No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Extrapolation of the Opponent's Past Behaviors
... It was first applied in a factory scheduling problem (Brueckner, 2000). In (Parunak and Brueckner, 2006b) the polyagent approach is used to evolve a model of a group of soldiers and extrapolate its behavior into the future. Path planning for robotic vehicles. ...
Complex systems are present everywhere in our environment: internet, electricity distribution networks, transport networks. This systems have as characteristics: a large number of autonomous entities, dynamic structures, different time and space scales and emergent phenomena. This thesis work is centered on the problem of control of such systems. The problem is defined as the need to determine, based on a partial perception of the system state, which actions to execute in order to avoid or favor certain global states of the system. This problem comprises several difficult questions: how to evaluate the impact at the global level of actions applied at a global level, how to model the dynamics of an heterogeneous system (different behaviors issue of different levels of interactions), how to evaluate the quality of the estimations issue of the modeling of the system dynamics. We propose a control architecture based on an ``equation-free'' approach. We use a multi-agent model to evaluate the global impact of local control actions before applying the most pertinent set of actions. Associated to our architecture, an experimental platform has been developed to confront the basic ideas or the architecture within the context of simulated ``free-riding'' phenomenon in peer to peer file exchange networks. We have demonstrated that our approach allows to drive the system to a state where most peers share files, despite given initial conditions that are supposed to drive the system to a state where no peer shares. We have also executed experiments with different configurations of the architecture to identify the different means to improve the performance of the architecture
... Fusion algorithms of RAID are beyond the scope of this paper and are discussed elsewhere [4,11,12,13]. ...
We motivate and offer a formal definition of validation as it applies to information fusion systems. Common definitions of validation compare the actual state of the world with that derived by the fusion process. This definition conflates properties of the fusion system with properties of systems that intervene between the world and the fusion system. We propose an alternative definition where validation of an information fusion system references a standard fusion device, such as recognized human experts. We illustrate the approach by describing the validation process implemented in RAID, a program conducted by DARPA and focused on information fusion in adversarial, deceptive environments.
... In (Parunak and Brueckner, 2006b) the polyagent approach is used to evolve a model of a group of soldiers and extrapolate its behavior into the future. Path planning for robotic vehicles. ...
Complex systems are present everywhere in our environment: internet, electricity distribution networks, transport networks. This systems have as characteristics: a large number of autonomous entities, dynamic structures, different time and space scales and emergent phenomena. This thesis work is centered on the problem of control of such systems. The problem is defined as the need to determine, based on a partial perception of the system state, which actions to execute in order to avoid or favor certain global states of the system. This problem comprises several difficult questions: how to evaluate the impact at the global level of actions applied at a global level, how to model the dynamics of an heterogeneous system (different behaviors issue of different levels of interactions), how to evaluate the quality of the estimations issue of the modeling of the system dynamics. We propose a control architecture based on an " equation-free " approach. We use a multi-agent model to evaluate the global impact of local control actions before applying the most pertinent set of actions. Associated to our architecture, an experimental platform has been developed to confront the basic ideas or the architecture within the context of simulated "free-riding" phenomenon in peer to peer file exchange networks. We have demonstrated that our approach allows to drive the system to a state where most peers share files, despite given initial conditions that are supposed to drive the system to a state where no peer shares. We have also executed experiments with different configurations of the architecture to identify the different means to improve the performance of the architecture.
... It thus estimates where units will want not to go. BEE [5] integrates the estimates of KIP and SAD with each unit's distinctive personality, style, and emotional condition [4] 5 shows how KIP predicts where a unit wants to go and what it wants to do, SAD warns about high-threat regions to avoid, and BEE integrates these with its own personality induction and emulation to yield high-quality predictions. ...
DARPA's Real-time Adversarial Intelligence and Decision-making (RAID) program [1] has demonstrated a promising new capability to predict enemy location and intent in dynamic urban combat environments. This capa-bility may significantly improve the Blue commander's decision processes by increasing his situational awareness and tactical team coordination capabilities. Experimental results obtained over the past two years indicate that a sin-gle commander in a simulated urban combat environment assisted by RAID outperforms a 5-person senior staff of military Subject Matter Experts. These results also indi-cate that RAID predictions and recommendations can im-prove the mission planning process by providing a previ-ously unavailable level of predictive analysis. This paper will address several team performance factors that are im-proved by RAID and their impact on the mission planning process, present results from the RAID Experiment 4 (July 2006), and describe a key technology extension that is needed for improving the real-time situational aware-ness data provided to RAID.
... The DARPA RAID program specifically focused on computational techniques of adversarial reasoning -estimating the current and upcoming actions of the opponent (80,81). Some of the algorithms developed in the program (73) are relatively inexpensive computationally and could be adapted to the limited CPUs available on small robots. In our secure-building problem case, the output of the algorithm would be the likely infiltration routes into and through the building. ...
While a number of excellent review articles on military robots have appeared in existing literature, this paper focuses on a distinct sub-space of related problems: small military robots organized into moderately sized squads, operating in a ground combat environment. Specifically, we consider the following: Command of practical small robots, comparable to current generation, small unmanned ground vehicles (e.g., Pac,Bots) with limited computing and sensor payload, as opposed to larger vehicle-sized robots or micro-scale robots; Utilization of moderately sized practical forces of 3-10 robots applicable to currently envisioned military ground operations; Complex three-dimensional physical environments, such as urban areas or mountainous terrains and the inherent difficulties they impose, including limited and variable fields of observation, difficult navigation, and intermittent communication; Adversarial environments where the active, intelligent enemy is the key consideration in determining the behavior of the robotic force; and Purposeful, partly autonomous, coordinated behaviors that are necessary for such a robotic force to survive and complete mission; these are far more complex than, for example, formation control or field coverage behavior.
... Fusion algorithms of RAID are beyond the scope of this paper and are discussed elsewhere [4,11,12,13]. ...
We motivate and offer a formal definition of validation as it applies to information fusion systems. Common definitions of validation compare the actual state of the world with that derived by the fusion process. This definition conflates properties of the fusion system with properties of systems that intervene between the world and the fusion system. We propose an alternative definition where validation of an information fusion system references a standard fusion device, such as recognized human experts. We illustrate the approach by describing the validation process implemented in RAID, a program conducted by DARPA and focused on information fusion in adversarial, deceptive environments.
... Indicators: Generated across levelsuseful for COA decisions [7,10] has been tested in multiple phases of the program and is an effective tool for predicting more general (non-IED) intents in urban terrain [9]. This technology incorporates historical data and knowledge bases on IED attacks, models of insurgent behavior, and models of blue courses of action and patrol behavior. ...
IEDs, made infamous in Iraq and Afghanistan, are a potential terrorist weapon anywhere in the world. Most counter-IED technologies are targeted at the point of the blast. DEFUSE can interdict and disrupt OPFOR activities left of the blast, well before planting and detonating the IED. The system integrates three layers of simulation: social, process, and environmental.
... However, this paper focuses on only one aspect of the RAID effort that falls into the Level-2 fusion area. Other aspects of the RAID program are discussed in [13,14,15]. It is important to stress the adversarial nature of this fusion process: the correctness of the fused output can be strongly impacted if the Red force intentionally distorts the input information. ...
The problem domain addressed in this work is urban, armed engagement against a guerilla force. The paper focuses particularly on the algorithm developed to combine incomplete and potentially deceptive observations of the opponent forces and actions into a fused estimate of the opponent’s actual positions and strengths. The algorithm generates and maintains a set of hypotheses, and evaluates each hypothesis in a manner that combines ongoing observations with recognition of the opponent’s efforts to conceal its forces and to deceive. The theoretical foundations of the proposed approach derive primarily from the theory of risk-sensitive control. The paper describes an implementation of the proposed approach that approximates theoretical constructs with heuristics for the sake of computational feasibility in applications that require near-real-time generation of fused estimates. Multiple realistic experiments, including live force experiments, demonstrated quantitatively that the resulting tools are capable of producing estimates at least comparable in accuracy to those produced by competent humans. The paper also discusses the potential incorporation of the tools into operational battle command systems.
While a number of excellent review articles on military robots have appeared in existing literature, this paper focuses on a distinct sub-space of related problems: small military robots organized into moderately sized squads, operating in a ground combat environment. Specifically, we consider the following: - Command of practical small robots, comparable to current generation, small unmanned ground vehicles (e.g., PackBots) with limited computing and sensor payload, as opposed to larger vehicle-sized robots or micro-scale robots; - Utilization of moderately sized practical forces of 3-10 robots applicable to currently envisioned military ground operations; - Complex three-dimensional physical environments, such as urban areas or mountainous terrains and the inherent difficulties they impose, including limited and variable fields of observation, difficult navigation, and intermittent communication; - Adversarial environments where the active, intelligent enemy is the key consideration in determining the behavior of the robotic force; and - Purposeful, partly autonomous, coordinated behaviors that are necessary for such a robotic force to survive and complete missions; these are far more complex than, for example, formation control or field coverage behavior.
Agent-based modeling is a powerful tool for systems modeling. Instantiating each domain entity with an agent permits us to capture many aspects of system dynamics and interactions that other modeling techniques do not support. However, the software agent representing an entity can execute only one trajectory in each run of the system, and so does not capture the alternative trajectories accessible to the entity in the evolution of any realistic system. Averaging over multiple runs still does not capture the range of individual interactions involved. We have addressed these problems with a new modeling entity, the polyagent, which represents each entity with a single persistent avatar supported by a swarm of transient ghosts. Each ghost interacts with the ghosts of all other avatars through digital pheromone fields, capturing a wide range of alternative trajectories in a single run of the system that can proceed faster than real time for many reasonable domains. We articulate this modeling concept, give examples from actual applications, and discuss directions for further research.
Emotion is an essential element of human behavior. Particularly in stressful situations such as combat, it is at least as important as rational analysis in determining a participant's behavior. DETT (Disposition, Emotion, Trigger, Tendency) is an environmentally mediated model of emotion that captures the essential features of the widely-used OCC (Ortony, Clore, Collins) model in a computationally tractable framework that can support large numbers of combatants. We motivate and describe this architecture, and report preliminary experiments that use it in simulating combat scenarios.
Agent-based modeling is a powerful tool for systems modeling. In- stantiating each domain entity with an agent captures many aspects of system dynamics and interactions that other modeling techniques do not. However, an entity's agent can execute only one trajectory per run, and does not sample the alternative trajectories accessible to the entity in the evolution of a realistic sys- tem. Averaging over multiple runs does not capture the range of individual in- teractions involved. We address these problems with a new modeling entity, the polyagent, which represents each entity with a single persistent avatar sup- ported by a swarm of transient ghosts. Each ghost interacts with the ghosts of other avatars through digital pheromone fields, capturing a wide range of alter- native trajectories in a single run that can proceed faster than real time.
1. Introduction The study of emotion Types of evidence for theories of emotion Some goals for a cognitive theory of emotion 2. Structure of the theory The organisation of emotion types Basic emotions Some implications of the emotions-as-valenced-reactions claim 3. The cognitive psychology of appraisal The appraisal structure Central intensity variables 4. The intensity of emotions Global variables Local variables Variable-values, variable-weights, and emotion thresholds 5. Reactions to events: I. The well-being emotions Loss emotions and fine-grained analyses The fortunes-of-others emotions Self-pity and related states 6. Reactions to events: II. The prospect-based emotions Shock and pleasant surprise Some interrelationships between prospect-based emotions Suspense, resignation, hopelessness, and other related states 7. Reactions to agents The attribution emotions Gratitude, anger, and some other compound emotions 8. Reactions to objects The attraction emotions Fine-grained analyses and emotion sequences 9. The boundaries of the theory Emotion words and cross-cultural issues Emotion experiences and unconscious emotions Coping and the function of emotions Computational tractability.
Hypergames are an emerging tool for combining decision theoretic and game theoretic information. We explain a new approach to the standard two-player zero-sum single-stage normal game that maximizes expected gain while quantifying possible loss. A DTGT agent can use this formulation to select a plan based on its assessment of an opponent's intent, its assessment of an opponent's unpredictability and its utility model of the situation.
Knowing a user's plans and goals can significantly improve the effectiveness of an interactive system. However, recognizing such goals and the user's intended plan for achieving them is not an easy task. Although much research has dealt with representing the knowledge necessary for plan inference and developing strategies that hypothesize the user's evolving plans, a number of serious problems still impede the use of plan recognition in large-scale, real-world applications. This paper describes the various approaches that have been taken to plan inference, along with techniques for dealing with ambiguity, robustness, and representation of requisite domain knowledge, and discusses areas for further research.
In many applied domains such as military operations, manufacturing, and logistics, entities change location under constraints. The centralized control mechanisms traditionally used for these problems can become bottlenecks and points of vulnerability. Multi-agent negotiation schemes enable the entities to maintain the desired constraints among themselves in decentralized fashion. This paper explores a particularly simple form of coordination that replaces central coordination and agentto -agent communication with interaction through a shared environment. Inspired by pheromones in insect populations, this method can solve the classical Missionaries and Cannibals problem. We illustrate how agents can be programmed to interact using synthetic pheromones, and evaluate the performance of our algorithms for four different levels of pheromone information and two different approaches to constructing the functions by which agents respond to the pheromones. Keywords Synthetic pheromones, commu...
Influences and reactions: a model of situated multiagent systems
- J Ferber
- P Müller
Digital pheromones for coordination of unmanned vehicles
- H V D Parunak
- S Brueckner
- J Sauter
- Ilachinski A.