Skip to main content
The AIG web pages make heavy use of cascading style sheet features for formatting. You may still browse the text of the site, but for best results, please use a CSS enabled browser. Netscape 6 and Mozilla 5 are good. IE 5 will do.

JPL Header

Navigation Sidebar

Main Content

Steve Schaffer
Jet Propulsion Laboratory

Title Image
Constants aren't. Variables won't.    -Murphy's Law of Programming
Steve Schaffer webcam cap for ecaps Steve Schaffer



Contact Info






Office Location


Mailing Address

Steve Schaffer
M/S: 301-260
4800 Oak Grove Dr.
Pasadena CA, 91109-8099


Steven Schaffer has worked for the Jet Propulsion Laboratory's Artificial Intelligence Group as a research programmer since May 2001. He has been involved in automated DSN antenna control and scheduling, executive modelling for research rovers, flight experiment validation, sensorweb operations, autonomous planning under uncertainty, aerobot executive control, onboard science analysis, and mission telemetry analysis. Most recently, he has worked on automating data product chain management for the constellation project. Coincidentally, he is also sometimes the AIG webmaster.

Steve holds bachelors degrees in
computer science and chemistry from Carnegie Mellon University, where he specialized in multi-agent artificial intelligence. He has worked under Gal Kaminka and Manuela Veloso on the Gamebots multi-agent team competition infrastructure. Steve recently received a masters degree in computer science from the University of Southern California.

Steve's research interests are in multi-agent problem solving, adaptive online algorithms, reasoning about uncertainty, and human-agent interaction. Outside of work, Steve enjoys motorcycling, video games, frisbee, hiking, and incinerating things using the Michele Judd Memorial Giant Fresnel Lens.

Project History


EO1/ASE Sensorweb

Expanded the onboard EO1 Science agent's capabilities to respond to events observed by a network of ground based sensors.
DSN Dish

DSN Scheduling Assistant

Developed GUI and backend planner models to assist human planners in preparing and repairing DSN schedules.

Autonomous Sciencecraft Experiment

Supported validation and operation of reactive science agent onboard the EO-1 spacecraft.

Planning With Uncertainty

Designed, implemented, and evaluated a probabilistic reasoning system to augment the existing ASPEN planner.

Autonomous Rover Control

Implemented executive model in TDL for the Rocky 7 and 8 research rover demonstrations.
DSN Dish

DSN Automation

Developed executive infrastructure and models for autonomous control of a single DSN tracking antenna.

Selected Publications

Probabilistic Reasoning for Plan Robustness
Steve Schaffer, Steve Chien, Brad Clement
International Joint Conference on Artificial Intelligence (JCAI 2005)
Edinburgh, Scotland. July 2005.

Validating the Autonomous EO-1 Science Agent
B. Cichy, S. Chien, S. Schaffer, D. Tran, G. Rabideau, R. Sherwood International Workshop on Planning and Scheduling for Space (IWPSS 2004).
Darmstadt, Germany. June 2004.

CLEaR: A Framework for Balancing Deliberation and Reactive Control
F. Fisher, D. Gaines, T. Estlin, S. Schaffer, C. Chouinard
Artificial Intelligence Planning and Scheduling (AIPS 2002): On-line Planning and Scheduling Workshop.
Toulouse, France. April 2002.

Gamebots: A 3D Virtual World Test-Bed for Multi-Agent Research
R. Adobbati, A. Marshall, A. Scholer, S. Tejada, G. Kaminka, S. Schaffer, C. Sollitto.
Second International Workshop on Infrastructure for Agents, MAS, and Scalable MAS.
Montreal, Canada. May 2001.

+ Complete AIG Listing