David Franklin

Programming CHIP for the IJCAI-95 Robot Competition

The University of Chicagos robot, CHIP, is part of the Animate Agent Project, aimed at understanding the software architecture and knowledge representations needed to build a general-purpose robotic assistant. CHIPs strategy for the Office Cleanup event of the 1995 Robot Competition and Exhibition was to scan an entire area systematically and, as collectible objects were identified, pick them up and deposit them in the nearest appropriate receptacle. This article describes CHIP and its various systems and the ways in which these elements combined to produce an effective entry to the robot competition.

The intelligent classroom: providing competent assistance

In the software industry, designers are forever trying to “improve” their products by adding ever more features to them, producing bloated software systems that are capable of doing just about anything. However, these systems often make it increasingly difficult for their users to perform their tasks as they are forced to wade through a mess of unwanted features to find the few that they actually need. We believe that a fruitful area of research is in building intelligent systems for particular tasks and then having the systems actively try to assist their users in performing these tasks. Such a system knows the plans (and the problems associated with those plans) that their users are likely to pursue. These \textit{competent assistants} can use their expertise on their particular tasks to guide their users through their tasks, provide better help, or perhaps even volunteer to take over some part of the task. Such an assistive agent is able to helpful because, through its task knowledge, it is able to limit what it needs to consider in cooperating with its user. In this paper we look at the implementation of a competent assistant that functions in a physical domain. The Intelligent Classroom is a prototype automated lecture facility that serves as its own audio/visual assistant. We focus on the representations and algorithms to use task knowledge to produce cooperative behavior, arguing these techniques could easily to be extended for use in a wide range of domains (i.e. both physical and purely electronic domains).

Improving human computer interaction in a classroom environment using computer vision

In this paper we discuss our use of multi-modal input to improve human computer interaction. Specifically we look at the methods used in the Intelligent Classroom to combine multiple input modes, and examine in particular the visual input modes. The Classroom provides context that improves the functioning of the visual input modes. It also determines which visual input modes are needed when. We examine a number of visual input modes to see how they fit into the general scheme, and look at how the Classroom controls their operation.

Jabberwocky: you don't have to be a rocket scientist to change slides for a hydrogen combustion lecture

In designing Jabberwocky—a speech-based interface to Microsoft PowerPoint—we have tried to go beyond simple commands like “Next slide, please” and make a tool that aids speakers as they present and even learns as they rehearse their presentations. Jabberwocky looks at the contents of the slides, extracting key words and phrases and associating them with their places in the presentation. By listening for these phrases (and synonymous phrases derived using syntactic rules) Jabberwocky is able to follow along with the presentation, switching slides at the appropriate moments. In this paper, we discuss the implementation of this system—a component of our Intelligent Classroom project—and look at how we are using it.

Integrating range and object data for robot navigation

Most sensors used for robot navigation fall into one of two broad categories: range sensors that give approximate distances to obstacles, and object-based sensors that detect and locate objects of specific types. Each type of sensor does a good job of detecting certain kinds of obstacles, but fails to detect others. A robust robot navigation system must be able to integrate data from both sources. We present an implemented system that combines information from range and object-based sensors into a single representation that is used to reliably navigate a robot through an office environment. The high level nature of the representation allows easy integration of task-specific navigation constraints. Results are given demonstrating how the system is utilized on our mobile robot, \textsc{Chip}.