A study of mechanisms for improving robotic group performance

Many collaborative multi-robot application domains have limited areas of operation that cause spatial conflicts between robotic teammates. These spatial conflicts can cause the team's productivity to drop with the addition of robots. This phenomenon is impacted by the coordination methods used by the team-members, as different coordination methods yield radically different productivity results. However, selecting the best coordination method to be used by teammates is a formidable task. This paper presents techniques for creating adaptive coordination methods to address this challenge. We first present a combined coordination cost measure, CCC, to quantify the cost of group interactions. Our measure is useful for facilitating comparison between coordination methods, even when multiple cost factors are considered. We consistently find that as CCC values grow, group productivity falls. Using the CCC, we create adaptive coordination techniques that are able to dynamically adjust the efforts spent on coordination to match the number of perceived coordination conflicts in a group. We present two adaptation heuristics that are completely distributed and require no communication between robots. Using these heuristics, robots independently estimate their combined coordination cost (CCC), adjust their coordination methods to minimize it, and increase group productivity. We use simulated robots to perform thousands of experiment trials to demonstrate the efficacy of our approach. We show that using adaptive coordination methods create a statistically significant improvement in productivity over static methods, regardless of the group size.

[1]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[2]  R. Arkin,et al.  Behavioral diversity in learning robot teams , 1998 .

[3]  Yoav Shoham,et al.  Boosting as a Metaphor for Algorithm Design , 2003, CP.

[4]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[5]  R. J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[6]  Michael R. M. Jenkin,et al.  A taxonomy for multi-agent robotics , 1996, Auton. Robots.

[7]  Milind Tambe,et al.  Robust Agent Teams via Socially-Attentive Monitoring , 2000, J. Artif. Intell. Res..

[8]  Sarit Kraus,et al.  Collaborative Plans for Complex Group Action , 1996, Artif. Intell..

[9]  Victor R. Lesser Evolution of the GPGP/TÆMS domain-independent coordination framework , 2002, AAMAS.

[10]  Maria Gini,et al.  Performance Evaluation of Multiple Robots in a Search and Retrieval Task , 1998 .

[11]  Bart Selman,et al.  Algorithm portfolios , 2001, Artif. Intell..

[12]  Victor R. Lesser,et al.  Evolution of the GPGP/TÆMS Domain-Independent Coordination Framework , 2002, AAMAS '02.

[13]  Milind Tambe,et al.  The Communicative Multiagent Team Decision Problem: Analyzing Teamwork Theories and Models , 2011, J. Artif. Intell. Res..

[14]  Gal A. Kaminka,et al.  Flexible Teamwork in Behavior-Based Robots , 2005, AAAI.

[15]  Dani Goldberg Design and Evaluation of Robust Behavior-Based Controllers for Distributed Multi-Robot Collection Tasks , 2001 .

[16]  Milind Tambe,et al.  Towards Flexible Teamwork , 1997, J. Artif. Intell. Res..

[17]  J Stebbins,et al.  Law of Diminishing Returns , 1944, Encyclopedia of Parallel Computing.

[18]  Bernhard Nebel,et al.  Dynamic decentralized area partitioning for cooperating cleaning robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[19]  Gaurav S. Sukhatme,et al.  Emergent bucket brigading: a simple mechanisms for improving performance in multi-robot constrained-space foraging tasks , 2001, AGENTS '01.

[20]  Guido Boella,et al.  A game theoretic approach to contracts in multiagent systems , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[21]  Pattie Maes,et al.  A Study of Territoriality: The Role of Critical Mass in Adaptive Task Division , 1996 .

[22]  Maja J. Mataric,et al.  Territorial multi-robot task division , 1998, IEEE Trans. Robotics Autom..

[23]  Nicholas R. Jennings,et al.  Socially intelligent reasoning for autonomous agents , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[24]  Michail G. Lagoudakis,et al.  Algorithm Selection using Reinforcement Learning , 2000, ICML.

[25]  Lynne E. Parker,et al.  Robot Teams: From Diversity to Polymorphism , 2002 .

[26]  Gaurav S. Sukhatme,et al.  Go ahead, make my day: Robot conflict resolution by aggressive competition , 2000 .

[27]  Tucker R. Balch The impact of diversity on performance in multi-robot foraging , 1999, AGENTS '99.

[28]  Kevin Crowston,et al.  The interdisciplinary study of coordination , 1994, CSUR.

[29]  Peter Stone,et al.  Machine Learning for Fast Quadrupedal Locomotion , 2004, AAAI.

[30]  Chris Watkins,et al.  Learning from delayed rewards , 1989 .

[31]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[32]  Maja J. Mataric,et al.  Interference as a Tool for Designing and Evaluating Multi-Robot Controllers , 1997, AAAI/IAAI.

[33]  Stanley L. Brue Retrospectives The Law of Diminishing Returns , 1993 .

[34]  Nicholas R. Jennings,et al.  The Dynamic Selection of Coordination Mechanisms , 2004, Autonomous Agents and Multi-Agent Systems.

[35]  Ching-Lai Hwang,et al.  Multiple attribute decision making : an introduction , 1995 .

[36]  Sridhar Mahadevan,et al.  Automatic Programming of Behavior-Based Robots Using Reinforcement Learning , 1991, Artif. Intell..

[37]  Tucker R. Balch,et al.  Behavior-based formation control for multirobot teams , 1998, IEEE Trans. Robotics Autom..

[38]  Gal A. Kaminka,et al.  Towards flexible teamwork in behavior-based robots: extended abstract , 2005, AAMAS '05.

[39]  Steven Minton,et al.  Selecting the Right Heuristic Algorithm: Runtime Performance Predictors , 1996, Canadian Conference on AI.

[40]  Maja J. Mataric,et al.  Reinforcement Learning in the Multi-Robot Domain , 1997, Auton. Robots.