Connecting Cognitive and Physical Worlds with Dynamic Cost Function Definition

AAAI Conferences

Our goal is to mesh the symbolic reasoning capabilities of a cognitive model with the constrained optimization possibilities inherent in optimal controls. We plan to develop and test such a system for several different dynamical models in environments of differing certainty and differing efficiency requirements.


A Practice Strategy for Robot Learning Control

Neural Information Processing Systems

The most general definition of Adaptive Control is one which includes any controller whose behavior changes in response to the controlled system's behavior. In practice, this definition is usually restricted to modifying a small number of controller parameters inorder to maintain system stability or global asymptotic stability of the errors during execution of a single trajectory (Sastry and Bodson 1989, for review). Learning Control represents a second level of operation, since it uses Adaptive Con-335 336 Sanger trol to modify parameters during repeated performance trials of a desired trajectory so that future trials result in greater accuracy (Arimoto et al. 1984). In this paper I present a third level called a "Practice Strategy", in which Learning Control is applied to a sequence of intermediate trajectories leading ultimately to the true desired trajectory. I claim that this can significantly increase learning speed and make learning possible for systems which would otherwise become unstable.



On the use of Hybrid Control for Legged Locomotion

AAAI Conferences

In this paper, we develop a hybrid control approach for legged locomotion. We motivate the development of the control architecture using the results of a series of walking, running and obstacle climbing experiments conducted using a six legged robot called HEX. Our initial simulation results indicate the potential stability of the control approach, and our future analytical work should provide the formal proof of these results. I. Introduction It is well known that legged locomotion involves the use of prototypical movements wherein the phase, frequency and amplitude of individual leg motions are related to one another in specific ways. In the literature, such movements are referred to as gaits.


Making Decisions about Motion

AAAI Conferences

There is often seen in the literature a disconnect between higher-level artificial intelligence and lower-level controls research. Too often, path planners do not account for the physical capabilities of the agents that will be following their paths. Similarly, the best controllers available need to be given trajectories from somewhere. This work presents a combined architecture that links a high-level cognitive model, which can handle symbolic information and make rational decisions using it, with a lower-level optimal controller for planning detailed robotic vehicle trajectories. The priorities of the cognitive model are passed to the controller in the form of a set of weights that vary the importance of terms in a cost functional. Using the calculus of variations, this cost functional is combined with the physical system dynamics and globally optimized, resulting in a full-state trajectory that is optimal with respect to the agent's strategic goals and physical capabilities.