Evolving behaviour trees for supervisory control of robot swarms
- PDF / 2,621,187 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 100 Downloads / 212 Views
ORIGINAL ARTICLE
Evolving behaviour trees for supervisory control of robot swarms Elliott Hogg1 · Sabine Hauert1 · David Harvey1,2 · Arthur Richards1 Received: 20 May 2020 / Accepted: 13 September 2020 / Published online: 18 October 2020 © The Author(s) 2020
Abstract Supervisory control of swarms is essential to their deployment in real-world scenarios to both monitor their operation and provide guidance. We explore mechanisms by which humans can provide supervisory control to swarms to improve their performance. Rather than have humans guess the correct form of supervisory control, we use artificial evolution to learn effective human-readable strategies. Behaviour trees are applied to represent human-readable decision strategies which are produced through evolution. These strategies can be thoroughly tested and can provide knowledge to be used in the future in a variety of scenarios. A simulated set of scenarios are investigated where a swarm of robots have to explore varying environments and reach sets of objectives. Effective supervisory control strategies are evolved to explore each environment using different local swarm behaviours. The evolved behaviour trees are examined in detail alongside swarm simulations to enable clear understanding of the supervisory strategies. We conclude by identifying the strengths in accelerated testing and the benefits of this approach for scenario exploration and training of human operators. Keywords Human swarm interaction · Swarm · Artificial evolution · Supervisory control · Behaviour trees
1 Introduction Growing interest in the use of swarm systems has led to new questions regarding effective design for real-world environments [19]. Although their use has great potential in areas ranging from search and rescue to automated agriculture, there are still few examples of real-world deployment. Human supervision has been proposed to improve the performance of swarming by maintaining the scalability and robustness of swarms whilst taking advantage of human intelligence [4]. Human swarm interaction (HSI) aims to adapt swarm models into hybrid systems which operate with the aid of a human operator. The operator can compensate for the limitations of swarming behaviours and increase performance by interacting with the swarm. This is achieved through the This work was presented in part at the 3rd International Symposium on Swarm Behavior and Bio-Inspired Robotics (Okinawa, Japan, November 20–22, 2019). * Elliott Hogg [email protected] 1
Bristol Robotics Laboratory, University of Bristol, Bristol, UK
Thales UK, Reading, UK
2
human’s higher-level understanding and reasoning of a task that individually, swarm agents cannot perceive. This control scheme allows the human to correct for poor performance and research has highlighted significant improvements over purely autonomous swarms [5]. In HSI, research has investigated ways in which an operator can infer high-level knowledge to the swarm to improve performance. Initial answers have defined methods to directly contro
Data Loading...
