Predicting the State of Agents Using Motion and Occupancy Grids

David Ball, Gordon Wyeth

Abstract

This paper presents an approach to predicting the future state of dynamic agents using an extension to occupancy grids that we have called motion and occupancy grids. These grids capture both the location and motion of an agent. The basis of the prediction is to model the behaviour of an agent as the probability of transitions between the states represented in the grid. Prediction can then be made using a Markov chain. The potential state explosion inherent in this method is overcome by dynamically building the state transition matrix in a tree structure. The results show that the system is able to rapidly develop probabilistic models of complex agents and predict their future state.

References

  1. Ball, D. and G. Wyeth. Modeling and Exploiting Behavior Patterns in Dynamic Environments. in 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2004. Sendai, Japan.
  2. Ross, S.M., Applied Probability Models with Optimization Applications. 1992, New York: Dover Publications, Inc.
  3. Goldberg, D. and M.J. Mataric. Reward Maximization in a Non-Stationary Mobile Robot Environment. in The Fourth International Conference on Autonomous Agents. 2000. Barcelona, Spain.
  4. Elfes, A.E. Occupancy grids: A stochastic spatial representation for active robot perception. in Sixth Conference on Uncertainty in AI. 1990.
  5. Moravec, H.P. and A.E. Elfes. High resolution maps from wide angle sonar. in Proceedings of the 1985 IEEE International Conference on Robotics and Automation. 1985. Washington, D.C, USA.
  6. Kitano, H., et al. RoboCup: The Robot World Cup Initiative. in IJCAI-95 Workshop on Entertainment and AI/ALife. 1995.
  7. Ball, D. and G. Wyeth. Multi-Robot Control in Highly Dynamic, Competitive Environments. in RoboCup 2003. 2003. Padua, Italy: Springer Verlag.
Download


Paper Citation


in Harvard Style

Ball D. and Wyeth G. (2005). Predicting the State of Agents Using Motion and Occupancy Grids . In Proceedings of the 1st International Workshop on Multi-Agent Robotic Systems - Volume 1: MARS, (ICINCO 2005) ISBN 972-8865-34-1, pages 112-121. DOI: 10.5220/0001192301120121


in Bibtex Style

@conference{mars05,
author={David Ball and Gordon Wyeth},
title={Predicting the State of Agents Using Motion and Occupancy Grids},
booktitle={Proceedings of the 1st International Workshop on Multi-Agent Robotic Systems - Volume 1: MARS, (ICINCO 2005)},
year={2005},
pages={112-121},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001192301120121},
isbn={972-8865-34-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Workshop on Multi-Agent Robotic Systems - Volume 1: MARS, (ICINCO 2005)
TI - Predicting the State of Agents Using Motion and Occupancy Grids
SN - 972-8865-34-1
AU - Ball D.
AU - Wyeth G.
PY - 2005
SP - 112
EP - 121
DO - 10.5220/0001192301120121