Robotic Technology for USAR Illah Nourbakhsh Robotics Lead
Robotic Technology for USAR Illah Nourbakhsh Robotics Lead NASA/Ames Research Center Illah Nourbakhsh | DHS visit | March 2004
Background – Key Secondary Affiliations § University l l l Carnegie Mellon Associate Professor (on leave) University of California Santa Cruz Adjunct Professor University of Pittsburgh, Stanford, USF collaborations § Government l l l NSF Co-PI on Agent Architectures for Urban Search & Rescue NIST PI on Instrumented Facilities for USAR standardization Chair, 2003 National Robocup Rescue exhibition § Industry l l Intel Corporation embedded robotics processor development Intel Pittsburgh robotics university lead Robotics Engineering Task Force Evolution Robotics advisor Illah Nourbakhsh | DHS visit | March 2004
Role of Robotics in USAR § Lower latency of first entry l l HAZMAT scheduling, preparation Structural analysis and approval § Lower very high human risk l l Increase accessible domain Broaden operating conditions (heat, lack of oxygen) § Human sensing augmentation l l Sensing: Infrared imaging, Environmental modeling Force multiplier Illah Nourbakhsh | DHS visit | March 2004
Role of Robotics in USAR § Lower latency of first entry § Lower human risk § Human sensing augmentation Increase survival chance and outcome for victims, decrease risk exposure and hazards to first responders. Illah Nourbakhsh | DHS visit | March 2004
Role of Robotics in Space Exploration § Lower latency of first entry § Lower human risk § Human sensing augmentation Space Exploration and USAR share common goals and therefore common technological trajectories. - synergy Illah Nourbakhsh | DHS visit | March 2004
Barriers to Success § Effective human-robot interaction § USAR robot operating system standardization § Mechatronic robot innovation § Robot – sensor interfaces § Systems-level field testing and validation Illah Nourbakhsh | DHS visit | March 2004
Barriers to Success § Effective human-robot interaction Current interfaces: fragile, inefficient and need extensive training l Human factors analysis must be applied to USAR case l Iterative interaction design of interfaces l This investment has high payoff, imagine 1: 6 human: robot § USAR robot operating system standardization § Mechatronic robot innovation § Robot – sensor interfaces § Systems-level field testing and validation Illah Nourbakhsh | DHS visit | March 2004
ROBOTS AT GROUND ZERO Photos courtesy of University of South Florida Illah Nourbakhsh | DHS visit | March 2004
Barriers to Success § Effective human-robot interaction § USAR robot operating system standardization To maximize effectiveness across research efforts, we need standardized integrations of heterogeneous robot platforms. l Decouple physical robot structure, embedded processing and high-level interaction design l USAR O. S. will lower barrier to entry for industry and research partners § Mechatronic robot innovation § Robot – sensor interfaces § Systems-level field testing and validation Illah Nourbakhsh | DHS visit | March 2004
Barriers to Success § Effective human-robot interaction § USAR robot operating system standardization § Mechatronic robot innovation No single robot design serves all search & rescue needs. l Consider USAR robotics as a set of tools dynamically assembled based on real-time demands l Robustness and price point: essential to commercial viability § Robot – sensor interfaces § Systems-level field testing and validation Illah Nourbakhsh | DHS visit | March 2004
Barriers to Success § Effective human-robot interaction § USAR robot operating system standardization § Mechatronic robot innovation § Robot – sensor interfaces Retooling existing USAR sensors for robot use. l Human-readable sensors must be dual-use l Overcome mechanical, electronic and AI obstacles § Systems-level field testing and validation Illah Nourbakhsh | DHS visit | March 2004
Barriers to Success § § § Effective human-robot interaction USAR robot operating system standardization Mechatronic robot innovation Robot – sensor interfaces Systems-level field testing and validation We must build foundational knowledge rather than individual engineered solutions. l Design > Implementation > Testing > Evaluation > Refinement > Dissemination l Instrumented test facilities, standards and evaluation methodologies are required Illah Nourbakhsh | DHS visit | March 2004
ARC and Partner Roles ARC has the on-base physical and intellectual resources and collaborators to be a prime center for rapidly maturing research and development for USAR robotics. Illah Nourbakhsh | DHS visit | March 2004
ARC Instrumented Test Facility § Instrumentation for robotics per NIST direction § Additional instruments for human factors § From NIST 3 -level to ARC: spectrum of realism and continuity § No test facility for robotics would be complete without real first responder training Illah Nourbakhsh | DHS visit | March 2004
Cooperative Test Facilities Illah Nourbakhsh | DHS visit | March 2004
USAR Test Arena Proliferation FOSTERING COLLABORATION THROUGH STANDARDS PREVIOUS COMPETITIONS AAAI Conference 2000 AUSTIN, TEXAS, USA IJCAI/AAAI Conference 2001 SEATTLE, WASHINTON, USA Robo. Cup. Rescue 2002 FUKUOKA, JAPAN AAAI Conference 2002 EDMONTON, ALBERTA, CANADA American Open 2003 PENNSYLVANIA, USA Japan Open 2003 NIIGATA, JAPAN Robo. Cup. Rescue 2003 PADUA, ITALY IJCAI/AAAI Conference 2003 YEAR-ROUND ARENAS NIST MARYLAND, USA (2000) Museum of Emerging Science 2004 COMPETITIONS American Open German Open TOKYO, JAPAN (2002) Japan Open Carnegie Mellon University Robo. Cup. Rescue Istituto Superiore Antincendi AAAI Conference PENNSYLVANIA, USA (2003) ROME, ITALY (2003) University of New Orleans LOUSIANA USA (2004) Bremen University BREMEMN GERMANY (2004) Portugal TBD LISBON, PORTUGAL (2004) ACAPULCO, MEXICO Illah Nourbakhsh | DHS visit | March 2004 LISBON, PORTUGAL CALIFORNIA, USA
USAR Interaction Design & Testing § ARC Human Factors division § ARC Human-centered Computing Area § JPL MER operation lessons § U. Pitt. Psychology test instruments Illah Nourbakhsh | DHS visit | March 2004
Modeling and Visualization § Migration of ARC tools used by scientists at MER mission ops in JPL l l Model visualization Image refinement Illah Nourbakhsh | DHS visit | March 2004
USAR Robotics Operating System § ARC, Intel and CMU cooperation l l l Modular robot architecture developed by JPL and ARC Embedded robot control board produced by Intel Robot control API for Intel XScale released by CMU Illah Nourbakhsh | DHS visit | March 2004
USAR Robotics Operating System § ARC, Intel and CMU cooperation l l l Modular robot architecture developed by JPL and ARC Embedded robot control board produced by Intel Robot control API for Intel XScale released by CMU Illah Nourbakhsh | DHS visit | March 2004
Sensor Integration § USF expertise in first responder sensor needs § CMU expertise in embedded sensor interfacing electronics and software § ARC expertise in local reasoning and interpretation Illah Nourbakhsh | DHS visit | March 2004
Sensor Integration § USF expertise in first responder sensor needs § CMU expertise in embedded sensor interfacing electronics and software § ARC expertise in local reasoning and interpretation Illah Nourbakhsh | DHS visit | March 2004
Sensor Integration § USF expertise in first responder sensor needs § CMU expertise in embedded sensor interfacing electronics and software § ARC expertise in local reasoning and interpretation Illah Nourbakhsh | DHS visit | March 2004
Sensor Integration § USF expertise in first responder sensor needs § CMU expertise in embedded sensor interfacing electronics and software § ARC expertise in local reasoning and interpretation Illah Nourbakhsh | DHS visit | March 2004
Mechatronic Robot Innovation § ARC robot control development § CMU rapid prototyping facilities Illah Nourbakhsh | DHS visit | March 2004
Mechatronic Robot Innovation § ARC robot control development § CMU rapid prototyping facilities Illah Nourbakhsh | DHS visit | March 2004
Mechatronic Robot Innovation § ARC robot control development § CMU rapid prototyping facilities Illah Nourbakhsh | DHS visit | March 2004
Mechatronic Robot Innovation § ARC robot control development § CMU rapid prototyping facilities Illah Nourbakhsh | DHS visit | March 2004
Mechatronic Robot Innovation § ARC robot control development § CMU rapid prototyping facilities Illah Nourbakhsh | DHS visit | March 2004
Simulation and Training § U. Pitt. / CMU Unreal simulation, chosen for broad dissemination as the NIST standard § Sensor model characterization: only possible in most realistic possible environments: ARC § Scorpion Ear. Bot dynamic modeling and neural net – controlled V. O. R. research Illah Nourbakhsh | DHS visit | March 2004
Simulation and Training § U. Pitt. / CMU Unreal simulation, chosen for broad dissemination as the NIST standard § Sensor model characterization: only possible in most realistic possible environments: ARC § Scorpion Ear. Bot dynamic modeling and neural net – controlled V. O. R. research Illah Nourbakhsh | DHS visit | March 2004
Simulation and Training § U. Pitt. / CMU Unreal simulation, chosen for broad dissemination as the NIST standard § Sensor model characterization: only possible in most realistic possible environments: ARC § Scorpion Ear. Bot dynamic modeling and neural net – controlled V. O. R. research Illah Nourbakhsh | DHS visit | March 2004
Simulation and Training § U. Pitt. / CMU Unreal simulation, chosen for broad dissemination as the NIST standard § Sensor model characterization: only possible in most realistic possible environments: ARC § Scorpion Ear. Bot dynamic modeling and neural net – controlled V. O. R. research Illah Nourbakhsh | DHS visit | March 2004
Systems-level Field Testing § ARC Robotics acts as a whole-system hub l l l Continuity extending beyond a student or academic year Test facility combined with evaluation methodology Industry, government and academic partnerships Illah Nourbakhsh | DHS visit | March 2004
Conclusion ARC has the on-base physical and intellectual resources and collaborators to be a prime center for rapidly maturing research and development for USAR robotics. First milestones for success: l l l Training center for USAR robotics Quantitative measurement of team effectiveness Robot prototypes that have viable commercial potential Illah Nourbakhsh | DHS visit | March 2004
Questions Thank you Illah Nourbakhsh | DHS visit | March 2004
- Slides: 36