$Id: cmu-ri-labgroup.daml, v 0.1 2001/01/20 13:41:24 dconst Exp $ Instances defined by the labgroup ontology, defined for HW3. Contact terry@acm.org for details. AML http://www.ri.cmu.edu/labs/lab_1.html http://www.cs.cmu.edu/afs/cs.cmu.edu/project/chimera/www/aml.html The goal of research in the AML is to develop the enabling technologies for "Rapidly Deployable Systems" through composition (using hardware and software building blocks) and collaboration (amongst autonomous hardware and software agents). Our vision of an intelligent system involves several specialized components (hardware or software) that can be rapidly composed to create a system and collaborate with each other to achieve the desired behavior. We are currently pursuing the research areas of Distributed Informations Systems, Distributed Robotics Systems, Distributed Design Systems, Intelligent Instruments, Sensor Based Robotics, and Reconfigurable Systems to meet the goal. Microdynamic Systems Lab http://www.ri.cmu.edu/labs/lab_10.html http://www.cs.cmu.edu/afs/cs/project/msl/www/msl_home.html In the Microdynamic Systems Laboratory we are exploring the limits of robotics in terms of speed, precision, dexterity and miniaturization. This endeavor requires development of new sensing, actuation, and control technologies for agile robotic systems that can be applied to a variety of real-world situations. Major themes of our work include moving toward robotics operating at or below the micrometer scale, simplifying robotic mechanisms while providing greater functionality through software, and providing new ways for humans to interact with the world through robotics. Examples include sensor-moderated coarse-fine manipulation, miniature factories for precision assembly, and magnetic levitation haptic interfaces that allow humans to interact with remote or simulated environments through the sense of touch. MEMS Lab http://www.ri.cmu.edu/labs/lab_11.html http://www.ece.cmu.edu/~mems/ Our research group designs, fabricates, and tests microdevices that are primarily made using a process in which conventional foundry CMOS is followed by simple micromachining steps. This process provides us with high-performance electronics integrated on chip with electrostatically actuated microstructures, capacitive and piezoresistive sensors, and polysilicon thermal heaters. Projects include micromechanisms for magnetic probe-based data storage, accelerometers and gyroscopes for inertial sensing, and ciliary sensors for tactile and acoustic imaging. Of particular interest is how large arrays of these sensors and actuators may improve overall system-level performance. Issues include system design and integration, distributed control and communication, and interfacing to the environment. MEMS are coupled multi-domain systems and, therefore, are difficult to design without expertise in a diverse set of fields. To address this problem, MEMS designers and CAD developers work closely together in a synergetic research environment in our lab. We are developing a multi-domain hierarchical design methodology to speed up the design cycle. A MEMS schematic is being developed in which mechanical, electromechanical, and electronic elements are graphically interconnected, resulting in rapid simulation and evaluation of designs. We are also modeling topologies for common MEMS applications, such as accelerometry, to codify design constraints for use in automated synthesis tools. Mobile Robot Lab http://www.ri.cmu.edu/labs/lab_12.html http://www.frc.ri.cmu.edu/mrl The Mobile Robot Laboratory is engaged in long-term basic research in perception, control and planning for robots that navigate through complex indoor and outdoor spaces. Since 1981, building on work conducted at Stanford University since 1973, the lab has built three dissimilar mobile robots (Pluto, Neptune and Uranus) and demonstrated new methods that allow them to map and navigate cluttered surroundings by stereo and monocular vision, by broad beam sonar, scanning laser rangefinder and other sensors. The two decades of experience have given us the means and confidence to develop a mobile robot control program with enough spatial competence to reliably execute tasks like delivery and floor care in normal areas, with no special navigational aids and trained only by an initial run through. Our current efforts may result in a laboratory prototype of the first mobile robots with mass market potential. Our approach accumulates sensed evidence about surrounding geometry in a spatial grid. We plan to integrate about ten thousand 3D location estimates from multi-baseline stereo vision several times per meter traveled. Preliminary, but very efficient, implementations of stereo and 3D grid algorithms suggest that 100 to 1000 MIPS of computer power will suffice to safely guide walking-speed robots through normal indoors. This amount of computing power will be inexpensive by the end of the decade, and we anticipate the widespread use of freely roaming robots shortly thereafter. Parallel Computer Vision Lab http://www.ri.cmu.edu/labs/lab_13.html http://www.cs.cmu.edu/afs/cs.cmu.edu/user/webb/html/pcv.html Current Work Managing large data structures. We are studing how algorithms that manipulate large data structures can be mapped efficiently onto a distribute memory parallel computer. Real-time stereo vision. We have implemented the fastest stereo vision system ever demonstrated. It uses Kanade-Okutomi multi-baseline stereo and operates at 15 Hz on a 64-cell iWarp, turning three 240x256 input images into a 240x256x16 depth image. This system was recently demonstrated at Supercomputing '93. RML http://www.ri.cmu.edu/labs/lab_14.html http://www.cs.cmu.edu/afs/cs/project/imw/www/RML/ Our research involves the design and implementation of flexible machines, mechanical hardware, electronics, control and software. The goal is customizing, which is now in great demand. The new machine tool industry will allow corporations to respond to the ever changing patterns of world trade. The new manufacturing systems can analyze new products and automatically will produce near optimal plans for production. Adaptability is the key. The research comprises a series of projects implementing an Intelligent Bending Workstation: Bend Sequence Planner BendCad Modeler Fine Motion Planner Grasping Planner Motion Planner Stacking Planner Robotics Education Lab http://www.ri.cmu.edu/labs/lab_15.html http://www.cs.cmu.edu/~rel The Robotics Education Lab is a central resource to support courses and individual projects. Equipment includes manipulators, mobile robots, electronics and mechanical fabrication benches, Lego, a video editing workstation, machine vision systems and more. Vision for Virtual Environments http://www.ri.cmu.edu/labs/lab_16.html http://www.cs.cmu.edu/afs/cs.cmu.edu/project/vision/www/VR/vr.html Using techniques from computer vision and robotics, we are developing novel sensing and display technologies to support practical, useful virtual environments. Video Surveillance and Monitoring http://www.ri.cmu.edu/labs/lab_17.html http://www.cs.cmu.edu/~vsam/ The VSAM lab is developing a state-of-the-art video surveillance system that coordinates a network of active sensors to seamlessly track multiple moving objects through a large, cluttered environment. Visualization and Intelligent Interfaces Group http://www.ri.cmu.edu/labs/lab_18.html http://www.cs.cmu.edu/~sage/ Our research has four themes. The first theme focuses on ways to help people design graphics to visualize and thus better understand information. We have been studying this problem in the context of SAGE (System for Automated Graphics and Explanation). SAGE enhances user-directed design by providing tools that: create the novel displays that users specify, complete partial specifications, retrieve previously created graphics based on their appearance and/or their data content, and design graphics completely autonomously when users request them. The second theme running through all our work is developing environments for data exploration. We aim to develop visual environments where users directly perceive and act upon information. We have developed a drag-and-drop information-centric paradigm, in which applications as discrete entities no longer appear. This paradigm is implemented in Visage (Very Integrated SAGE). The third theme has to do with interactive techniques, which all of our systems support in various ways. We are focusing on them most in the SDM (which stands for Selective Dynamic Manipulation) paradigm, which is implemented in a system of the same name. The SDM paradigm is based on physicalization, which has to do with creating "physical" graphical objects to represent abstract information objects. This paradigm gives users the ability to move and stretch the graphical objects, analogous to the manner in which users might manipulate physical models placed on a table. The fourth theme is automatic presentation. An automatic presentation system is an intelligent interface component which receives information from a user or application program and designs a combination of graphics and text that effectively conveys this information. SAGE has been one arena for us to test ideas in. We have automated caption generation to explain SAGE's automatically generated graphics. We are currently working on the automatic generation of full briefings in AutoBrief. The fifth theme is visual query environments (VQE). VQE is a Visual Query Environment for expressing queries involving navigation among multiple objects, aggregating these objects, and defining derived attributes for them. VLSI Computation Sensor Lab http://www.ri.cmu.edu/labs/lab_19.html http://www.cs.cmu.edu/~compsenslab The VLSI computational sensor lab designs and builds VLSI vision chips. The lab investigates new vision algorithms that map well onto silicon. CIL http://www.ri.cmu.edu/labs/lab_2.html http://www.cs.cmu.edu/afs/cs.cmu.edu/project/cil/ftp/html/cil.html A resource used by the CMU research community to obtain high quality images in a tightly controlled and yet flexible environment. A wide choice of lighting and video cameras including a cooled, very-low-noise photometrics camera are available. A six degree of freedom jig permits the cameras to be accurately positioned under computer control, and a rail and turntable permit control of an object's position. The lab has been used to study color, texture and illumination and the impact of these on computer vision tasks such as estimating surface orientation, object segmentation and physical model creation. It has also been used to calibrate cameras (an implementation of Tsai's calibration technique is available), and to take images of objects for stereo and 3D shape reconstruction. Helicopter Lab http://www.ri.cmu.edu/labs/lab_21.html http://www.cs.cmu.edu/afs/cs/project/chopper/www/ To develop a vision-guided robot helicopter which can autonomously carry out functions applicable to search and rescue, surveillance, law enforcement, inspection, mapping, and aerial cinematography, in any weather conditions and using only on-board intelligence and computing power. Task-Oriented Vision Lab http://www.ri.cmu.edu/labs/lab_23.html The Task-Oriented Vision Laboratory is investigating the theory of how the requirements for accomplishing a visual task determine the optimal architecture of a vision system: representations, selection of modules and control schemata. Traditionally, computer vision research has emphasized investigating each vision module in a general and isolated condition. Such research efforts often generate unrealistic solutions from ill-defined assumptions. In contrast, we consider a vision system as a whole and emphasize the research on interactions among modules as well as the research on each vision module. Computational Mechanics Laboratory http://www.ri.cmu.edu/labs/lab_24.html NavLab http://www.ri.cmu.edu/labs/lab_28.html http://www.cs.cmu.edu/afs/cs.cmu.edu/project/alv/member/www/navlab_home_page.html Project LISTEN http://www.ri.cmu.edu/labs/lab_29.html http://www.cs.cmu.edu/~listen Literacy/Language/Learning Innovation/Instruction that Speech Technology ENables Case Based Reasoning Lab http://www.ri.cmu.edu/labs/lab_3.html Robotic Sensor Based Planning Lab http://www.ri.cmu.edu/labs/lab_30.html My group's current work deals with on-line sensor based planning for highly articulated robots. These systems possess multiple degrees of freedom yielding agility far superior to that of conventional robots. This enables them to thread through tightly packed environments, such as collapsed buildings after a disaster. One type of highly articulated system is a serpentine or snake-like robot. Highly articulated robots are difficult to control because they have an unusually high number of degrees of freedom. In order to cope with these many degrees of freedom, my group is developing the underlying math that will enable the realistic implementation of highly articulated robots. The motion planning work for snake robots also applies to three-dimensional flying robots. In collaboration with scientists at the Johnson Space Center, we are developing motion planning for Aercam, soccer-ball sized space craft that will fly around the Space Shuttle and future Space Station to perform autonomous inspection. Once the paths are determined, we then optimize these paths for fuel usage, safety, and other user preferences. The highly articulated motion planning techniques are not limited to robotics. In collaboration with Professor William Messner, we are developing algorithms for a distributed array of cells where each cell can induce a directed force onto an object that rests on it. The collection of cells can transport and manipulate an object. Sensor based planning allows for the realistic deployment of highly articulated robots into unknown environments and into environments that are too difficult to model. We have already developed a provably correct incremental construction procedure that makes use of line of sight information to generate a representation of an unknown environment. The underlying math furnishes the strength to this method; we provide the mathematical guarantees that (in a perfect or simulated environment) the robot is guaranteed to "see" everything, which is important for applications such as search and rescue. We also perform research in coverage path planning. Coverage is the determination of a path that a robot must follow such that the robot passes over every point in the environment. One application of coverage path planning is robotic mine removal. Current de-mining robots are small, have little computational power and use simple rudimentary algorithms to find the mines. We are developing intelligent probabilistic approaches to guide a robot to search for mines and other unexploded munitions. Robot Learning Lab http://www.ri.cmu.edu/labs/lab_31.html http://www.cs.cmu.edu/~rll Our research focuses on making robots learn and making learning robots succeed in the real world. Research aspects range from theoretical considerations over algorithmic design to practical implementations and demonstrations. Machine Perception Laboratory http://www.ri.cmu.edu/labs/lab_32.html Mobile Robot Programming Lab http://www.ri.cmu.edu/labs/lab_33.html http://www.cs.cmu.edu/~illah/lab.html The Mobile Robot Programming Lab focuses on the Art of Robot Programming. The Lab's aim is the principled design of autonomous, deliberate systems that achieve real-world goals. We include both research projects studying robot programming and curriculum design projects for teaching robot programming at the secondary school level and beyond. Topics of interest in the lab include: formal representations of perception and action; learning and planning with incomplete information; interleaving planning and execution; mobile robot architectures; real-time visual obstacle avoidance and navigation; robot team communication and cooperation; robotics for the handicapped. Space Robotics Laboratory http://www.ri.cmu.edu/labs/lab_34.html Computer Graphics Lab http://www.ri.cmu.edu/labs/lab_35.html http://www.cs.cmu.edu/groups/graphics/graphics.html Modeling, animation, and rendering of 3-D scenes ISL http://www.ri.cmu.edu/labs/lab_4.html http://www.cs.cmu.edu/afs/cs.cmu.edu/project/pcvision/www/ Shape Deposition Lab http://www.ri.cmu.edu/labs/lab_44.html http://www.cs.cmu.edu/~sdm/ Shape Deposition Manufacturing (SDM) is a solid freeform fabrication process which systemically combines material deposition with material removal processes. Our mission is to: enable the rapid manufacture of high-quality, complex designs which could not be practically fabricated with conventional manufacturing processes take advantage of the vast, existing CNC milling machine infrastructure throughout the world by creating SFF processes which can be implemented by simply adding deposition apparatus to a CNC machine. Affect Analysis Group http://www.ri.cmu.edu/labs/lab_45.html http://www.cs.cmu.edu/afs/cs/project/face/www/Facial.htm The face is a rich source of information about human behavior. Facial displays indicate emotion, pain, brain function and pathology, and regulate social behavior. Manual methods of coding facial behavior are labor intensive, semi-quantitative, and difficult to standardize across laboratories or over time. With few exceptions, current approaches to automated analysis focus on a small set of prototypic expressions (e.g., anger or joy), which facilitates analysis. In daily life, prototypic expressions occur relatively infrequently, and emotion more often is communicated by change in one or two discrete features, such as tightening the lips in anger. To capture the subtlety of human emotion and non-verbal communication, our interdisciplinary team of computer scientists and psychologists developed the first version of Automated Face Analysis. Automated Face Analysis quantifies subtle changes in facial motion and demonstrates concurrent validity with human observers using the Facial Action Coding System. Continuing system development is part of a larger goal of developing computer systems that can detect human activity, recognize the people involved, understand their behavior, and respond appropriately. Tissue Engineering http://www.ri.cmu.edu/labs/lab_46.html http://www.cs.cmu.edu/~tissue/ Tissue Engineering is a multidisciplinary field that applies the principles of biology and engineering to develop tissue substitutes to restore, maintain, or improve the function of diseased or damaged human tissues. One approach for engineering tissue involves seeding biodegradable scaffolds with donor cells and/or growth factors, then culturing and implanting the scaffolds to induce and direct the growth of new, healthy tissue. The need for bone substitutes is particularly important. Bone substitutes are often required to help repair or replace damaged or diseased tissues in cases ranging from trauma, to congenital and degenerative diseases, to cancer, to cosmetics. Our vision for creating tissue engineered bone is an advanced CAD/CAM (computer-aided-design/computer-aided-manufacturing) bioreactor system capable of growing large-scale, customized bone substitutes as depicted in the figure above. Our current research involves not only laying the foundation for several of the components required for realizing such an advanced system, but also gaining knowledge and developing components that will have clinical relevance in the nearer term. MRCAS http://www.ri.cmu.edu/labs/lab_47.html http://www.mrcas.ri.cmu.edu/ The MRCAS Laboratory is the main laboratory of the Center for Medical Robotics and Computer Assisted Surgery. Our research involves both planning aspects of computer-assisted surgery, e.g., medical image computing and surgical simulation, and execution aspects, e.g., intraoperative sensing, registration, and actuation. Current projects include the HipNav system for total hip replacement surgery, the Image Overlay system for enhanced visualization of anatomical structures during surgery, projects simulating knee surgery and soft tissue properties, and the Intelligent Instrument project for enhanced manual accuracy in opthalmological microsurgery. Distributed Multi-Agent Systems http://www.ri.cmu.edu/labs/lab_48.html Evolutionary Computation http://www.ri.cmu.edu/labs/lab_49.html ICLL http://www.ri.cmu.edu/labs/lab_5.html http://www.ozone.ri.cmu.edu/ Problems of large-scale coordination and logistics are ubiquitous, and better solutions are becoming increasingly critical in many domains. In manufacturing, trends toward industrial globalization and constrained market focus on high value-adding products, together with new coordination concepts such as electronic marketplaces, require organizations to become more agile. Military command and control infra-structure is faced with shrinking budgets and personnel, even though current geopolitical realities demand improved capability for rapid crisis-action mission planning and deployment. The rising cost of health care places a premium on more efficient methods for administration and delivery. Intelligent systems technologies provide new opportunities for addressing such problems of large-scale planning, scheduling and control. The Intelligent Coordination and Logistics Laboratory (ICLL) is developing new theories, techniques and software technologies that capitalize on these opportunities and enable flexible, robust, efficient, and high quality management and control of complex organizations. Our research is tackling fundamental technological challenges relating to problem complexity and solution/system scalability, decision-making under diverse and complex constraints, time-stressed decision-making in dynamic domains, human-computer collaboration, multi-agent and distributed decision-making, and solution/system reconfigurability, reuse and self-improvement. Methodologically, our research is driven by the requirements and complexities of actual applications; we are developing, validating and transitioning intelligent planning and scheduling tools in a variety of application contexts spanning manufacturing management, transportation logistics, and space mission planning. Face Group http://www.ri.cmu.edu/labs/lab_51.html We are conducting research on a variety of problems related to perception and understanding of human faces. MultiRobot Lab http://www.ri.cmu.edu/labs/lab_52.html http://www.cs.cmu.edu/~multirobotlab/ In the MultiRobot Lab at CMU we are interested in building and studying teams of robots that operate in dynamic and uncertain environments [1]. Our research focuses specifically on issues of multiagent communication, cooperation and learning. We experiment with and test our theories in simulation and on a number of real robot testbeds. 3D Computer Vision Group http://www.ri.cmu.edu/labs/lab_53.html http://www.cs.cmu.edu/~3dvision/ Our group studies fundamental problems of 3-D computer vision with a concentration on applications of modeling, recognition, and free-form surface matching. We investigate these problems over a range of physical scales and with a variety of sensors. To efficiently solve surface matching problems, we have developed novel representations, and we are working on algorithms to incorporate machine learning and artificial intelligence techniques into the recognition process. The domains we consider cover a range of scales, including small-scale object modeling and recognition, medium-scale modeling of building interiors, and large-scale environment mapping and localization. We exploit the fact that many aspects of these problems that are independent of scale, which allows us to use a common base of general algorithms. At the same time, we explore the issues specific to each domain. From a sensing standpoint, we employ a variety of devices capable of measuring 3-D data. Current sensing systems include desktop laser rangefinders, field-deployable scanning and single-line laser rangefinders (mounted on autonomous vehicles), stereo camera systems, and a 3-D sonar system. For representing free-form surfaces, we primarily use triangular meshes. Our group has developed new representations to aid in solving surface matching problems, including harmonic maps and spin-image signatures. These representations are examples of surface signatures, meaning they distinctively encode local properties of arbitrary points on a free-form surface. The Robotic Performance Lab http://www.ri.cmu.edu/labs/lab_54.html The Synthetic Performance Lab http://www.ri.cmu.edu/labs/lab_55.html Intelligent Sensor, Measurement, and Control Lab http://www.ri.cmu.edu/labs/lab_6.html http://www.cs.cmu.edu/afs/cs/project/sensor-9/ftp/www/papers.html We do applied research in sensor-based measurent and control. This research comprises inspection robotics, stereoscopic displays, online process monitoring and control, medical (and other) sensor data fusion and display, and environmental sensing. Our primary focus is on "difficult measurements in difficult environments." For example, we have developed a tetherless light weight inspection robot for finding cracks and corrosion on aircraft skins. Other applications that can use the robotics and telepresence technologies we developed in this context include landmine clearing, contraband, explosives, and weapons detection, hazardous materials cleanup, and other scenarios in which "expendible", "low metal content", and "field assembled" are important. Our publications [[14]] are accessible for reading online as PDF or for downloading as PostScript files. Interactive Systems Lab http://www.ri.cmu.edu/labs/lab_7.html http://www.cs.cmu.edu/ The Interactive Systems Laboratories are located at SCS-CMU [[14]] in Pittsburgh and at University of Karlsruhe [[15]] in Germany. The ISL aim to develop user interfaces that improve human-machine and human-to-human communication. Two challenging examples of the laboratories' interests are the development of a speech-to-speech translation system (the JANUS project) and multimodal interfaces (the INTERACT project). Our first demonstration of JANUS (in early `93) has shown that speaker-independent, continuous speech-to-speech translation is possible. The system was first limited in vocabulary size, and could not accept ill-formed conversational speech. We have since extended its early success to JANUS-II, which now also handles ill-formed spontaneously spoken language and an open vocabulary in a given domain of discourse. We are continuing our efforts to provide greater robustness and portability to new languages (English, German, Spanish, Korean, Japanese) and new domains. This involves new inroads in robust understanding of spoken language, improved speech recognition methods, as well as more flexible, interactive ways of deploying such a system to meet natural multi-lingual communication needs. The purpose of the INTERACT project is to enhancing human-computer communication by the processing and combination of multiple communication modalities known to be helpful in human communicative situations. Among others, we seek to derive a better model of where a person is in a room, who he/she might be talking to, and what he/she is saying despite the presence of jamming speakers and sounds in the room (the cocktail party effect). We are also working to interpret the joint meaning of gestures and handwriting in conjunction with speech, so that computer applications ("assistants") can carry out actions more robustly and naturally and in more flexible ways. Several human-computer interaction tasks are explored to see how automatic gesture, speech and handwriting recognition, face and eye tracking, lipreading and sound source localization can all help to make human-computer interaction easier and more natural. To be easy to use, computer systems must also be able to learn and to adapt to a changing environment and growing demands of a user. Toward this end, we are working on various statistical and connectionist machine learning and modeling strategies to advance the state of the art, particularly as applied to speech, language, visual and interactive signal processing. We are collaborating with other faculty to develop and enhance algorithms, that have the required properties for deployment in the real world. Manipulation Lab http://www.ri.cmu.edu/labs/lab_9.html http://www.cs.cmu.edu/afs/cs/project/mlab/www/home.html The Manipulation Laboratory at Carnegie Mellon University investigates fundamental modes of manipulation under uncertainty. Our goal is to produce robots that can perform a variety of tasks in the physical world, ranging from industrial assembly to everyday chores. Examples include prepositioning parts for camcorder assembly to sorting papers on a desktop. Our key contribution has been to elucidate and harness natural sources of information. Often, when asked to name sources of information researchers think of simple sensors such as cameras, light detectors, and strain gauges. They forget that action is as much a source of information as it is a source of uncertainty. Dropping a book on a desk is often the best way to know that the book is on the table. More complicated mechanical information appears in dynamic settings. Pushing on a coffee cup with a sensating finger provides a combination of mechanical and sensory information that allows the robot to determine the cup's shape and pose. Many techniques such as these were first developed in the Manipulation Laboratory in the context of hands and arms interacting with objects in the world. They are now commonplace in other domains, such as mobile robotics. Software automation has become a natural part of human life. In the future this automation will extend to physical devices. Today we can place orders for goods over the internet, but humans still pack and ship these orders. In the future, we will be able to go grocery shopping without human intervention. Today, we can call up cameras to view scenery in Hawaii or New York. In the future we will be able to sample the plants and rocks we see at such distances. The Manipulation Laboratory is contributing with fundamental research into the nature of action and sensing and their natural connections.