Game Theoretic Motion Planning for Multi-robot Racing

  title = {Game {Theoretic} {Motion} {Planning} for {Multi}-robot {Racing}},
  volume = {9},
  isbn = {978-3-030-05815-9 978-3-030-05816-6},
  url = {},
  abstract = {This paper presents a real-time game theoretic planning algorithm for a robotic vehicle (e.g. a drone or a car) to race competitively against multiple opponents on a racecourse. Our algorithm plans receding horizon trajectories to maximally advance the robot along the racecourse, while taking into account the opponents’ intentions and responses. We build on our previous work [5], which only considered racing with two robots. Our algorithm uses an iterative best response scheme with a new sensitivity term to find approximate Nash equilibria in the space of the multiple robots’ trajectories. The sensitivity term seeks Nash equilibria that are advantageous to the ego robot. We demonstrate our approach through extensive multi-player racing simulations, where our planner exhibits rich behaviors such as blocking, overtaking, nudging or threatening, similar to what we observe from racing with human participants. Statistics also reveal that our game theoretic planner largely outperforms a baseline model predictive controller that does not consider the opponents’ responses. Experiments are conducted with four quadrotor aerial robots to validate our approach in real time and with physical robot hardware.},
  language = {en},
  urldate = {2020-07-21},
  booktitle = {Distributed {Autonomous} {Robotic} {Systems}},
  publisher = {Springer},
  author = {Wang, Zijian and Spica, Riccardo and Schwager, Mac},
  year = {2020},
  keywords = {game\_theoretic\_planning},
  pages = {225--238}