Teaching an Old Robot New Tricks: Learning Novel Tasks via Interaction with People and Things

As AI has begun to reach out beyond its symbolic, objectivist roots into the embodied, experientialist realm, many projects are exploring different aspects of creating machines which interact with and respond to the world as humans do. Techniques for visual processing, object recognition, emotional response, gesture production and recognition, etc., are necessary components of a complete humanoid robot. However, most projects invariably concentrate on developing a few of these individual components, neglecting the issue of how all of these pieces would eventually fit together. The focus of the work in this dissertation is on creating a framework into which such specific competencies can be embedded, in a way that they can interact with each other and build layers of new functionality. To be of any practical value, such a framework must satisfy the real-world constraints of functioning in real-time with noisy sensors and actuators. The humanoid robot Cog provides an unapologetically adequate platform from which to take on such a challenge. This work makes three contributions to embodied AI. First, it offers a general-purpose architecture for developing behavior-based systems distributed over networks of PC's. Second, it provides a motor-control system that simulates several biological features which impact the development of motor behavior. Third, it develops a framework for a system which enables a robot to learn new behaviors via interacting with itself and the outside world. A few basic functional modules are built into this framework, enough to demonstrate the robot learning some very simple behaviors taught by a human trainer. A primary motivation for this project is the notion that it is practically impossible to build an "intelligent" machine unless it is designed partly to build itself. This work is a proof-of-concept of such an approach to integrating multiple perceptual and motor systems into a complete learning agent.

Interaction and Intelligent Behavior

We introduce basic behaviors as primitives for control and learning in situated, embodied agents interacting in complex domains. We propose methods for selecting, formally specifying, algorithmically implementing, empirically evaluating, and combining behaviors from a basic set. We also introduce a general methodology for automatically constructing higher--level behaviors by learning to select from this set. Based on a formulation of reinforcement learning using conditions, behaviors, and shaped reinforcement, out approach makes behavior selection learnable in noisy, uncertain environments with stochastic dynamics. All described ideas are validated with groups of up to 20 mobile robots performing safe--wandering, following, aggregation, dispersion, homing, flocking, foraging, and learning to forage.

Assembly Guidance in Augmented Reality Environments Using a Virtual Interactive Tool

The application of augmented reality (AR) technology for assembly guidance is a novel approach in the traditional manufacturing domain. In this paper, we propose an AR approach for assembly guidance using a virtual interactive tool that is intuitive and easy to use. The virtual interactive tool, termed the Virtual Interaction Panel (VirIP), involves two tasks: the design of the VirIPs and the real-time tracking of an interaction pen using a Restricted Coulomb Energy (RCE) neural network. The VirIP includes virtual buttons, which have meaningful assembly information that can be activated by an interaction pen during the assembly process. A visual assembly tree structure (VATS) is used for information management and assembly instructions retrieval in this AR environment. VATS is a hierarchical tree structure that can be easily maintained via a visual interface. This paper describes a typical scenario for assembly guidance using VirIP and VATS. The main characteristic of the proposed AR system is the intuitive way in which an assembly operator can easily step through a pre-defined assembly plan/sequence without the need of any sensor schemes or markers attached on the assembly components.