Human-machine collaborative systems: Intelligent virtual fixtures and space applications

摘要

Human-Machine Collaborative Systems (HMCSs) are able to sense human operator intent and provide contextappropriate assistance to improve performance in applications ranging from space exploration to minimally invasive surgery. The underlying technology in our HMCSs is the virtual fixture. Virtual fixtures are software-generated force and position signals applied to human operators in order to improve the safety, accuracy, and speed of robot-assisted manipulation tasks. They are effective and intuitive because they capitalize on both the accuracy of robotic systems and the intelligence of human operators. In this position paper, we describe our HMCS technology and its potential for application in operational tasks in space. I. HUMAN-MACHINE COLLABORATIVE SYSTEMS The goal of Human-Machine Collaborative Systems (HMCS) project is to investigate human-machine cooperative execution of tool-based manipulation activities. The motivation for collaborative systems is based on evidence suggesting that humans operating in collaboration with robotic mechanisms can take advantage of robotic speed and precision, but avoid the difficulties of full autonomy by retaining the human “in the loop” for essential decision making and/or physical guidance [14]. Our previous work on HMCS has aimed at microsurgery [3], minimally invasive surgery [1], cell manipulation [6] and several fine-scale manufacturing tasks [7], but the basic principles apply broadly in many domains. In this paper, we explore possible applications in space. Our approach to HMCS focuses on three inter-related problems: (1) Synthesis: developing systems tools necessary for describing and implementing HMCSs; (2) Modeling: given sensor traces of a human performing a task, segmenting those traces into logical task components and/or measuring the compatibility of a given HMCS structure to that sequence of components; and (3) Validation: measuring and evaluating HMCS performance. Figure 1 depicts the high-level structure of our HMCS framework, which includes three main components: the human, the augmentation system, and an observer. We assume that a user primarily manipulates the environment using the augmentation system, although unaided manipulation may This work is partially supported by National Science Foundation Grants #EEC-9731478 and #ITR-0205318. take place in some settings (dashed line). The user is able to visually observe the tool and surrounding environment, and directs an augmentation device using force and position commands. The system may also have access to endpoint force data, targeted visual data and other application-dependent sensors, e.g., intra-operative imaging. The role of the observer is to assess available sensor data (including haptic feedback from the user) and initiate, modify, or terminate various forms of assistance. Optional direct interaction between the observer and the user may also be used to convey information or otherwise synchronize their interaction. The basic notion of HMCS is clearly related to traditional teleoperation, although the goal in HMCS is not to “remotize” the operator [5] but rather to provide appropriate levels of operator assistance depending on context. At one extreme, shared control [4] can be viewed as an HMCS for manipulation tasks in which some degrees of freedom are controlled by machine and others by the human. At the other extreme, supervisory control [13] gives a more discrete, highlevel notion of human-machine interaction. Our notion of HMCS essentially incorporates both views, combining them with broader questions of modeling manipulation activities consisting of multiple steps and varying level of assistance, and validating those models against human performance data. Fig. 1. Structure of a Human-Machine Collaborative System. II. VIRTUAL FIXTURES An important component of our HMCS framework is the virtual fixture. Virtual fixtures are software-generated force and position signals applied to human operators via robotic