Abstract
Maintaining contact between the robot and plume is significant in chemical plume tracing (CPT). In the time immediately following the loss of chemical detection during the process of CPT, Track-Out activities bias the robot heading relative to the upwind direction, expecting to rapidly re-contact the plume. To determine the bias angle used in the Track-Out activity, we propose an online instance-based reinforcement learning method, namely virtual trail following (VTF). In VTF, action-value is generalized from recently stored instances of successful Track-Out activities. We also propose a collaborative VTF (cVTF) method, in which multiple robots store their own instances, and learn from the stored instances, in the same database. The proposed VTF and cVTF methods are compared with biased upwind surge (BUS) method, in which all Track-Out activities utilize an offline optimized universal bias angle, in an indoor environment with three different airflow fields. With respect to our experimental conditions, VTF and cVTF show stronger adaptability to different airflow environments than BUS, and furthermore, cVTF yields higher success rates and time-efficiencies than VTF.
Highlights
Many animals exhibit the capability of tracing the plume of chemical stimuli to its source using the olfactory sense: Pacific salmons retain odor memories of their home stream to guide homeward migration [1]; crustacean species sense the relatively rare patches of coral reef to search for their settlement habitat [2]; crabs [3] and crayfishes [4] use chemical cues to find the source of food odor; male moths [5] navigate along pheromone plume, which consists of intermittent, wind-blown patches [6] of chemical substances separated by large voids, to locate females, etc
The srs of biased upwind surge (BUS) and reverse BUS (rBUS) are similar in each group, indicating the low srs of BUS are not caused by the sign of bias angle
We have proposed an instance-based reinforcement learning (RL) method and its collaborative version, namely virtual trail following (VTF) and collaborative VTF (cVTF), for learning the bias angle used in Track-Out activity to rapidly re-contact the lost plume during the process of chemical plume tracing (CPT)
Summary
Many animals exhibit the capability of tracing the plume of chemical stimuli to its source using the olfactory sense: Pacific salmons retain odor memories of their home stream to guide homeward migration [1]; crustacean species sense the relatively rare patches of coral reef to search for their settlement habitat [2]; crabs [3] and crayfishes [4] use chemical cues to find the source of food odor; male moths [5] navigate along pheromone plume, which consists of intermittent, wind-blown patches [6] of chemical substances separated by large voids, to locate females, etc. Mobile robots capable of such feats (i.e., tracing the chemical plume to its source using the olfactory sense) can be used in sweeping mines, searching for survivors in collapsed buildings, and finding the leakage sites of hazardous chemicals. From the early 1990s, various biomimetic methods for chemical plume tracing (CPT) using mobile robots have been proposed. A class of most extensively studied biomimetic CPT methods are the ones imitating the pheromone plume tracing behavior of male moths to search for females [8]. Once the first chemical detection event occurs, the robot is controlled by the circulation process shown, where TL denotes the number of cycles from the last chemical detection event till the current time; λ and Re are the cycle limit of the Track-Out activity and plume reacquiring behavior, respectively.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
