Trust-Aware Behavior Reflection for Robot Swarm Self-Healing

The deployment of robot swarms is influenced by real-world factors, such as motor issues, sensor failure, and wind disturbances. These factors cause the appearance of faulty robots. In a decentralized swarm, sharing incorrect information from faulty robots will lead to undesired swarm behaviors, such as swarm disconnection and incorrect heading directions. We envision a system where a human operator is exerting supervisory control over a remote swarm by indicating changes in trust to the swarm via a "trust-signal". By correcting faulty behaviors, trust between the human and the swarm is maintained to facilitate human-swarm cooperation. In this research, a trust-aware behavior reflection method --Trust-R -- is designed based on a weighted mean subsequence reduced algorithm (WMSR). By using Trust-R, detected faulty behaviors are automatically corrected by the swarm in a decentralized fashion by referring to the motion status of their trusted neighbors and isolating failed robots from the others. Based on real-world scenarios, three types of robot faults -- degraded performance caused by motor wear, abnormal motion caused by system uncertainty and motion deviation caused by an external disturbance such as wind -- were simulated to test the effectiveness of Trust-R. Results show that Trust-R is effective in correcting swarm behaviors for swarm self-healing.

[1]  Ali Marjovi,et al.  Optimal spatial formation of swarm robotic gas sensors in odor plume finding , 2013, Autonomous Robots.

[2]  Shreyas Sundaram,et al.  Robustness of information diffusion algorithms to locally bounded adversaries , 2011, 2012 American Control Conference (ACC).

[3]  Cherif Foudil,et al.  Monitoring a robot swarm using a data-driven fault detection approach , 2017, Robotics Auton. Syst..

[4]  Xukai Zou,et al.  A Prototype Model for Self-Healing and Self-Reproduction In Swarm Robotics System , 2006, 2006 2nd IEEE International Symposium on Dependable, Autonomic and Secure Computing.

[5]  Andrzej Pelc,et al.  Broadcasting with locally bounded Byzantine faults , 2005, Inf. Process. Lett..

[6]  Weidong Chen,et al.  Self-healing for mobile robot networks with motion synchronization , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  John P. Lewis,et al.  The Future of Disaster Response: Humans Working with Multiagent Teams using DEFACTO , 2005, AAAI Spring Symposium: AI Technologies for Homeland Security.

[8]  Marco Dorigo,et al.  Supervised morphogenesis: Exploiting morphological flexibility of self-assembling multirobot systems through cooperation with aerial robots , 2019, Robotics Auton. Syst..

[9]  Katia P. Sycara,et al.  Human Interaction With Robot Swarms: A Survey , 2016, IEEE Transactions on Human-Machine Systems.

[10]  Shaya Wolf,et al.  Secure and Decentralized Swarm Behavior with Autonomous Agents for Smart Cities , 2018, 2018 IEEE International Smart Cities Conference (ISC2).

[11]  Vijay Kumar,et al.  Resilient consensus for time-varying networks of dynamic agents , 2017, 2017 American Control Conference (ACC).

[12]  Andrea Gasparri,et al.  Trust-based interactions in teams of mobile agents , 2016, 2016 American Control Conference (ACC).

[13]  Jonathan Timmis,et al.  Towards Fault Diagnosis in Robot Swarms: An Online Behaviour Characterisation Approach , 2017, TAROS.

[14]  Yan Li,et al.  A Survey of Autonomous Control for UAV , 2009, 2009 International Conference on Artificial Intelligence and Computational Intelligence.

[15]  Yue Wang,et al.  Co-design of Control and Scheduling for Human–Swarm Collaboration Systems Based on Mutual Trust , 2017 .

[16]  Jie Lin,et al.  Coordination of groups of mobile autonomous agents using nearest neighbor rules , 2003, IEEE Trans. Autom. Control..

[17]  Vijay Kumar,et al.  Resilient Flocking for Mobile Robot Teams , 2017, IEEE Robotics and Automation Letters.

[18]  Katia P. Sycara,et al.  Automated sequencing of swarm behaviors for supervisory control of robotic swarms , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Ben Paechter,et al.  An investigation of environmental influence on the benefits of adaptation mechanisms in evolutionary swarm robotics , 2017, GECCO.

[20]  Eric J. Leaman,et al.  Hybrid Centralized/Decentralized Control of Bacteria-Based Bio-Hybrid Microrobots , 2018, 2018 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS).

[21]  Anders Lyhne Christensen,et al.  Generic, scalable and decentralized fault detection for robot swarms , 2017, PloS one.

[22]  Francesco Mondada,et al.  Mergeable nervous systems for robots , 2017, Nature Communications.

[23]  Changjoo Nam,et al.  Predicting trust in human control of swarms via inverse reinforcement learning , 2017, 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).