Carnegie Mellon University
The
Advanced Search   
  Look in
       Title     Description
  Include
       Inactive Projects

New Projects at the Robotics Institute
[Please Enter Project Name!]

[Please Enter Project Name!]

Adaptive Introspection for Robust Long Duration Autonomy
Long duration autonomy for unmanned systems is difficult to achieve as current systems are design limited to anticipated exceptions and do not adapt to long-term changes in the environment. In addition, the challenge of designing experiments for long durations that provoke unanticipated exceptions is difficult. In this project we will enable long-term operation in unpredictable environments by developing an adaptive introspection and deployment approach and evaluating the ideas in an experimental setup that will provoke exceptions.
Optimal LIDAR Sensor Configuration
This project is developing a framework that allows objective comparison between alternative LIDAR configurations.
Automated Reverse Engineering of Buildings
The goal of this project is to use data from 3D sensors to automatically reconstruct compact, accurate, and semantically rich models of building interiors.
The Aerial Robotic Infrastructure Analyst (ARIA)
The Aerial Robotic Infrastructure Analyst (ARIA) rapidly creates comprehensive, high-resolution, semantically rich 3D models of infrastructure – an interactive assistant for infrastructure inspection.
GPS-denied Localization using ground and air vehicles
In this project, we are developing mapping and localization methods that combine aerial imagery from satellite and aerial platforms with maps and perception from ground-based robots to produce integrated maps even when GPS is unavailable.
The Intelligent Workcell
This project is studying methods for augmenting industrial workcells with sensors and feedback mechanisms to enable workers and robots to operate safely in the same environment.
Micro Air Vehicle Scouts for Intelligent Semantic Mapping
The goal of this project is develop the next level of capability for a low-flying, map building MAV scout. The research will demonstrate rapid scouting in cluttered environments and acquire relevant semantically annotated maps.
Indoor Flight in Degraded Visual Environments
Our goal is to fly indoors in degraded visual environments to localize people and fire. We are developing accurate real-time localization and control to be able to fly in these challenging conditions.
Helicopter Obstacle Avoidance and Landing
In this project we develop the trajectory planning system for an autonomous helicopter. The helicopter is used for cargo delivery. To read more about the trajectory planning system see the following publications.
Simple Hands
Designing simple grippers for autonomous general purpose manipulation.
Extrinsic Dexterity
"Extrinsic Dexterity" is a way to get dexterous manipulation with a very simple hand, by coordinating finger motion with arm motion. The more common approach is to depend entirely on the fingers of the hand, which requires at least three fingers and at least nine motors. We have demonstrated Extrinsic Dexterity using the single motor of the MLab Hand, coordinated with the motions of the arm.
Harnessing Human Manipulation

Exploration of Planetary Skylights and Caves

Hand Held Force Magnifier
We have developed a novel and relatively simple method for magnifying forces perceived by an operator using a tool. A sensor measures the force between the tip of a tool and its handle held by the operator’s fingers.
Path Planning for Autonomous Vessel
A path planning system helps an autonomous surface vessel to navigate autonomously while obeying international maritime law.
Formal Models of Human Control and Interaction with Cyber-Physical Systems
Cyber-Physical Systems (CPS) encompass a large variety of systems including example future energy systems (e.g. smart grid), homeland security and emergency response, smart medical technologies, smart cars and air transportation. The goal of this project is to develop cognitively-based analytic models of human operators so that they can be integrated with models of the physical/robotic system so that the whole mixed human-CPS system can be formally verified.
Human Control of Robotic Swarms
Robotic Swarms are distributed systems whose members interact via local control laws to achieve different behaviors. The goal of the project is to develop effective methods for human-swarm interaction and control considering realistic environment and system constraints.
Traffic Data Analysis
NREC and FHWA are developing techniques for automatically analyzing large amounts of video collected from vehicles traveling on highways.