Real-time distributed non-myopic task selection for heterogeneous robotic teams
- 170 Downloads
In this paper we introduce a novel algorithm for online distributed non-myopic task-selection in heterogeneous robotic teams. Our algorithm uses a temporal probabilistic representation that allows agents to evaluate their actions in the team’s joint action space while robots individually search their own action space. We use Monte-Carlo tree search to asymmetrically search through the robot’s individual action space while accounting for the probable future actions of their team members using the condensed temporal representation. This allows a distributed team of robots to non-myopically coordinate their actions in real-time. Our developed method can be applied across a wide range of tasks, robot team compositions, and reward functions. To evaluate our coordination method, we implemented it for a series of simulated and fielded hardware trials where we found that our coordination method is able to increase the cumulative team reward by a maximum of \(47.2\%\) in the simulated trials versus a distributed auction-based coordination. We also performed several outdoor hardware trials with a team of three quadcopters that increased the maximum cumulative reward by \(24.5\%\) versus a distributed auction-based coordination.
KeywordsHeterogeneous robotic teams Non-myopic coordination Robotic planning Robotic coordination Robotic fielded hardware trials
- Arkin, R. C., & Balch, T. (1998). Cooperative multiagent robotic systems. In Artificial intelligence and mobile robots.Google Scholar
- Beck, Z., Teacy, L., Rogers, A., & Jennings, N. R. (2016). Online planning for collaborative search and rescue by heterogeneous robot teams. In Proceedings of the international conference on autonomous agents & multiagent systems (pp. 1024–1033).Google Scholar
- Best, G., Cliff, O., Patten, T., Mettu, R. R., & Fitch, R. (2018). Dec-MCTS: Decentralized planning for multi-robot active perception. International Journal of Robotics Research. https://doi.org/10.1177/0278364918755924.
- Best, G., Forrai, M., Mettu, R. R., & Fitch, R. (2018). Planning-aware communication for decentralised multi-robot coordination. In Proceedings of the IEEE International Conference on Robotics and Automation.Google Scholar
- Best, G., Huang, S., & Fitch, R. (2018). Decentralised mission monitoring with spatiotemporal optimal stopping. In Proceedings of the IEEE/RSJ international conference on intelligent robots and systems.Google Scholar
- Corah, M., & Michael, N. (2018). Distributed matroid-constrained submodular maximization for multi-robot exploration: Theory and practice. Autonomous Robots. https://doi.org/10.1007/s10514-018-9778-6.
- Desrosiers, J., Dumas, Y., Solomon, M. M., & Soumis, F. (1995). Chapter 2: Time constrained routing and scheduling. In M. O. Ball, T. L. Magnanti, C. L. Monma, & G. L. Nemhauser (Eds.), Handbooks in operations research and management science (Vol. 8, pp. 35–139). ElsevierGoogle Scholar
- DJI. Matrice 100 quadcopter for developers. https://www.dji.com/matrice100.
- Faigl, J., Kulich, M., & Preucil, L. (2012). Goal assignment using distance cost in multi-robot exploration. In: Proceedings of the IEEE International Conference on Intelligent Robots and Systems (pp. 3741–3746).Google Scholar
- Fukuda, T., Nakagawa, S., Kawauchi, Y., & Buss, M. (1989). Structure decision for self organising robots based on cell structures. In Proceedings of the IEEE international conference on robotics and automation.Google Scholar
- Garivier, A., & Moulines, E. (2011). On upper-confidence bound policies for switching bandit problems. In Proceedings of the international conference on algorithmic learning theory (pp. 174–188). Berlin: Springer.Google Scholar
- Karp, R.M. (1992). On-line algorithms versus off-line algorithms: How much is it worth to know the future? In IFIP Congress (1) (Vol. 12, pp. 416–429).Google Scholar
- Kartal, B., Godoy, J., Karamouzas, I., & Guy, S. J. (2015). Stochastic tree search with useful cycles for patrolling problems. In Proceedings of the IEEE international conference on robotics and automation (ICRA) (pp. 1289–1294).Google Scholar
- Kocsis, L., & Szepesvári, C. (2006). Bandit based Monte-Carlo planning. In Proceedings of the European conference on machine learning (pp. 282–293).Google Scholar
- Labbé, M., & Michaud, F. (2014). Online global loop closure detection for large-scale multi-session graph-based SLAM. In Proceedings of the IEEE/RSJ international conference on intelligent robots and systems (pp. 2661–2666).Google Scholar
- Liu, Y., & Chopra, N. (2009). Controlled synchronization of robotic manipulators in the task space. In Proceedings of the ASME dynamic systems and control conference (pp. 443–450).Google Scholar
- Luo, L., Chakraborty, N., & Sycara, K. (2012). Competitive analysis of repeated greedy auction algorithm for online multi-robot task assignment. In Proceedings of the IEEE international conference on robotics and automation (pp. 4792–4799).Google Scholar
- Meyer, J., Sendobry, A., Kohlbrecher, S., Klingauf, U., & von Stryk, O. (2012). Comprehensive simulation of quadrotor UAVs using ROS and Gazebo. In Proceedings of the international conference on simulation, modeling and programming for autonomous robots (SIMPAR).Google Scholar
- Mills-Tettey, G. A., Stentz, A., & Dias, M. B. (2007). The dynamic Hungarian algorithm for the assignment problem with changing costs. Technical Report, Carnegie Mellon University.Google Scholar
- O. S. R. Foundation. Robot operating system. http://www.ros.org/. Accessed 7 February 2017.
- O. S. R. Foundation: Gazebo: Robot simulation made easy. http://gazebosim.org/. Accessed 13 October 2017.
- Petersen, K., Kleiner, A., & von Stryk, O. (2013). Fast task-sequence allocation for heterogeneous robot teams with a human in the loop. In Proceedings of the international conference on intelligent robots and systems (pp. 1648–1655).Google Scholar
- Smith, A. Github/smithan7. https://github.com/smithan7.
- Yoshizoe, K., Kishimoto, A., Kaneko, T., Yoshimoto, H., & Ishikawa, Y. (2011). Scalable distributed Monte-Carlo tree search. In Proceedings of the fourth annual symposium on combinatorial search.Google Scholar
- Zavlanos, M. M., Spesivtsev, L., & Pappas, G. J. (2008). A distributed auction algorithm for the assignment problem. In Proceedings of the IEEE conference on decision and control (pp. 1212–1217).Google Scholar
- Zheng, X., & Koenig, S. (2009). K-swaps: Cooperative negotiation for solving task-allocation problems. In: Proceedings of the international joint conference on artificial intelligence (Vol. 9, pp. 373–378).Google Scholar
- Zlot, R., Stentz, A., Dias, M. B., & Thayer, S. (2002). Multi-robot exploration controlled by a market economy. In Proceedings of the IEEE international conference on robotics and automation (Vol. 3, pp. 3016–3023).Google Scholar