Publications

Abstract not provided.

Abstract not provided.

Modern security control rooms gather video and sensor feeds from tens to hundreds of cameras. Advanced camera analytics can detect motion from individual video streams and convert unexpected motion into alarms, but the interpretation of these alarms depends heavily upon human operators. Unfortunately, these operators can be overwhelmed when a large number of events happen simultaneously, or lulled into complacency due to frequent false alarms. This LDRD project has focused on improving video surveillance-based security systems by changing the fundamental focus from the cameras to the targets being tracked. If properly integrated, more cameras shouldn’t lead to more alarms, more monitors, more operators, and increased response latency but instead should lead to better information and more rapid response times. For the course of the LDRD we have been developing algorithms that take live video imagery from multiple video cameras, identify individual moving targets from the background imagery, and then display the results in a single 3D interactive video. In this document we summarize the work in developing this multi-camera, multi-target system, including lessons learned, tools developed, technologies explored, and a description of current capability.

The Site Exploitation System for Situational Awareness ( SESSA ) tool kit , developed by Sandia National Laboratories (SNL) , is a comprehensive de cision support system for crime scene data acquisition and Sensitive Site Exploitation (SSE). SESSA is an outgrowth of another SNL developed decision support system , the Building R estoration Operations Optimization Model (BROOM), a hardware/software solution for data acquisition, data management, and data analysis. SESSA was designed to meet forensic crime scene needs as defined by the DoD's Military Criminal Investigation Organiza tion (MCIO) . SESSA is a very comprehensive toolki t with a considerable amount of database information managed through a Microsoft SQL (Structured Query Language) database engine, a Geographical Information System (GIS) engine that provides comprehensive m apping capabilities, as well as a an intuitive Graphical User Interface (GUI) . An electronic sketch pad module is included. The system also has the ability to efficiently generate necessary forms for forensic crime scene investigations (e.g., evidence submittal, laboratory requests, and scene notes). SESSA allows the user to capture photos on site, and can read and generate ba rcode labels that limit transcription errors. SESSA runs on PC computers running Windows 7, but is optimized for touch - screen tablet computers running Windows for ease of use at crime scenes and on SSE deployments. A prototype system for 3 - dimensional (3 D) mapping and measur e ments was also developed to complement the SESSA software. The mapping system employs a visual/ depth sensor that captures data to create 3D visualizations of an interior space and to make distance measurements with centimeter - level a ccuracy. Output of this 3D Model Builder module provides a virtual 3D %22walk - through%22 of a crime scene. The 3D mapping system is much less expensive and easier to use than competitive systems. This document covers the basic installation and operation of th e SESSA tool kit in order to give the user enough information to start using the tool kit . SESSA is currently a prototype system and this documentation covers the initial release of the tool kit . Funding for SESSA was provided by the Department of Defense (D oD), Assistant Secretary of Defense for Research and Engineering (ASD(R&E)) Rapid Fielding (RF) organization. The project was managed by the Defense Forensic Science Center (DFSC) , formerly known as the U.S. Army Criminal Investigation Laboratory (USACIL) . ACKNOWLEDGEMENTS The authors wish to acknowledge the funding support for the development of the Site Exploitation System for Situational Awareness (SESSA) toolkit from the Department of Defense (DoD), Assistant Secretary of Defense for Research and Engineering (ASD(R&E)) Rapid Fielding (RF) organization. The project was managed by the Defense Forensic Science Center (DFSC) , formerly known as the U.S. Army Criminal Investigation Laboratory (USACIL). Special thanks to Mr. Garold Warner, of DFSC, who served as the Project Manager. Individuals that worked on the design, functional attributes, algorithm development, system arc hitecture, and software programming include: Robert Knowlton, Brad Melton, Robert Anderson, and Wendy Amai.

This report documents a three-year to develop technology that enables mobile robots to perform autonomous assembly tasks in unstructured outdoor environments. This is a multi-tier problem that requires an integration of a large number of different software technologies including: command and control, estimation and localization, distributed communications, object recognition, pose estimation, real-time scanning, and scene interpretation. Although ultimately unsuccessful in achieving a target brick stacking task autonomously, numerous important component technologies were nevertheless developed. Such technologies include: a patent-pending polygon snake algorithm for robust feature tracking, a color grid algorithm for uniquely identification and calibration, a command and control framework for abstracting robot commands, a scanning capability that utilizes a compact robot portable scanner, and more. This report describes this project and these developed technologies.

Improvised Explosive Device (IED) defeat (IEDD) operations can involve intricate operations that exceed the current capabilities of the grippers on board current bombsquad robots. The Shadow Dexterous Hand from the Shadow Robot Company or 'ShadowHand' for short (www.shadowrobot.com) is the first commercially available robot hand that realistically replicates the motion, degrees-of-freedom and dimensions of a human hand (Figure 1). In this study we evaluate the potential for the ShadowHand to perform potential IED defeat tasks on a mobile platform.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

The RoboHound{trademark} Project was a three-year, multiphase project at Sandia National Laboratories to build and refine a working prototype trace explosive detection system as a tool for a commercial robot. The RoboHound system was envisioned to be a tool for emergency responders to test suspicious items (i.e., packages or vehicles) for explosives while maintaining a safe distance. The project investigated combining Sandia's expertise in trace explosives detection with a wheeled robotic platform that could be programmed to interrogate suspicious items remotely for the presence of explosives. All of the RoboHound field tests were successful, especially with regards to the ability to collect and detect trace samples of RDX. The project has gone from remote sampling with human intervention to a fully automatic system that requires no human intervention until the robot returns from a sortie. A proposal is being made for additional work leading towards commercialization.

Mobile manipulator systems used by emergency response operators consist of an articulated robot arm, a remotely driven base, a collection of cameras, and a remote communications link. Typically the system is completely teleoperated, with the operator using live video feedback to monitor and assess the environment, plan task activities, and to conduct the operations via remote control input devices. The capabilities of these systems are limited, and operators rarely attempt sophisticated operations such as retrieving and utilizing tools, deploying sensors, or building up world models. This project has focused on methods to utilize this video information to enable monitored autonomous behaviors for the mobile manipulator system, with the goal of improving the overall effectiveness of the human/robot system. Work includes visual servoing, visual targeting, utilization of embedded video in 3-D models, and improved methods of camera utilization and calibration.

This activity brought two robotic mobile manipulation systems developed by Sandia National Laboratories to the Maneuver Support Center (MANSCEN) at Ft. Leonard Wood for the following purposes: Demonstrate advanced manipulation and control capabilities; Apply manipulation to hazardous activities within MANSCEN mission space; Stimulate thought and identify potential applications for future mobile manipulation applications; and Provide introductory knowledge of manipulation to better understand how to specify capability and write requirements.

The need for a telerobotic vehicle with hazard sensing and integral manipulation capabilities has been identified for use in transportation accidents where nuclear weapons are involved. The Accident Response Mobile Manipulation System (ARMMS) platform has been developed to provide remote dexterous manipulation and hazard sensing for the Accident Response Group (ARG) at Sandia National Laboratories. The ARMMS' mobility platform is a military HMMWV [High Mobility Multipurpose Wheeled Vehicle] that is teleoperated over RF or Fiber Optic communication channels. ARMMS is equipped with two high strength Schilling Titan II manipulators and a suite of hazardous gas and radiation sensors. Recently, a modular telerobotic control architecture call SMART (Sandia Modular Architecture for Robotic and Teleoperation) has been applied to ARMMS. SMART enables input devices and many system behaviors to be rapidly configured in the field for specific mission needs. This paper summarizes current SMART developments applied to ARMMS.