t t i i i i i i i i t t
play

T T I I I I I I I I T T University of Lbeck Institute of - PowerPoint PPT Presentation

Sep 24, 2023 •114 likes •325 views

Organic Fault-tolerant Robot Control Architecture E. Maehle, W. Brockmann, K.-E. Gropietsch A. El Sayed Auf, N. Rosemann S. Krannich, R. Maas T T I I I I I I I I T T University of Lbeck Institute of Computer Science

  1. Organic Fault-tolerant Robot Control Architecture E. Maehle, W. Brockmann, K.-E. Großpietsch A. El Sayed Auf, N. Rosemann S. Krannich, R. Maas T T I I I I I I I I T T University of Lübeck Institute of Computer Science Fraunhofer Institut AIS Institute of Computer Computer Engineering Group Sankt Augustin Engineering 11 th Colloquium Organic Computing München

  2. ORCA – Organic Robot Control Architecture Planning decisional level OCU-Architecture functional level OCUs Behaviours Memory Gait-Pattern-Gen. Reflexes Gait-Pattern-Gen. Gait-Generation / OCU Reflexes -Selection Reasoner Monitor Motor-Controller Perception Proprioception Motor-Controllers - Monitor: anomaly detection - Memory: short term history (learning) hardware level - Reasoner: hard real-time determination Motor (PWM) Motors (PWM) Gait-Pattern-Gen. Gait-Pattern-Gen. of a counteraction Sensor Modules Variant of Observer/Controller Architecture BCU = Basic Control Unit OCU = Organic Control Unit

  3. Characteristics of ORCA • Application of ORCA in complex embedded automation systems • Reduction of complexity of overall system design by structuring functionalities and providing the system with self-x-properties • Anomalies and uncertainties are treated in a uniform way, by encapsulating monitoring and reconfiguration reasoning into OCU modules (inspired by immune system) -> health signal generation • Bypassing the problem of impossibility to make complete world/environmental and fault models by means of OCU interplay • Incorporation of learning methods into the OCUs • Modular structure fits object-orientated programming style

  4. Architectural Work Package Platform: six-legged walking machine OSCAR Features: - 18 digital servos - Internal servostate feedback - Leg-(de)attachment

  5. ORCA planning level behavior level reflex/leg behavior level

  6. ORCA planning level behavior level reflex/leg behavior level

  7. Planning level: Simulator beta Health signal Temporarily forbidden regions

  8. ORCA planning level behavior level reflex/leg behavior level

  9. Behavior level • Movement behavior health signals are based on monitored events, not only on sensor health signals • Wander, avoid IR, avoid US and escape behavior OCUs share event information • Behavior OCU may notify neighboring OCUs to suppress their outputs to allow execution of a behavior “self test” • “Self tests” can include carefully executed actions where the robot might gently touch objects • OCUs can alter their health signals based on “self test” results

  10. ORCA planning level behavior level reflex/leg behavior level

  11. Reflex / Leg behavior level Gap crossing (extended search reflex)

  12. ORCA planning level behavior level reflex/leg behavior level

  13. Methodological Work Package • Lower level of architecture: – Trajectory tracking – Detection of anomalies – Compensation of anomalies  Self-optimizing, self-healing interface for higher levels, concerning – good representation of actual system state by preprocessing (anomaly compensation, virtual sensors, etc.) – the execution of commands / trajectories from higher levels

  14. Adaptive Filters for Anomaly Compensation • Use of adaptive filters for the treatment of environment-induced disturbance effects • Use of adaptive filters for the combination of fault monitoring and fault correction  Compensated faults can be ignored by higher levels (self-healing)  Results of monitoring can be mapped to health signals

  15. Self-Models for Anomaly Detection • Machine learning approach: local anomaly detection by self-models  Learn normal system behavior during periods of (more or less) self- normality model • Self-models have to be able to deal with uncertainties / anomalies within the inputs as well as within the learning stimuli output uncertainties • Self-models have to assess the quality / trustworthiness of their own output self- model • Challenge: handling of uncertainties within self-models input uncertainties reference uncertainties

  16. HS-based Blending of Strategies OCU input health • Aim: use anomaly information within a BCU signals determine strategy • Approach: blending of behaviors based on BCU health signals (HS) (self-opt) s 1 BCU • HS-Blending between s 2 BCU – a safe, but suboptimal behavior (safe) – a self-optimizing behavior • Example: process Activation input Health signal uncertainties 0 1 s 1 s 2

  17. Controlled Self-Optimization uncertain local ill-posed learning problem sequential  regularization required learning stimuli OCU Approach: incremental regularization by the SILKE approach (System to Immunize Learning Knowledge-based Elements) BCU process input uncertainties So far: convergence for zero-order sTS (self-optimization) first-order sTS (self-modelling) (for specific templates)

  18. Controlled Self-Optimization • Formal framework and proof – Analyze repetitive SILKE steps     ( ) ( ) ( ) ( ) T p o p o p u m u concerning the contraction  u U property – Here, contraction corresponds to         ( ) ( 1 ) ( ) ( ( ) ( )) o p o p o p T p constraints on the eigenvalues of a specific matrix – Matrix depends on SILKE mask , which corresponds to the desired meta-level property

  19. Controlled Self-Optimization Result: procedure for designing SILKE templates which are convergent by construction with |eig( M )| < 1 Design matrix Characteristics matrices  Formal a priori guarantees of general, dynamic system properties, even though there is online self-optimization

  20. Outlook / Final Demonstration Scenario • Final, joint demonstration scenario based on the OSCAR robot • Implement and investigate the full ORCA architecture for a rescue/monitoring scenario • Adaptive filters for compensation of anomalies • Self-optimizing system representation with the SILKE / ODIL approach for anomaly detection • Health aware behaviors and reflexes • Health aware re-planning • Generalization to other applications: („ORCA = Organic Robust Control Architecture“)

  21. References • Rosemann, N.; Brockmann, W.: Incremental Regularization to Compensate Biased Teachers in Incremental Learning. In: Proc. 2010 World Congress on Computational Intelligence, IEEE Press, Piscataway, 2010, 1963-1970 • Großpietsch, K.-E.; Silayeva, T.A.: Fault Monitoring for Hybrid Systems by Means of Adaptive Filters. In: Proc. IDIMT 2010 Conf. Jindrichuv Hradec 2010, Trauner Verlag Linz, pp. 177 – 185 • Buschermöhle, A.; Hülsmann, J.; Brockmann, W.: A Generic Concept to Increase the Robustness of Embedded Systems by Trust Management. Accepted for: 2010 IEEE Conference on Systems, Man, and Cybernetics - SMC2010, Istanbul, 10.-13.10.2010 • Jakimovski, B.; Maehle, E.: In situ self-reconfiguration of hexapod robot OSCAR using biologically inspired approaches. Climbing and Walking Robots by Behnam Miripour (Ed.), INTECH, ISBN: 978-953-307-030-8, 311-332, 2010 • Jakimovski, B.; Meyer, B.; Maehle, E.: Firefly flashing synchronization as inspiration for self-synchronization of walking robot gait patterns using a decentralized robot control architecture. Architecture of Computing Systems - ARCS 2010, 23rd International Conference, pp. 61-72, Hannover, Germany, 2010 • Jakimovski B.; Meyer B.; Maehle E.: Design ideas and development of a reconfigurable robot OSCAR-X. 13th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines - CLAWAR, 31 August – 03 September 2010, 391-398, Nagoya, Japan, 2010 • Dissertation A. El Sayed Auf: Eine Organic Computing basierte Steuerung für einen hexapoden Laufroboter unter dem Aspekt reaktiver Zuverlässigkeit und Robustheit, Lübeck, Aug. 2010

Recommend

More recommend