Autonomous humanlike robots that interact in natural language with people in real-time pose many design challenges, from the functional organization of the robotic architecture, to the computational infrastructure possibly employing middle-ware for distributed computing, to the hardware operating many specialized devices for sensory and effector processing in addition to embedded controllers and standard computational boards. The task is to achieve a functional integration of very diverse modules that operate at different temporal scales using different representations on parallel hardware in a reliable and fault-tolerant manner that allows for natural, believable human-robot interaction (HRI). To achieve reliable, natural interaction with humans, several challenging requirements must be met, two of which are (R1) appropriate interaction capabilities, including natural language capacity (speech recognition and speech production), dialog structure (knowledge about dialogs, teleological discourse, etc.), affect recognition and expression (both for speech as well as facial expressions), and mechanisms for nonverbal communication (via gestures, head movements, gaze, etc.); and (R2) mechanisms for ensuring robust interactions, including recovery from various communication failures (acoustic, syntactic, semantic misunderstandings, dialog failures, etc.) as well as software and hardware failure recovery (crashes of components, internal timing problems, faulty hardware, etc.). We are developing DIARC, a distributed integrated affect, reflection, cognition architecture for robots that interact naturally with humans (Scheutz et al. 2005; 2006). DIARC is a complete architecture that can be employed for HRI experiments without any modifications-robot behaviors can be expressed simply by virtue of scripts that contain general knowledge about conversations and action sequences. DI-ARC provides several features that are critical for the study of natural human interaction that are not easily found in other robotic systems. Some of these features are described below, and will be featured in the 2006 AAAI Robot Competition and Exhibition.
Scheutz, Matthias (Tufts University) | Briggs, Gordon (Tufts University) | Cantrell, Rehj (Indiana University) | Krause, Evan (Tufts University) | Williams, Thomas (Tufts University) | Veale, Richard (Indiana University)
Natural human-like human-robot interactions require many functional capabilities from a robot that have to be reflected in architectural components in the robotic control architecture. In particular, various mechanisms for producing social behaviors , goal-oriented cognition , and robust intelligence are required. In this paper, we present an overview of the most recent version of our DIARC architecture and show how several novel algorithms attempt to address these three areas, leading to more natural interactions with humans, while also extending the overall capability of the integrated system.
In this paper, we address the problem of communicating, interpreting,and executing complex yet abstract instructions to a robot teammember. This requires specifying the tasks in an unambiguous manner,translating them into operational procedures, and carrying outthose procedures in a persistent yet reactive manner. We reportour response to these issues, after which we demonstrate theircombined use in controlling a mobile robot in a multi-room officesetting on tasks similar to those in search-and-rescue operations.We conclude by discussing related research and suggesting directionsfor future work.
Many human social exchanges and coordinated activities critically involve dialogue interactions. Hence, we need to develop natural humanlike dialogue-processing mechanisms for future robots if they are to interact with humans in natural ways. In this article we discuss the challenges of designing such flexible dialoguebased robotic systems. We report results from data we collected in human interaction experiments in the context of a search task and show how we can use these results to build more flexible robotic architectures that are starting to address the challenges of task-based humanlike natural language dialogues on robots. As a result, the ability of future social and service robots to interact with humans in natural ways (Scheutz et al. 2007) will critically depend on developing capabilities of humanlike dialoguebased natural language processing (NLP) in robotic architectures.
Many human social exchanges and coordinated activities critically involve dialogue interactions. Hence, we need to develop natural humanlike dialogue processing mechanisms for future robots if they are to interact with humans in natural ways. In this article we discuss the challenges of designing such flexible dialogue-based robotic systems. We report results from data we collected in human interaction experiments in the context of a search task and show how we can use these results to build more flexible robotic architectures that are starting to address the challenges of task-based humanlike natural language dialogues on robots.