Various algorithms for optimization and learning in adaptive systems

This thesis discusses various methods for learning and optimization in adaptive systems. Overall, it emphasizes the relationship between optimization, learning, and adaptive systems; and it illustrates the influence of underlying hardware upon the construction of efficient algorithms for learning and optimization. Chapter 1 provides a summary and an overview.

Chapter 2 discusses a method for using feed-forward neural networks to filter the noise out of noise-corrupted signals. The networks use back-propagation learning, but they use it in a way that qualifies as unsupervised learning. The networks adapt based only on the raw input data-there are no external teachers providing information on correct operation during training. The chapter contains an analysis of the learning and develops a simple expression that, based only on the geometry of the network, predicts performance.

Chapter 3 explains a simple model of the piriform cortex, an area in the brain involved in the processing of olfactory information. The model was used to explore the possible effect of acetylcholine on learning and on odor classification. According to the model, the piriform cortex can classify odors better when acetylcholine is present during learning but not present during recall. This is interesting since it suggests that learning and recall might be separate neurochemical modes (corresponding to whether or not acetylcholine is present). When acetylcholine is turned off at all times, even during learning, the model exhibits behavior somewhat similar to Alzheimer's disease, a disease associated with the degeneration of cells that distribute acetylcholine.

Chapters 4, 5, and 6 discuss algorithms appropriate for adaptive systems implemented entirely in analog hardware. The algorithms inject noise into the systems and correlate the noise with the outputs of the systems. This allows them to estimate gradients and to implement noisy versions of gradient descent, without having to calculate gradients explicitly. The methods require only noise generators, adders, multipliers, integrators, and differentiators; and the number of devices needed scales linearly with the number of adjustable parameters in the adaptive systems. With the exception of one global signal, the algorithms require only local information exchange.

Analog VLSI-based, neuromorphic sensorimotor systems: modeling the primate oculomotor system

Using neuromorphic analog VLSI techniques for modeling large neural systems has several advantages over software techniques. By designing massively-parallel analog circuit arrays which are ubiquitous in neural systems, analog VLSI models are extremely fast, particularly when local interactions are important in the computation. While analog VLSI circuits are not as flexible as software methods, the constraints posed by this approach are often very similar to the constraints faced by biological systems. As a result, these constraints can offer many insights into the solutions found by evolution. This dissertation describes a hardware modeling effort to mimic the primate oculomotor system which requires both fast sensory processing and fast motor control. A one-dimensional hardware model of the primate eye has been built which simulates the physical dynamics of the biological system. It is driven by analog VLSI circuits mimicking brainstem and cortical circuits that control eye movements. In this framework, a visually-triggered saccadic system is demonstrated which generates averaging saccades. In addition, an auditory localization system, based on the neural circuits of the barn owl, is used to trigger saccades to acoustic targets in parallel with visual targets. Two different types of learning are also demonstrated on the saccadic system using floating-gate technology allowing the non-volatile storage of analog parameters directly on the chip. Finally, a model of visual attention is used to select and track moving targets against textured backgrounds, driving both saccadic and smooth pursuit eye movements to maintain the image of the target in the center of the field of view. This system represents one of the few efforts in this field to integrate both neuromorphic sensory processing and motor control in a closed-loop fashion.

Learning and using taxonomies for visual and olfactory classification

Humans are able of distinguishing more than 5000 visual categories even in complex environments using a variety of different visual systems all working in tandem. We seem to be capable of distinguishing thousands of different odors as well. In the machine learning community, many commonly used multi-class classifiers do not scale well to such large numbers of categories. This thesis demonstrates a method of automatically creating application-specific taxonomies to aid in scaling classification algorithms to more than 100 cate- gories using both visual and olfactory data. The visual data consists of images collected online and pollen slides scanned under a microscope. The olfactory data was acquired by constructing a small portable sniffing apparatus which draws air over 10 carbon black polymer composite sensors. We investigate performance when classifying 256 visual categories, 8 or more species of pollen and 130 olfactory categories sampled from common household items and a standardized scratch-and-sniff test. Taxonomies are employed in a divide-and-conquer classification framework which improves classification time while allowing the end user to trade performance for specificity as needed. Before classification can even take place, the pollen counter and electronic nose must filter out a high volume of background “clutter” to detect the categories of interest. In the case of pollen this is done with an efficient cascade of classifiers that rule out most non-pollen before invoking slower multi-class classifiers. In the case of the electronic nose, much of the extraneous noise encountered in outdoor environments can be filtered using a sniffing strategy which preferentially samples the visensor response at frequencies that are relatively immune to background contributions from ambient water vapor. This combination of efficient background rejection with scalable classification algorithms is tested in detail for three separate projects: 1) the Caltech-256 Image Dataset, 2) the Caltech Automated Pollen Identification and Counting System (CAPICS) and 3) a portable electronic nose specially constructed for outdoor use.

Distributed optimization in power networks and general multi-agent systems

The dissertation studies the general area of complex networked systems that consist of interconnected and active heterogeneous components and usually operate in uncertain environments and with incomplete information. Problems associated with those systems are typically large-scale and computationally intractable, yet they are also very well-structured and have features that can be exploited by appropriate modeling and computational methods. The goal of this thesis is to develop foundational theories and tools to exploit those structures that can lead to computationally-efficient and distributed solutions, and apply them to improve systems operations and architecture.

Specifically, the thesis focuses on two concrete areas. The first one is to design distributed rules to manage distributed energy resources in the power network. The power network is undergoing a fundamental transformation. The future smart grid, especially on the distribution system, will be a large-scale network of distributed energy resources (DERs), each introducing random and rapid fluctuations in power supply, demand, voltage and frequency. These DERs provide a tremendous opportunity for sustainability, efficiency, and power reliability. However, there are daunting technical challenges in managing these DERs and optimizing their operation. The focus of this dissertation is to develop scalable, distributed, and real-time control and optimization to achieve system-wide efficiency, reliability, and robustness for the future power grid. In particular, we will present how to explore the power network structure to design efficient and distributed market and algorithms for the energy management. We will also show how to connect the algorithms with physical dynamics and existing control mechanisms for real-time control in power networks.

The second focus is to develop distributed optimization rules for general multi-agent engineering systems. A central goal in multiagent systems is to design local control laws for the individual agents to ensure that the emergent global behavior is desirable with respect to the given system level objective. Ideally, a system designer seeks to satisfy this goal while conditioning each agent’s control on the least amount of information possible. Our work focused on achieving this goal using the framework of game theory. In particular, we derived a systematic methodology for designing local agent objective functions that guarantees (i) an equivalence between the resulting game-theoretic equilibria and the system level design objective and (ii) that the resulting game possesses an inherent structure that can be exploited for distributed learning, e.g., potential games. The control design can then be completed by applying any distributed learning algorithm that guarantees convergence to the game-theoretic equilibrium. One main advantage of this game theoretic approach is that it provides a hierarchical decomposition between the decomposition of the systemic objective (game design) and the specific local decision rules (distributed learning algorithms). This decomposition provides the system designer with tremendous flexibility to meet the design objectives and constraints inherent in a broad class of multiagent systems. Furthermore, in many settings the resulting controllers will be inherently robust to a host of uncertainties including asynchronous clock rates, delays in information, and component failures.

Spinal cord injury therapy through active learning

Therapy employing epidural electrostimulation holds great potential for improving therapy for patients with spinal cord injury (SCI) (Harkema et al., 2011). Further promising results from combined therapies using electrostimulation have also been recently obtained (e.g., van den Brand et al., 2012). The devices being developed to deliver the stimulation are highly flexible, capable of delivering any individual stimulus among a combinatorially large set of stimuli (Gad et al., 2013). While this extreme flexibility is very useful for ensuring that the device can deliver an appropriate stimulus, the challenge of choosing good stimuli is quite substantial, even for expert human experimenters. To develop a fully implantable, autonomous device which can provide useful therapy, it is necessary to design an algorithmic method for choosing the stimulus parameters. Such a method can be used in a clinical setting, by caregivers who are not experts in the neurostimulator's use, and to allow the system to adapt autonomously between visits to the clinic. To create such an algorithm, this dissertation pursues the general class of active learning algorithms that includes Gaussian Process Upper Confidence Bound (GP-UCB, Srinivas et al., 2010), developing the Gaussian Process Batch Upper Confidence Bound (GP-BUCB, Desautels et al., 2012) and Gaussian Process Adaptive Upper Confidence Bound (GP-AUCB) algorithms. This dissertation develops new theoretical bounds for the performance of these and similar algorithms, empirically assesses these algorithms against a number of competitors in simulation, and applies a variant of the GP-BUCB algorithm in closed-loop to control SCI therapy via epidural electrostimulation in four live rats. The algorithm was tasked with maximizing the amplitude of evoked potentials in the rats' left tibialis anterior muscle. These experiments show that the algorithm is capable of directing these experiments sensibly, finding effective stimuli in all four animals. Further, in direct competition with an expert human experimenter, the algorithm produced superior performance in terms of average reward and comparable or superior performance in terms of maximum reward. These results indicate that variants of GP-BUCB may be suitable for autonomously directing SCI therapy.

Control of dynamical systems with temporal logic specifications

This thesis is motivated by safety-critical applications involving autonomous air, ground, and space vehicles carrying out complex tasks in uncertain and adversarial environments. We use temporal logic as a language to formally specify complex tasks and system properties. Temporal logic specifications generalize the classical notions of stability and reachability that are studied in the control and hybrid systems communities. Given a system model and a formal task specification, the goal is to automatically synthesize a control policy for the system that ensures that the system satisfies the specification. This thesis presents novel control policy synthesis algorithms for optimal and robust control of dynamical systems with temporal logic specifications. Furthermore, it introduces algorithms that are efficient and extend to high-dimensional dynamical systems.

The first contribution of this thesis is the generalization of a classical linear temporal logic (LTL) control synthesis approach to optimal and robust control. We show how we can extend automata-based synthesis techniques for discrete abstractions of dynamical systems to create optimal and robust controllers that are guaranteed to satisfy an LTL specification. Such optimal and robust controllers can be computed at little extra computational cost compared to computing a feasible controller.

The second contribution of this thesis addresses the scalability of control synthesis with LTL specifications. A major limitation of the standard automaton-based approach for control with LTL specifications is that the automaton might be doubly-exponential in the size of the LTL specification. We introduce a fragment of LTL for which one can compute feasible control policies in time polynomial in the size of the system and specification. Additionally, we show how to compute optimal control policies for a variety of cost functions, and identify interesting cases when this can be done in polynomial time. These techniques are particularly relevant for online control, as one can guarantee that a feasible solution can be found quickly, and then iteratively improve on the quality as time permits.

The final contribution of this thesis is a set of algorithms for computing feasible trajectories for high-dimensional, nonlinear systems with LTL specifications. These algorithms avoid a potentially computationally-expensive process of computing a discrete abstraction, and instead compute directly on the system's continuous state space. The first method uses an automaton representing the specification to directly encode a series of constrained-reachability subproblems, which can be solved in a modular fashion by using standard techniques. The second method encodes an LTL formula as mixed-integer linear programming constraints on the dynamical system. We demonstrate these approaches with numerical experiments on temporal logic motion planning problems with high-dimensional (10+ states) continuous systems.

Formal methods for control synthesis in partially observed environments : application to autonomous robotic manipulation

Modern robots are increasingly expected to function in uncertain and dynamically challenging environments, often in proximity with humans. In addition, wide scale adoption of robots requires on-the-fly adaptability of software for diverse application. These requirements strongly suggest the need to adopt formal representations of high level goals and safety specifications, especially as temporal logic formulas. This approach allows for the use of formal verification techniques for controller synthesis that can give guarantees for safety and performance. Robots operating in unstructured environments also face limited sensing capability. Correctly inferring a robot's progress toward high level goal can be challenging.

This thesis develops new algorithms for synthesizing discrete controllers in partially known environments under specifications represented as linear temporal logic (LTL) formulas. It is inspired by recent developments in finite abstraction techniques for hybrid systems and motion planning problems. The robot and its environment is assumed to have a finite abstraction as a Partially Observable Markov Decision Process (POMDP), which is a powerful model class capable of representing a wide variety of problems. However, synthesizing controllers that satisfy LTL goals over POMDPs is a challenging problem which has received only limited attention.

This thesis proposes tractable, approximate algorithms for the control synthesis problem using Finite State Controllers (FSCs). The use of FSCs to control finite POMDPs allows for the closed system to be analyzed as finite global Markov chain. The thesis explicitly shows how transient and steady state behavior of the global Markov chains can be related to two different criteria with respect to satisfaction of LTL formulas. First, the maximization of the probability of LTL satisfaction is related to an optimization problem over a parametrization of the FSC. Analytic computation of gradients are derived which allows the use of first order optimization techniques.

The second criterion encourages rapid and frequent visits to a restricted set of states over infinite executions. It is formulated as a constrained optimization problem with a discounted long term reward objective by the novel utilization of a fundamental equation for Markov chains - the Poisson equation. A new constrained policy iteration technique is proposed to solve the resulting dynamic program, which also provides a way to escape local maxima.

The algorithms proposed in the thesis are applied to the task planning and execution challenges faced during the DARPA Autonomous Robotic Manipulation - Software challenge.