agents: The logical policy utilizes deep Reinforcement Learning in a multi-agent setup to optimize the strategy with respect to the game formalism and the available argument. In contrast, the emotional policy selects the next move in compliance with an agent emotion that is adapted to user feedback to persuade on an emotional level. The resulting interaction is presented to the user via virtual avatars and can be rated through an intuitive interface.

scholarly journals Towards a balancing safety against performance approach in human–robot co-manipulation for door-closing emergencies

2021 ◽  
Author(s):  
Chuande Liu ◽  
Chuang Yu ◽  
Bingtuan Gao ◽  
Syed Awais Ali Shah ◽  
Adriana Tapus
Keyword(s):  
Loop Control ◽  
Risk Levels ◽  
Human In The Loop ◽  
Planning And Control ◽  
Power Stations ◽  
Markov Decision ◽  
Partially Observable ◽  
And Control ◽  
Self Protection ◽  
Balance Mechanism

AbstractTelemanipulation in power stations commonly require robots first to open doors and then gain access to a new workspace. However, the opened doors can easily close by disturbances, interrupt the operations, and potentially lead to collision damages. Although existing telemanipulation is a highly efficient master–slave work pattern due to human-in-the-loop control, it is not trivial for a user to specify the optimal measures to guarantee safety. This paper investigates the safety-critical motion planning and control problem to balance robotic safety against manipulation performance during work emergencies. Based on a dynamic workspace released by door-closing, the interactions between the workspace and robot are analyzed using a partially observable Markov decision process, thereby making the balance mechanism executed as belief tree planning. To act the planning, apart from telemanipulation actions, we clarify other three safety-guaranteed actions: on guard, defense and escape for self-protection by estimating collision risk levels to trigger them. Besides, our experiments show that the proposed method is capable of determining multiple solutions for balancing robotic safety and work efficiency during telemanipulation tasks.

Benchmarking and Robust Multi-Agent-Based Production Planning and Control

2003 ◽  
Vol 36 (3) ◽  
pp. 249-254
Author(s):  
Daniel Frey ◽  
Jens Nimis ◽  
Heinz Wörn ◽  
Peter Lockemann
Keyword(s):  
Production Planning ◽  
Production Planning And Control ◽  
Agent Based ◽  
Planning And Control ◽  
Multi Agent ◽  
And Control

Eine bibliometrische Analyse/PPC and machine learning A bibliometric analysis

2020 ◽  
Vol 110 (04) ◽  
pp. 220-225
Author(s):  
Matthias Schmidt ◽  
Janine Tatjana Maier ◽  
Mark Grothkopp
Keyword(s):  
Machine Learning ◽  
State Of The Art ◽  
Dynamic Environment ◽  
Production Planning And Control ◽  
Manufacturing Companies ◽  
Comprehensive Review ◽  
Planning And Control ◽  
Individual Task ◽  
The Individual ◽  
And Control

Produzierende Unternehmen stehen in einem dynamischen Umfeld vor der Herausforderung eine zunehmende Datenmenge effizienter zu verarbeiten. In diesem Zusammenhang werden häufig Ansätze des maschinellen Lernens (ML) diskutiert. Der Beitrag stellt eine umfassende Aufarbeitung des Stands der Forschung bezogen auf den Einsatz von ML-Ansätzen in der Produktionsplanung und -steuerung (PPS) bereit. Daraus lässt sich der Forschungsbedarf in den einzelnen Aufgabengebieten der PPS ableiten.   In a dynamic environment, manufacturing companies face the challenge of processing an increasing amount of data more efficiently. In this context, approaches of machine learning (ML) are often discussed. This paper provides a comprehensive review of the state of the art regarding the use of ML approaches in production planning and control (PPC). Based on this, the need for research in the individual task areas of PPC can be derived.

scholarly journals Augmented Reality for Robotics: A Review

Robotics ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 21 ◽  
Author(s):  
Zhanat Makhataeva ◽  
Huseyin Varol
Keyword(s):  
Augmented Reality ◽  
Human Robot Interaction ◽  
Multi Agent Systems ◽  
Planning And Control ◽  
Robot Swarms ◽  
Wearable Robots ◽  
Camera Localization ◽  
Recent Developments ◽  
Multi Agent ◽  
And Control

Augmented reality (AR) is used to enhance the perception of the real world by integrating virtual objects to an image sequence acquired from various camera technologies. Numerous AR applications in robotics have been developed in recent years. The aim of this paper is to provide an overview of AR research in robotics during the five year period from 2015 to 2019. We classified these works in terms of application areas into four categories: (1) Medical robotics: Robot-Assisted surgery (RAS), prosthetics, rehabilitation, and training systems; (2) Motion planning and control: trajectory generation, robot programming, simulation, and manipulation; (3) Human-robot interaction (HRI): teleoperation, collaborative interfaces, wearable robots, haptic interfaces, brain-computer interfaces (BCIs), and gaming; (4) Multi-agent systems: use of visual feedback to remotely control drones, robot swarms, and robots with shared workspace. Recent developments in AR technology are discussed followed by the challenges met in AR due to issues of camera localization, environment mapping, and registration. We explore AR applications in terms of how AR was integrated and which improvements it introduced to corresponding fields of robotics. In addition, we summarize the major limitations of the presented applications in each category. Finally, we conclude our review with future directions of AR research in robotics. The survey covers over 100 research works published over the last five years.

ANALYTICAL REVIEW OF MULTI-AGENT REINFORCEMENT LEARNING PROBLEMS

2020 ◽  
pp. 48-56
Author(s):  
Yu. V. Dubenko
Keyword(s):  
Reinforcement Learning ◽  
Intelligent Agents ◽  
Russian Language ◽  
Learning Problems ◽  
Multi Agent Systems ◽  
Hierarchical Reinforcement Learning ◽  
Collective Interaction ◽  
Analytical Review ◽  
Multi Agent ◽  
Partially Observable

This paper is devoted to the problem of collective artificial intelligence in solving problems by intelligent agents in external environments. The environments may be: fully or partially observable, deterministic or stochastic, static or dynamic, discrete or continuous. The paper identifies problems of collective interaction of intelligent agents when they solve a class of tasks, which need to coordinate actions of agent group, e. g. task of exploring the territory of a complex infrastructure facility. It is revealed that the problem of reinforcement training in multi-agent systems is poorly presented in the press, especially in Russian-language publications. The article analyzes reinforcement learning, describes hierarchical reinforcement learning, presents basic methods to implement reinforcement learning. The concept of macro-action by agents integrated in groups is introduced. The main problems of intelligent agents collective interaction for problem solving (i. e. calculation of individual rewards for each agent; agent coordination issues; application of macro actions by agents integrated into groups; exchange of experience generated by various agents as part of solving a collective problem) are identified. The model of multi-agent reinforcement learning is described in details. The article describes problems of this approach building on existing solutions. Basic problems of multi-agent reinforcement learning are formulated in conclusion.

Planning and Control Processes Across the Life Span: An Overview

1993 ◽  
Vol 16 (2) ◽  
pp. 131-143 ◽  
Author(s):  
Margie E. Lachman ◽  
Orah R. Burack
Keyword(s):  
Life Span ◽  
Well Being ◽  
Special Issue ◽  
Control Processes ◽  
Planning And Control ◽  
Integrate Control ◽  
The Individual ◽  
And Control ◽  
Future Work

We present a brief overview of the areas of planning and control to provide a context for the individual papers in this special issue. For both topics we consider development across the life span, subgroup variations (e.g. by gender), and correlates (e.g. well-being). We then explore potential linkages between planning and control. Our attempt to integrate control and planning is meant to stimulate future work which considers these processes together from a life span perspective.

Sign in / Sign up

Export Citation Format

Share Document