The Essential Dynamics Algorithm: Essential Results

This paper presents a novel algorithm for learning in a class of stochastic Markov decision processes (MDPs) with continuous state and action spaces that trades speed for accuracy. A transform of the stochastic MDP into a deterministic one is presented which captures the essence of the original dynamics, in a sense made precise. In this transformed MDP, the calculation of values is greatly simplified. The online algorithm estimates the model of the transformed MDP and simultaneously does policy search against it. Bounds on the error of this approximation are proven, and experimental results in a bicycle riding domain are presented. The algorithm learns near optimal policies in orders of magnitude fewer interactions with the stochastic MDP, using less domain knowledge. All code used in the experiments is available on the project's web site.

Series Elastic Actuators

This thesis presents the design, construction, control and evaluation of a novel force controlled actuator. Traditional force controlled actuators are designed from the premise that "Stiffer is better''. This approach gives a high bandwidth system, prone to problems of contact instability, noise, and low power density. The actuator presented in this thesis is designed from the premise that "Stiffness isn't everything". The actuator, which incorporates a series elastic element, trades off achievable bandwidth for gains in stable, low noise force control, and protection against shock loads. This thesis reviews related work in robot force control, presents theoretical descriptions of the control and expected performance from a series elastic actuator, and describes the design of a test actuator constructed to gather performance data. Finally the performance of the system is evaluated by comparing the performance data to theoretical predictions.