The Robotics Institute
 Search the site
RI | People | Sanjiv Singh

Text only version of this site

Sanjiv Singh
Research Professor

Associated centers: SRI, NREC, and FRC

Email address: ssingh@ri.cmu.edu

Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213

For more information, see my personal homepage.

Jump to: Research interests | Keywords | Projects | Publications

Research interests

I am interested in applications of robotics in outdoor, unstructured environments. Some past and current projects are:

Forceful Interaction with the world. I am interested in a class of tasks in which the interaction between a robot and the world is complex and involves large forces. The approach is to select optimal actions using physical models of the interaction, thereby making the machines more capable. Currently I am working with Howard Cannon on the ALS project to implement these ideas onto a full scaled excavator.

Navigation. In earlier work (FastNav project) we demonstrated a vehicle that used position-based path tracking to navigate at high speeds. More recently, we have developed a system that performs cross-country navigation (TUGV project). With Alex Yahja and Tony Stentz I am working on methods of efficient path planning for outdoor mobile robots.

Learning. For robots to perform well in an unstructured world, they must learn from experience; it is not possible to always provide sufficiently accurate a priori models. I am particularly interested in issues of representation and contend that solutions can be found through an analysis of the mechanics or probabilities that govern a task. We have used these ideas to automate sorting of plants (Eden project) and locate buried landmines (MURI project) .

Very Wide Angle Imaging. Robot navigation and telepresence benefit from wide field-of-view imaging. For robots operating outdoors, any more options can be considered with wide FOVs. For Telepresence, wide angle imaging provides (possibly for simeltaneous multiple users) an electronic pan-tilt device. On the Vista project we are developing devices that image upto a full 360 degrees in azimuth.

Mapping. The ABS project is investigating means of developing three dimensional maps of construction sites and buildings. The focus of this project is to produce high fidelity representations that allow computation of key parameters.

This section last updated - January 1999.

Research interest keywords

computer vision, field robotics, hazardous environments, machine learning, mobile robots, motion planning, and visual tracking

Current Projects [Past projects]

Automated Turf Management - This project deals with automated management and mowing of large areas of turf, such as golf courses, sports fields, and parks
Autonomous Mobile Assembly - The ACE project is concerned with autonomous mobile assembly.
DEPTHX: Deep Phreatic Thermal Explorer - The DEPTHX: Deep Phreatic Thermal Explorer project is developing an autonomy for underwater explorers to enable them to map their environment and plan and execute science investigations. The DEPTHX vehicle will explore the flooded caverns of the Zacaton Cenote in Mexico in 2006.
Distributed Robot Architectures - The primary objective of this project is to develop fundamental capabilities that enable multiple, distributed, heterogeneous robots to coordinate tasks that cannot be accomplished by the robots individually.
EMBER - The Ember project uses multi-agent teams, comprised of autonomous and human agents, to achieve effective results under emergency situations.
Life in the Atacama - Robotic field investigation will bring new scientific understanding of the Atacama as a habitat for life with distinct analogies to Mars.
Mars Autonomy - Long-distance marsrover navigation with minimal human intervention.
Quality of Life Technology Center - QoLT is a unique partnership between Carnegie Mellon and the University of Pittsburgh that brings together a cross-disciplinary team of technologists, clinicians, industry partners, end users, and other stakeholders to create revolutionary technologies that will improve and sustain the quality of life for all people.
Tartan Racing - Carnegie Mellon University is teaming with General Motors to compete in the 2007 DARPA Urban Challenge.
Transitional Unmanned Ground Vehicle - Cross Country Navigation
TRESTLE: Autonomous Assembly by Teams of Coordinated Robots - The TRESTLE project is developing the architectural framework necessary to coordinate robots performing complex assembly projects.
Unmanned Ground Vehicle for Security - We are developing autonomous ATVs to secure borders and facility perimeters.
Urban Challenge
VISTA - On the Vista project we are developing devices that image upto a full 360 degrees in azimuth. The imagery we are getting is ideal for estimation of egomotion (localization) as well as for extracting shape from a sequence of images.
Xavier - Perceptual, reasoning and learning abilities in autonomous mobile robots
 

Recent publications [View all 95 publications]

The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.
For updates and comments, please see these instructions.
This page maintained by robotwebmaster@ri.cmu.edu