Konstantinos Manousakis, Panayiotis Kolios and Georgios Ellinas (June 21st 2017). Multi-Period Attack-Aware Optical Network Planning under Demand Uncertainty, Optical Fiber and Wireless Communications, Rastislav Roka, IntechOpen, DOI: 10.5772/intechopen.68491. 

Ammar Mohammed, Ulrich Furbach and Frieder Stolzenburg (January 1st 2010). Multi-Robot Systems: Modeling, Specification, and Model Checking, Robot Soccer, Vladan Papi&#263;, IntechOpen, DOI: 10.5772/7349. 

Antonio Sgorbissa (December 1st 2006). Multi-Robot Systems and Distributed Intelligence: The ETHNOS Approach to Heterogeneity, Mobile Robotics, Moving Intelligence, Jonas Buchli, IntechOpen, DOI: 10.5772/4733. 

New Zealand

This paper presents a multi-robot long-term planning approach under uncertainty on the duration of tasks. The proposed method- ology takes advantage of generalized stochastic Petri nets to model multi-robot teams. It allows for unified modeling of action selection and uncertainty on duration of action execution. Goals are specified through the use of transition rewards and rewards per time unit. Our approach exploits the semantics provided by Markov reward automata in order to synthesize policies that optimize the long-run average reward. We provide an empirical evaluation on a simulated multi-robot monitoring problem, showing that the synthesized pol- icy outperforms a carefully hand-crafted policy.


AAMAS 2020

Long-Run Multi-Robot Planning With Uncertain Task Durations

AAMAS is the largest and most influential conference in the area of agents and multiagent systems, bringing together researchers and practitioners in all areas of agent technology and providing and internationally renowned high-profile forum for publishing and finding out about the latest developments in the field. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).  

![](https://assets.underline.io/uploads/markdown_image/1/image/ce4604bd54468a006164d16e080204fb.jpg)

Please click on the button below to register for this event.

If you are registered and see this page please check the account email you are logged in with. It must be the same as for the registration.

If you still have trouble accessing the contact please contact support at aamas2021@underline.io 

AAMAS 2021

technical paper

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). The aim of the joint conference is to provide a single, high-profile, internationally-respected archival forum for scientific research in the theory and practice of autonomous agents and multi-agent systems.

Browse keynotes, discussions, panels and over 300 presentations.


AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). 

Fair division of land is an important practical problem that is commonly handled either by hiring assessors or by selling and dividing the proceeds. A third way to divide land fairly is via algorithms for fair cake-cutting. However, the current theory of fair cake-cutting is
not yet ready to optimally share a plot of land and such algorithms are seldom used in practical land-division.
We attempt to narrow the gap between theory and practice by performing extensive simulations of a classic cake-cutting algorithm on real land-value data. We improve the practical performance of this algorithm using heuristics we developed, and show their effectiveness on real land-value maps compared to actual assessment and sale data on various performance metrics. The cake-cutting algorithms perform better in most metrics.
We further examined the cake cutting algorithm with respect to strategic gain of an agent relative to a truthful agent. The strategic gain was found to be insignificant effect in cake-cutting algorithms.


Fair Cake-Cutting Algorithms with Real Land-Value Data

To transition from control theory to real applications, it is important to study missions such as Swarm Search and Service (SSS) where vehicles are not only required to search an area, but also service all jobs that they find. In SSS missions each type of job requires a group of vehicles to break-off from the swarm for a given amount of time to successfully service it. The required number of vehicles and the service rate are unique to each job type. Once a job has been completed the vehicles are able to return to the swarm for use elsewhere. If not enough vehicles are present in the swarm at the time that the job is identified, that job is dropped without being serviced. In SSS missions that occur in open environments, the arrival rate of jobs varies dynamically as vehicles move in and out of the swarm to service jobs. Human operators as tasked with effectively planning and managing these complex missions. This paper presents a user study that seeks to test the efficacy and ease-of-use of a prediction model known as the Hybrid Model as an aid in planning and monitoring tasks. Results show that the novel computational model aid allows operators to more effectively choose the necessary swarm size to handle expected mission workload, as well as, maintain sufficient situation awareness to evaluate the performance of the swarm during missions.


Human-in-the-loop Planning and Monitoring of Swarm Search and Service Missions

Representing unknown and missing knowledge about the environment is fundamental to leverage robot behavior and improve its performance in completing a task. However, reconstructing spatial knowledge beyond the sensory horizon of the robot is an extremely
challenging task. Existing approaches assume that the environment static and features repetitive patterns (e.g. rectangular rooms) or that it can be all generalized with pre-trained models. Our goal is to remove such assumptions and to introduce a novel methodology that allows the robot to represent unknown spatial knowledge in dynamic and unstructured environments. To this end, we exploit generative learning to (1) learn a distribution of spatial landmarks observed during the robot mission and to (2) generate missing in- formation in real-time. The proposed approach aims at supporting planning and decision-making processes needed for robot behaviors. In this paper, we describe architecture modeling the proposed approach and a first validation on a mobile platform.

GUESs: Generative Modeling of Unknown Environments and Spatial Abstraction for robots

In participatory budgeting, citizens can take part in the decision on which projects a city should spend money. Formally, the input is a set of items, each having a certain cost, while agents can express their preferences. The task is to choose a set of items respecting a given bound. Recently Talmon and Faliszewski introduced a framework for budgeting based on approval votes. This paper revisits the introduced methods axiomatically from an irresolute point of view, especially showing that two of the proposed methods coincide. The study is complemented by approximation results.


Irresolute Approval-based Budgeting

When an AI system interacts with multiple users, it frequently needs to make allocation decisions. For instance, a virtual agent decides whom to pay attention to in a group setting, or a factory robot selects a worker to deliver a part. Demonstrating fairness in decision making is essential for such systems to be broadly accepted. We introduce a Multi-Armed Bandit algorithm with fairness constraints, where fairness is defined as a minimum rate that a task or a resource is assigned to a user. The proposed algorithm uses contextual information about the users and the task and makes no assumptions on how the losses capturing the performance of different users are generated. We provide theoretical guarantees of performance and an online user study. We view this as an exciting step towards including fairness constraints in resource allocation decisions.


The Fair Contextual Multi-Armed Bandit

Reinforcement learning under partial observability poses two types of conceptually orthogonal learning challenges; learning a useful representation
of the observable past, and selecting actions based on that representation. While the latter is common to both fully and partially observable control
problems, the former is idiomatic to the partially observable case. Traditional reinforcement learning relies exclusively on the reward signal to train the
representation model, but rewards constitute a weak learning signal in partially observable settings. To help train richer representations, we discuss
and propose an auxiliary self-supervised learning task designed to help the primary reinforcement learning task. We further propose two training schemes
for training with auxiliary tasks, one inspired by the idea of promoting complementary representations. Empirical evaluations show that agents which
exploit auxiliary tasks and complementary representations learn better policies, and converge faster, compared to agents which use common reactive and
recurrent representations trained on the rewards alone.

Learning Complementary Representations of the Past using Auxiliary Tasks in Partially Observable Reinforcement Learning

We consider solving a cooperative multi-robot object manipulation task using reinforcement learning (RL). We propose two distributed multi-agent RL approaches: distributed approximate RL (DA-RL), where each agent applies Q-learning with individual reward functions; and game-theoretic RL (GT-RL), where the agents update their Q-values based on the Nash equilibrium of a bimatrix Q-value game. We validate the proposed approaches in the setting of cooperative object manipulation with two simulated robot arms. Although we focus on a small system of two agents in this paper, both DA-RL and GT-RL apply to general multi-agent systems, and are expected to scale well to large systems.

Distributed Reinforcement Learning for Cooperative Multi-Robot Object Manipulation

Auction mechanism generally requires a trusted-third party as the market mediator to coordinate bidding and resource allocation via collecting private data from the agents, which may arouse severe privacy concerns and high computation overheads. To address such issues, we propose a novel privacy-aware double auction framework (namely PANDA) by designing an efficient cryptographic protocol to privately execute double auction for divisible resources among all the agents. To ensure privacy and truthfulness, PANDA delicately co-designs VCG auction and cryptographic protocol, which is equivalent to a mediator for sealed-bid auction of divisible resources. 


PANDA: Privacy-Aware Double Auction for Divisible Resources without a Mediator

Autonomous driving promises to transform road transport. Multi-vehicle and multi-lane scenarios, however, present unique challenges due to constrained navigation and unpredictable vehicle interactions. Learning-based methods—such as deep reinforcement learning—are emerging as a promising approach to automatically design intelligent driving policies that can cope with these challenges. Yet, the process of safely learning multi-vehicle driving behaviours is hard: while collisions—and their near-avoidance—are essential to the learning process, directly executing immature policies on autonomous vehicles raises considerable safety concerns. In this article, we present a safe and efficient framework that enables the learning of driving policies for autonomous vehicles operating in a shared workspace, where the absence of collisions cannot be guaranteed. Key to our learning procedure is a sim2real approach that uses real-world online policy adaptation in a mixed reality setup, where other vehicles and static obstacles exist in the virtual domain. This allows us to perform safe learning by simulating (and learning from) collisions between the learning agent(s) and other objects in virtual reality. Our results demonstrate that, after only a few runs in mixed reality, collisions are significantly reduced.


Downloads

Next from AAMAS 2020

Fair Cake-Cutting Algorithms with Real Land-Value Data

Similar lecture

Mitigating Negative Side Effects via Environment Shaping

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAMAS 2020

Fair Cake-Cutting Algorithms with Real Land-Value Data

Similar lecture

Mitigating Negative Side Effects via Environment Shaping

Downloads