Robohub.org
 

Finding outdoor odor sources using particle filters


by
05 April 2011



share this:

Robots with smell could be used to find sources of toxic gas, search for drugs, locate survivors under rubble or hidden mines. Robots have an advantage over sniffer dogs since they can enter dangerous areas and could potentially be deployed rapidly and at lower costs.

Most of the work on olfaction robots is done in controlled laboratory environments. Instead, Li et al. are looking at how robots can localize odor sources in outdoor environments with changing wind that can be turbulent and strong. To do this, they’ve developed a novel algorithm based on particle filters that tracks the location of the odor source over time.

Experiments were done using a two-wheeled robot equipped with a gas sensor, an anemometer (for wind measurements) and an electronic compass. The robot was placed in an outdoor 10 m × 10 m area and was asked to search for a humidifier containing liquid ethanol (odor source). To find the gas plume, the robot would perform spirals. As soon as gas was sensed, the robot followed a plume-tracing strategy to collect more information about the odor source. The videos below show the robot behavior (top) and the particle filter algorithm used (bottom).

Results show that the particle filter method is suitable for challenging outdoor odor source localization and that it outperforms Bayesian-inference-based methods.




Sabine Hauert is President of Robohub and Associate Professor at the Bristol Robotics Laboratory
Sabine Hauert is President of Robohub and Associate Professor at the Bristol Robotics Laboratory





Related posts :



#ICML2025 outstanding position paper: Interview with Jaeho Kim on addressing the problems with conference reviewing

  15 Sep 2025
Jaeho argues that the AI conference peer review crisis demands author feedback and reviewer rewards.

Apertus: a fully open, transparent, multilingual language model

  11 Sep 2025
EPFL, ETH Zurich and the Swiss National Supercomputing Centre (CSCS) released Apertus today, Switzerland’s first large-scale, open, multilingual language model.

Robots to the rescue: miniature robots offer new hope for search and rescue operations

  09 Sep 2025
Small two-wheeled robots, equipped with high-tech sensors, will help to find survivors faster in the aftermath of disasters.

#IJCAI2025 distinguished paper: Combining MORL with restraining bolts to learn normative behaviour

and   04 Sep 2025
The authors introduce a framework for guiding reinforcement learning agents to comply with social, legal, and ethical norms.

Researchers are teaching robots to walk on Mars from the sand of New Mexico

  02 Sep 2025
Researchers are closer to equipping a dog-like robot to conduct science on the surface of Mars

Engineering fantasy into reality

  26 Aug 2025
PhD student Erik Ballesteros is building “Doc Ock” arms for future astronauts.

RoboCup@Work League: Interview with Christoph Steup

and   22 Aug 2025
Find out more about the RoboCup League focussed on industrial production systems.

Interview with Haimin Hu: Game-theoretic integration of safety, interaction and learning for human-centered autonomy

and   21 Aug 2025
Hear from Haimin in the latest in our series featuring the 2025 AAAI / ACM SIGAI Doctoral Consortium participants.



 

Robohub is supported by:




Would you like to learn how to tell impactful stories about your robot or AI system?


scicomm
training the next generation of science communicators in robotics & AI


 












©2025.05 - Association for the Understanding of Artificial Intelligence