Loading...
Citations
Altmetric:
Abstract
Autonomy in robot systems is a valuable attribute that remains an elusive goal. Noisy sensors, stochastic actions, and variation in unstructured environments all lead to unavoidable errors that can be inconsequential or catastrophic depending on the circumstances. Developing techniques capable of mitigating uncertainty at runtime has, therefore, been a significant and challenging focus of the robotics community. The primary contribution of this dissertation is the introduction of a new hierarchical belief space planning architecture to manage uncertainty and solve tasks using a uniform framework. Such an approach provides a means of creating autonomous systems that focus on salient subsets of state information, mitigate risk, and require less frequent intervention. Results indicate that it is possible to implement near optimal solutions to interesting problems in a uniform, hierarchical framework of belief space planners by taking actions that condense belief towards goal distributions. Example hierarchies are presented to address simple assembly problems and to enable robust long-term autonomous mobile manipulation in deployments lasting on the order of hours during which the robot executes hundreds of actions.
Type
dissertation
Date
2019-05