Daniel W. Palmer

Multi-agent control algorithms for chemical cloud detection and mapping using unmanned air vehicles

Traditional control approaches fall well short of the necessary flexibility and efficiency needed to meet the commercial and military demands placed upon UAV swarms. Effective coordination of these swarms requires development of control strategies based on emergent behavior. We have developed a rule-based, decentralized control algorithm that relies on constrained randomized behavior and respects UAV restrictions on sensors, computation, and flight envelope. To demonstrate and evaluate the effectiveness of our approach, we have created a simulation of an air vehicle swarm searching for and mapping a chemical cloud within a patrolled region. We then consider several different detection and mapping strategies based on emergent behavior. We then establish an inverse linear relation between the size of the swarm and the time to detect the cloud, regardless of the size of the cloud. Further, we also show the size of the swarm has a linear relation with the successful detection of the cloud.

Decentralized cooperative auction for multiple agent task allocation using synchronized random number generators

A collection of agents, faced with multiple tasks to perform, must effectively map agents to tasks in order to perform the tasks quickly with limited wasted resources. We propose a decentralized control algorithm based on synchronized random number generators to enact a cooperative task auction among the agents. The algorithm finds probabilistically reasonable solutions in few rounds of bidding. Additionally, as the length of the auction increases, the expectation of a better solution increases. This algorithm is not intended to find the optimal solution; it finds a good solution with less computation and communication.

Exploring Mars Using a Group of Tumbleweed Rovers

Current Mars exploration and science is limited to orbiters and areas close to original rover landing sites. Most of the places of geological interest lay many kilometers outside of suitable landing sites. In-situ resources such as wind can enable rovers to travel great distances on Mars while using little internal power. In this paper, a dynamic model of an individual wind driven rover is used to enhance a stochastic simulation of multiple rovers traversing the Martian environment. The results from this simulation support the claim that a group of rovers equipped with minimal control mechanisms or internal energy sources can autonomously disperse and explore Mars.

Fuel optimal maneuvers for multiple spacecraft formation reconfiguration using multi-agent optimization

Generation of fuel optimal maneuvers for spacecraft formation reconfiguration is modeled and analyzed as a multi-agent optimal control problem. Multi-agent optimal control is quite different from the traditional optimal control for single agent. Specifically, in addition to fuel optimization for a single agent, multi-agent optimal control necessitates consideration of task assignment among agents for terminal targets in the optimization process. We develop an efficient hybrid optimization algorithm to address such a problem. Simulation results illustrate the efficacy of the proposed algorithm.

An aspect-oriented approach for modeling self-organizing emergent structures

Multi-agent systems must be engineered to ensure that desirable system-level properties will consistently emerge from the complex interactions of the underlying agents, while also guaranteeing that undesirable behavior will be suppressed. We present an Aspect-Oriented Programming (AOP) framework for modeling, visualizing and manipulating emergent structure in multi-agent systems. By encapsulating the macroscopic structure, we can identify undesirable patterns of behavior at a higher level of abstraction. The identification of such patterns allows us to implement a feedback loop to steer the behavior of the lower level agents towards actions favorable for the emergence of a reliable solution. AOP facilitates the modeling of the system-wide behavior, thus it serves as a valuable tool for building confidence that a given multi-agent system will consistently meet its requirements.

Emergent Diagnoses from a Collective of Radiologists: Algorithmic versus Social Consensus Strategies

Twelve radiologists independently diagnosed 74 medical images. We use two approaches to combine their diagnoses: a collective algorithmic strategy and a social consensus strategy using swarm techniques. The algorithmic strategy uses weighted averages and a geometric approach to automatically produce an aggregate diagnosis. The social consensus strategy used visual cues to quickly impart the essence of the diagnoses to the radiologists as they produced an emergent diagnosis. Both strategies provide access to additional useful information from the original diagnoses. The mean number of correct diagnoses from the radiologists was 50 and the best was 60. The algorithmic strategy produced 63 correct diagnoses and the social consensus produced 67. The algorithm’s accuracy in distinguishing normal vs. abnormal patients (0.919) was significantly higher than the radiologists’ mean accuracy (0.861; p = 0.047). The social consensus’ accuracy (0.951; p = 0.007) showed further improvement.

Emergence-Oriented Programming

In this paper we describe emergence-oriented programming (EOP), a novel, human-centric technique to engineer swarm algorithms at a higher level of complexity than those developed with simple reactive agents. The process is iterative, building modules of behavior that can be layered to produce solutions that converge faster than reactive swarms to the desired emergent goal. The layers are modular and can be independently applied, mirroring the arbitrarily nested cognitive model proposed by Baas and Emmeche. The layers are produced by external observers recognizing and reinforcing patterns within swarms that are not visible at lower levels. Each layer builds upon the previous one leading to emergence, but the entire hierarchy can be mechanically collapsed into executable if-then rules based on robot primitives. We demonstrate portions of this technique to improve on the reactive swarm approach for solving the 4-color mapping problem

Human-swarm hybrids outperform both humans and swarms solving digital Jigsaw puzzles

We compare three approaches to solving digital jigsaw puzzles with wrap-around connections: human-only, swarm-only, and a hybrid approach that requires humans to interact with the swarm in a high-level, scalable manner. Using an iterative improvement strategy, some positive aspects of the human solvers migrate to the swarm-only approach. As the swarm-only approach gets better, humans continue to assist and the hybrid outperforms either of the independent approaches. This strategy for improving swarms is general, and continuously applicable. We show that even after many iterations and significant improvements to the swarm-only approach, support from a human improves the performance of the swarm.

Perceptualization of particle swarm optimization

Through visualization humans are able to perceive the efficiency of particle swarms with respect to several levels of applied inertia as well as the inclusion or exclusion of dampening. We also are able to find relationships between these levels, the diversity of a swarm, and the swarms efficiency in finding the minimum for five typical particle swarm optimization functions. This makes it possible to look at new areas of investigation to understand the connection between individual actions and emergent behavior. This paper demonstrates how to blend human intelligence, by using both their visual systems and their deductive reasoning with a swarms computational intelligence to produce results better than each could achieve independently.

Behavioral feedback as a catalyst for emergence in multi-agent systems

Swarm algorithms rely on randomness to produce solutions for complex problems. The random selection of actions and chance interactions of agents force a swarm to attempt many behavioral possibilities - reinforcing the productive ones and dampening the dead ends. Randomness however, is a dual-edged sword: it is necessary to insure a wide range of agent behavior, but also a source of inefficiency and wasted resources. Using behavioral feedback, we reinforce effective use of randomness - using it to select from a restricted list of useful actions. By observing an agents behavior over the three domains of time, space, or category, we establish a context for the application of randomness. The set of possible agent actions can be reduced to only those that are potentially beneficial. With this constraint, our results show we can dramatically improve performance and induce faster emergence from swarm algorithms using behavioral feedback