Improving the robustness of Na?ve Physics airflow mapping, using Bayesian reasoning on a multiple hypothesis tree

Previous work on odour localisation in enclosed environments, relying on an airflow model, has faced significant limitations due to the fact that large differences between airflow topologies are predicted for only small variations in a physical map. This is due to uncertainties in the map and approximations in the modelling process. Furthermore, there are uncertainties regarding the flow direction through inlet/outlet ducts. We have presented a method for dealing with these uncertainties, by generating multiple airflow hypotheses. As the robot performs odour localisation, airflow in the environment is measured and used to adjust the confidences of the hypotheses using Bayesian inference. The best hypothesis is then selected, which allows the completion of the localisation task. We have shown experimentally that this method is capable of improving the robustness of our method for odour localisation in the presence of uncertainties, where previously it was incapable. The results further demonstrate the usefulness of naive physics for practical robotics applications.

[1]  R. Andrew Russell,et al.  Bi-modal search using complementary sensing (olfaction/vision) for odour source localisation , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[2]  Gideon Kowadlo,et al.  Naive physics for effective odour localisation , 2003 .

[3]  Ingemar J. Cox,et al.  Modeling a Dynamic Environment Using a Bayesian Multiple Hypothesis Approach , 1994, Artif. Intell..

[4]  Takamichi Nakamoto,et al.  Odor-source Localization In Clean Room By Autonomous Mobile Sensing System , 1995, Proceedings of the International Solid-State Sensors and Actuators Conference - TRANSDUCERS '95.

[5]  R. Andrew Russell,et al.  A comparison of reactive robot chemotaxis algorithms , 2003, Robotics Auton. Syst..

[6]  Donald Reid.  An algorithm for tracking multiple targets , 1978 .

[7]  Rodney M. Goodman,et al.  Swarm robotic odor localization , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[8]  R. Andrew Russell,et al.  To naively smell as no robot has smelt before , 2004, IEEE Conference on Robotics, Automation and Mechatronics, 2004..

[9]  Takamichi Nakamoto,et al.  Odor-source localization in the clean room by an autonomous mobile sensing system , 1996 .

[10]  W. Koch,et al.  On Bayesian MHT for well-separated targets in densely cluttered environment , 1995, Proceedings International Radar Conference.

[11]  Jonathan P. Bollback,et al.  Bayesian Inference of Phylogeny and Its Impact on Evolutionary Biology , 2001, Science.

[12]  Frank W. Grasso,et al.  Biomimetic robot lobster performs chemo-orientation in turbulence using a pair of spatially separated sensors: Progress and challenges , 2000, Robotics Auton. Syst..

[13]  Ingemar J. Cox,et al.  A Bayesian multiple-hypothesis approach to edge grouping and contour segmentation , 1993, International Journal of Computer Vision.

[14]  R. Andrew Russell,et al.  Using naïve physics for odor localization in a cluttered indoor environment , 2006, Auton. Robots.

[15]  Keung-Chi Ng,et al.  Uncertainty management in expert systems , 1990, IEEE Expert.