Stopping criteria for ending autonomous, single detector radiological source searches

Abstract

While the localization of radiological sources has traditionally been handled with statistical algorithms, such a task can be augmented with advanced machine learning methodologies. The combination of deep and reinforcement learning has provided learning-based navigation to autonomous, single-detector, mobile systems. However, these approaches lacked the capacity to terminate a surveying/search task without outside influence of an operator or perfect knowledge of source location (defeating the purpose of such a system). Two stopping criteria are investigated in this work for a machine learning navigated system: one based upon Bayesian and maximum likelihood estimation (MLE) strategies commonly used in source localization, and a second providing the navigational machine learning network with a “stop search” action. A convolutional neural network was trained via reinforcement learning in a 10 m × 10 m simulated environment to navigate a randomly placed detector-agent to a randomly placed source of varied strength (stopping with perfect knowledge during training). The network agent could move in one of four directions (up, down, left, right) after taking a 1 s count measurement at the current location. During testing, the stopping criteria for this navigational algorithm was based upon a Bayesian likelihood estimation technique of source presence, updating this likelihood after each step, and terminating once the confidence of the source being in a single location exceeded 0.9. A second network was trained and tested with similar architecture as the previous but which contained a fifth action: for self-stopping. The accuracy and speed of localization with set detector and source initializations were compared over 50 trials of MLE-Bayesian approach and 1000 trials of the CNN with self-stopping. The statistical stopping condition yielded a median localization error of ~1.41 m and median localization speed of 12 steps. The machine learning stopping condition yielded a median localization error of 0 m and median localization speed of 17 steps. This work demonstrated two stopping criteria available to a machine learning guided, source localization system.

Investigating the Interpretability of ML-Guided Radiological Source Searches

“…The checkpoint capturing the 842,500th episode of the one million trained was chosen as it satisfied the criteria for selection. See [15] for more details on this process.…”

“…The RL navigation model developed across [13] and [15] is used as a basis for this work, along with training scheme, simulation environment, and network architecture.…”

“…It was set to 5000 cps during feedback testing. For training and testing, collections are limited to 1 s. The considered algorithm regards only gross counts rather than a complete spectrum (as in [15]), and so no specific radioisotope is specified in the simulation. However, given the parameters, the source could be thought of as a Cs-137 point source with activity of 1.32 mCi (sample from a range of ~0.79 mCi to 1.84 mCi).…”

“…Of note, this environment does not pose extreme challenge to RSL algorithms, ML or statistical (with attenuation correction taken into account [4]). Scattering, limited attenuation, and detector response are not considered in the physics of this simulation [13,15]. Instead, the primary focus of this work is upon the interpretability of ML solutions.…”

“…The action space contains four options for moving to the neighboring grid spaces (from a top-down view: {left, right, up, and down}) and a fifth action for terminating the search. A full description of this model is available from [15]. To investigate communicating user-friendly information during the search, three generalizable information paradigms are presented to the user in real-time.…”