Thomas R. Collins

Io, Ganymede, and Callisto A Multiagent Robot Trash-Collecting Team

The Georgia Institute of Technology won the Office Cleanup event at the 1994 AAAI Robot Competition and Exhibition with a multirobot cooperating team. This article describes the design and implementation of these reactive trash-collecting robots, including details of multiagent cooperation, color vision for the detection of perceptual object classes, temporal sequencing of behaviors for task completion, and a language for specifying motor schema-based robot behaviors.

Tactical Mobile Robot Mission Specification and Execution

Abstract Georgia Tech, as part of DARPAs Tactical Mobile Robotics (TMR) Program, is developing a widerange of mission specification capabilities for the urban warfighter. These include the development of arange of easily configurable mission-specific robot behaviors suitable for various battlefield and special forces scenarios; communications planning and configuration capabilities for small teams of robotsacting in a coordinated manner; interactive graphical visual programming environments for missionspecification; and real-time analysis tools and methods for mission execution verification. This paperprovides an overview of the approach being taken by the Georgia Tech/Honeywell team and presentsa range of preliminary results for a variety of missions in both simulation and on actual robots. 1. Introduction and Overview As part of DARPAs Tactical Mobile Robotics Program, Georgia Tech is providing certain basic capabilities suitable for robotic missions in urban settings: flexible reactive behaviors suitable for specific

Reactive Speed Control System Based on Terrain Roughness Detection

Autonomous outdoor navigation requires the ability to discriminate among different types of terrain. A non-trivial problem is to manage the robot’s speed based on terrain roughness. This paper presents a speed control system for a robotic platform traveling over natural terrain. This system is based on the view of a line-scanning laser of the area just in front of the platform. Analysis of range data for roughness produced by the laser over different terrains is examined. An algorithm for managing speed through different terrain has been tested on real outdoor surfaces producing excellent performance.

An implementation of ROS on the Yellowfin autonomous underwater vehicle (AUV)

The design, testing, and mission execution of a network of autonomous underwater vehicles (AUV) is a difficult process. The design of low-level controllers requires high-fidelity hydrodynamic models for simulation, but the testing of a large network of AUVs with high-order models is computationally challenging. Also, efficiency is achieved when developers can reuse components already implemented and tested by others in the community. An integrated development system is discussed where the Robot Operating System (ROS) is used to interface a number of individual systems that could not natively communicate. The system integrates the low-level controller simulation, mission planning, and mission execution processes. Most importantly, ROS was integrated with the Mission Oriented Operating Suite (MOOS), which allowed for the use of both ROS and MOOS applications within the same robotic platform via the MOOS/ROS Bridge application. Also, the 3D globe mapping program, NASA WorldWind, was interfaced to ROS via rosjava. The target AUV for the ROS implementation was the GTRI Yellowfin, which was developed for multiple AUV collaborative missions.

Integration of reactive navigation with a flexible parallel hardware architecture

AuRA (autonomous robot architecture), a hybrid, schema-based software architecture encompassing aspects of both deliberative and reactive control is described. A flexible, real-time, message-passing hardware platform for the development of AuRA and other software architectures is also presented. To demonstrate their flexibility and portability, they were integrated within a very short period to be used in a mobile robot competition. The experience confirmed the advantages of onboard computational capability in mobile systems.<<ETX>>

Design and development of an under-ice autonomous underwater vehicle for use in Polar regions

Presented here is the initial hardware and software design of the Icefin autonomous underwater vehicle for use in under-ice missions in Antarctica. Exploration of the ocean beneath hundreds of meters of ice in Antarctica is a difficult task. However, many areas of science are interested in obtaining data from this environment and other similar environments including Jupiters moon Europa. Deployment of an unmanned underwater vehicle to obtain data beneath Earths ice shelves is much less dangerous and expensive than manned submarines or human diver deployments. However, the under-ice environment presents many unique challenges for an unmanned underwater vehicle including deployment through a small ice hole and extreme temperatures. The Icefin vehicle is designed as a modular, man portable, vertically deployed vehicle able to withstand the environmental challenges of the Polar Regions and the extreme depths required for the missions of interest. The Icefin has been designed with a full sensor suite to facilitate the necessary scientific data collection. The software suite used by the vehicle is designed around the MOOS middleware framework. This vehicle is slated to be deployed in Antarctica starting October 2014.

Bio-inspired multi-robot communication through behavior recognition

This paper focuses on enabling multi-robot teams to cooperatively perform tasks without the use of radio or acoustic communication. One key to more effective cooperative interaction in a multi-robot team is the ability to understand the behavior and intent of other robots. This is similar to the honey bee “waggle dance” in which a bee can communicate the orientation and distance of a food source. In this similar manner, our heterogenous multi-robot team uses a specific behavior to indicate the location of mine-like objects (MLOs). Observed teammate action sequences can be learned to perform behavior recognition and task-assignment in the absence of communication. We apply Conditional Random Fields (CRFs) to perform behavior recognition as an approach to task monitoring in the absence of communication in a challenging underwater environment. In order to demonstrate the use of behavior recognition of an Autonomous Underwater Vehicle (AUV) in a cooperative task, we use trajectory based techniques for model generation and behavior discrimination in experiments using simulated scenario data. Results are presented demonstrating heterogenous teammate cooperation between an AUV and an Autonomous Surface Vehicle (ASV) using behavior recognition rather than radio or acoustic communication in a mine clearing task.

Mission Specification and Control for Unmanned Aerial and Ground Vehicles for Indoor Target Discovery and Tracking

This paper describes ongoing research by Georgia Tech into the challenges of tasking and controlling heterogonous teams of unmanned vehicles in mixed indoor/outdoor reconnaissance scenarios. We outline the tools and techniques necessary for an operator to specify, execute, and monitor such missions. The mission specification framework used for the purposes of intelligence gathering during mission execution are first demonstrated in simulations involving a team of a single autonomous rotorcraft and three ground-based robotic platforms. Preliminary results including robotic hardware in the loop are also provided.

Under Ice in Antarctica: The Icefin Unmanned Underwater Vehicle Development and Deployment

Exploration of the furthest reaches of our planet, as well as other planetary bodies, typically requires the use of robotic platforms due to the extreme environments encountered. Some of the harshest conditions on earth are found in Antarctica and require the use of autonomous underwater vehicles (AUVs) to explore remote and hazardous areas beneath the ice. The custom-built Icefin under-ice unmanned underwater vehicle (UUV) has been developed for deployment in permanently ice-covered oceans, such as those found in Antarctica, with the intent of furthering relevant technology for future missions to Europa, a moon of Jupiter with an icecovered ocean. The design of the vehicle flows from program requirements that provide a road map for maximizing scientific data collection with the low-risk and low-logistical impact needed for polar science. Lessons learned from Antarctic deployment of the Icefin vehicle can be extrapolated for future polar AUV design.

Determining underwater vehicle movement from sonar data in relatively featureless seafloor tracking missions

Navigation through underwater environments is challenging given the lack of accurate positioning systems. The determination of underwater vehicle movement using an integrated acoustic sonar sensor would provide underwater vehicles with greatly increased autonomous navigation capabilities. A forward looking sonar sensor may be used for determining autonomous vehicle movement using filtering and optical flow algorithms. Optical flow algorithms have shown excellent results for vision image processing. However, they have been found difficult to implement using sonar data due to the high level of noise present, as well as the widely varying appearances of objects from frame to frame. For the bottom tracking applications considered, the simplifying assumption can be made that all features move with an equivalent direction and magnitude between frames. Statistical analysis of all estimated feature movements provides an accurate estimate of the overall shift, which translates directly to the vehicle movement. Results using acoustic sonar data are presented which illustrate the effectiveness of this methodology.