Conference Paper

Decision making for multi-objective multi-agent search and rescue missions

Authors:
  • Dubai Futue Labs
To read the full-text of this research, you can request a copy directly from the authors.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Several multi-agent coordination approaches have been investigated with applications ranging from surveillance [1], [2] to formation flying [3], [4], rescue missions [5], wildlife monitoring and exploration [6], precision agriculture [7], cooperative payload transport [8], [9] and hazardous environment sensing [10]. Virtual structure (VS) is a centralized technique in which a group of agents, operating as particles of a virtual rigid body, preserve a strict geometric relationship to one another and a frame of reference [11], [12]. ...
... and J is the Jacobian matrix in (5). Therefore, ...
Preprint
Full-text available
This paper develops and experimentally evaluates a navigation function for quadrotor formation flight that is resilient to abrupt quadrotor failures and other obstacles. The navigation function is based on modeling healthy quadrotors as particles in an ideal fluid flow. We provide three key contributions: (i) A Containment Exclusion Mode (CEM) safety theorem and proof which guarantees safety and formally specifies a minimum safe distance between quadrotors in formation, (ii) A real-time, computationally efficient CEM navigation algorithm, (iii) Simulation and experimental algorithm validation. Simulations were first performed with a team of six virtual quadrotors to demonstrate velocity tracking via dynamic slide speed, maintaining sufficient inter-agent distances, and operating in real-time. Flight tests with a team of two custom quadrotors were performed in an indoor motion capture flight facility, successfully validating that the navigation algorithm can handle non-trivial bounded tracking errors while guaranteeing safety.
... Multi-agent coordination has been an active research area and has found many applications such as surveillance [1,2], formation flight [3,4], traffic coordination and control [5], rescue missions [6], and cooperative payload transport [7,8]. Cooperative control and group coordination offer robustness and resilience to failure and reduces mission cost. ...
... f i and g i are smooth functions, and x i , u i , and r i denote state, input, and output vectors, respectively, i.e. actual position of quadcopter i ∈ V is considered as the output vector. Every quadcopter i applies a feedback linearization control to track the local desired trajectory defined by (6). This ensures that the global desired trajectory, defined by affine transformation (3), is acquired in a decentralized fashion via local communication. ...
Article
This paper studies the problem of continuum deformation of a multi-quadcopter system (MQS) under time-varying communication weights. Quadcopters are treated as particles of a deformable body with time-varying parameters, where a desired n-D continuum deformation is planned based on the trajectories of n+1 leaders placed at the vertices of n-D simplex. The followers distributed inside the simplex acquire the desired continuum deformation by local communication with time varying communication weights, where stability and convergence of the MQS continuum deformation can be proven. This paper formally characterizes safety of the MQS continuum deformation by ensuring inter agent collision avoidance and followers containment. Therefore, a large-scale MQS can safely deform in an obstacle-laden environment with modest computational cost.
... In the above fog computing experimental environment, this paper compares the alarm time of vulnerability detection with that of the model-based vulnerability assessment method proposed in [6] and the attribute-based vulnerability assessment method proposed in [7] and analyses the impact of different methods on the alarm time of vulnerability detection. The faster the alarm time of vulnerability detection, and the earlier the security flaws can be found in the fog computing system [27]. Figure 8 shows the comparison results of various methods under the premise that the experimental environment and parameters are basically the same. ...
Article
Full-text available
In this paper, an invocation chain technology is used to test the security of fog computing systems. Atomic attacks based on the attack graph are combined according to the type, time sequence, and causal relationship. Different test sequences have gone through according to the principle of depth-first. In addition, the vulnerability assessment based on an invocation chain is evaluated to verify whether it can detect existing or unknown vulnerability in fog computing systems. Finally, the experimental results show that the invocation chain test and evaluation method based on the attack graph can evaluate the system risk quantitatively rather than qualitatively by calculating comprehensive probability on all test sequences.
Conference Paper
Full-text available
Many sequential decision-making problems require an agent to reason about both multiple objectives and uncertainty regarding the environment's state. Such problems can be naturally modelled as multi-objective partially observable Markov decision processes (MOPOMDPs). We propose optimistic linear support with alpha reuse (OLSAR), which computes a bounded approximation of the optimal solution set for all possible weightings of the objectives. The main idea is to solve a series of scalarized single-objective POMDPs, each corresponding to a different weighting of the objectives. A key insight underlying OLSAR is that the policies and value functions produced when solving scalarized POMDPs in earlier iterations can be reused to more quickly solve scalarized POMDPs in later iterations. We show experimentally that OLSAR outperforms, both in terms of runtime and approximation quality, alternative methods and a variant of OLSAR that does not leverage reuse.
Conference Paper
Full-text available
In May 2012, two major earthquakes occurred in the Emilia-Romagna region, Northern Italy, followed by further aftershocks and earthquakes in June 2012. This sequence of earthquakes and shocks caused multiple casualties, and widespread damage to numerous historical buildings in the region. The Italian National Fire Corps deployed disaster response and recovery of people and buildings. In June 2012, they requested the aid of the EU-funded project NIFTi, to assess damage to historical buildings, and cultural artifacts located therein. To this end, NIFTi deployed a team of humans and robots (UGV, UAV) in the red-area of Mirandola, Emilia-Romagna, from Tuesday July 24 until Friday July 27, 2012. The team worked closely together with the members of the Italian National Fire Corps involved in the red area. This paper describes the deployment, and experience.
Article
Full-text available
Robotic systems are today capable of performing patrolling and surveillance tasks in indoor structured environments. However, they need to be designed by taking into account the operational environment and the specific task to be accomplished. This dependency from the specific features of task and environment (contextual information, according to Turner [11]), severely restricts their practical deployment. In this paper, we address the creation of semantic maps for the effective deployment of surveillance robot in an a priori unknown indoor scenario. More specifically, we propose an architecture based on multimodal human-robot interaction that allows the user to specify in a natural way, knowledge about the environment that is represented in a semantic map. Given the acquired knowledge, the robot is then capable to plan and execute an effective patrolling of the scenario.
Article
Full-text available
There is an increasing amount of research into the area of pervasive computing, smart homes and intelligent spaces, one example being that of the DTI-funded Pervasive Home Environment Networking (PHEN) project. Much of the current research focuses on environments populated by numerous computing devices, sensors, actuators, various wired and wireless networking systems and poses the question of how such computing environments might become intelligent? Often, the proposed solution is to explicitly preprogram in the intelligence. In this paper we discuss a solution based on embedded-agents which enables emergent intelligent behaviour by predominantly implicit processes. We describe an experimental test-bed for pervasive computing, the iDorm, and report on experiments that scope the agent-learning characteristics in such environments. We also introduce a more human-directed approach to programming in pervasive environments which we refer to as task-oriented programming (TOP).
Conference Paper
Full-text available
Plans and decisions in many real-world scenarios are made under uncertainty and to satisfy multiple, possibly conflicting, objectives. In this work, we contribute the multi-reward partially-observable Markov decision process (MR-POMDP) as a general modelling framework. To solve MR-POMDPs, we present two hybrid (memetic) multi-objective evolutionary algorithms that generate non-dominated sets of policies (in the form of stochastic finite state controllers). Performance comparisons between the methods on multi-objective problems in robotics (with 2, 3 and 5 objectives), web-advertising (with 3, 4 and 5 objectives) and infectious disease control (with 3 objectives), revealed that memetic variants outperformed their original counterparts. We anticipate that the MR-POMDP along with multi-objective evolutionary solvers will prove useful in a variety of theoretical and real-world applications.
Article
Sequential decision problems that involve multiple objectives are prevalent. Consider for example a driver of a semi-autonomous car who may want to optimize competing objectives such as travel time and the effort associated with manual driving. We introduce a rich model called Lexicographic MDP (LMDP) and a corresponding planning algorithm called LVI that generalize previous work by allowing for conditional lexicographic preferences with slack. We analyze the convergence characteristics of LVI and establish its game theoretic properties. The performance of LVI in practice is tested within a realistic benchmark problem in the domain of semi-autonomous driving. Finally, we demonstrate how GPU-based optimization can improve the scalability of LVI and other value iteration algorithms for MDPs.
Conference Paper
One popular approach to active perception is using POMDPs to maximize rewards received for sensing actions towards task accomplishment and/or continually refining the agent's knowledge. Multiple types of reward functions have been proposed to achieve these goals: (1) state-based rewards which minimize sensing costs and maximize task rewards, (2) belief-based rewards which maximize belief state improvement, and (3) hybrid rewards combining the other two types. However, little attention has been paid to understanding the differences between these function types and their impact on agent sensing and task performance. In this paper, we begin to address this deficiency by providing (1) an intuitive comparison of the strengths and weaknesses of the various function types, and (2) an empirical evaluation of our comparison in a simulated active perception environment.
Article
This paper studies active perception in an urban sce- nario, focusing on the cooperation between a set of surveillance cameras and mobile robots. The fixed cameras provide a global but incomplete and possi- bly inaccurate view of the environment, which can be enhanced by a robot's local sensors. Active percep- tion means that the robot considers the effects of its actions on its sensory capabilities. In particular, it tries to improve its sensors' performance, for instance by pointing a pan-and-tilt camera. In this paper, we present a decision-theoretic approach to cooperative ac- tive perception, by formalizing the problem as a Par- tially Observable Markov Decision Process (POMDP). POMDPs provide an elegant way to model the interac- tion of an active sensor with its environment. The goal of this paper is to provide first steps towards an inte- grated decision-theoretic approach of cooperative active perception.
A roadmap for us robotics: From internet to robotics, 2013 edition
  • V Robotics
Fukushima robot operator writes tell-all blog
  • E Guizzo